Authors: Pratim Saha, Chengcui Zhang
Abstract: Translation-based Video Synthesis (TVS) has emerged as a vital research area in computer vision, aiming to facilitate the transformation of videos between distinct domains while preserving both temporal continuity and underlying content features. This technique has found wide-ranging applications, encompassing video super-resolution, colorization, segmentation, and more, by extending the capabilities of traditional image-to-image translation to the temporal domain. One of the principal challenges faced in TVS is the inherent risk of introducing flickering artifacts and inconsistencies between frames during the synthesis process. This is particularly challenging due to the necessity of ensuring smooth and coherent transitions between video frames. Efforts to tackle this challenge have induced the creation of diverse strategies and algorithms aimed at mitigating these unwanted consequences. This comprehensive review extensively examines the latest progress in the realm of TVS. It thoroughly investigates emerging methodologies, shedding light on the fundamental concepts and mechanisms utilized for proficient video synthesis. This survey also illuminates their inherent strengths, limitations, appropriate applications, and potential avenues for future development.
Authors: Kei Ikemura, Yiming Huang, Felix Heide, Zhaoxiang Zhang, Qifeng Chen, Chenyang Lei
Abstract: Existing depth sensors are imperfect and may provide inaccurate depth values in challenging scenarios, such as in the presence of transparent or reflective objects. In this work, we present a general framework that leverages polarization imaging to improve inaccurate depth measurements from various depth sensors. Previous polarization-based depth enhancement methods focus on utilizing pure physics-based formulas for a single sensor. In contrast, our method first adopts a learning-based strategy where a neural network is trained to estimate a dense and complete depth map from polarization data and a sensor depth map from different sensors. To further improve the performance, we propose a Polarization Prompt Fusion Tuning (PPFT) strategy to effectively utilize RGB-based models pre-trained on large-scale datasets, as the size of the polarization dataset is limited to train a strong model from scratch. We conducted extensive experiments on a public dataset, and the results demonstrate that the proposed method performs favorably compared to existing depth enhancement baselines. Code and demos are available at https://lastbasket.github.io/PPFT/.
Authors: Yuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue, Sida Peng, Yujun Shen, Xiaowei Zhou
Abstract: Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate, we posit that the underlying 3D motion can often be simple and low-dimensional. In this work, we propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators, represents the 3D content of each frame efficiently using a triplane representation, and performs iterative updates using a transformer to estimate 3D trajectories. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts. Extensive evaluation shows that our approach achieves state-of-the-art tracking performance both qualitatively and quantitatively, particularly in challenging scenarios such as out-of-plane rotation.
Authors: Reuben Tan, Ximeng Sun, Ping Hu, Jui-hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan Russell, Kate Saenko
Abstract: Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution due to their demonstrated emergent capabilities on new tasks. However, despite being trained on millions of short seconds-long videos, vLLMs are unable to understand minutes-long videos and accurately answer questions about them. To address this limitation, we propose a lightweight and self-supervised approach, Key frame-conditioned long video-LLM (Koala), that introduces learnable spatiotemporal queries to adapt pretrained vLLMs for generalizing to longer videos. Our approach introduces two new tokenizers that condition on visual tokens computed from sparse video key frames for understanding short and long video moments. We train our proposed approach on HowTo100M and demonstrate its effectiveness on zero-shot long video understanding benchmarks, where it outperforms state-of-the-art large models by 3 - 6% in absolute accuracy across all tasks. Surprisingly, we also empirically show that our approach not only helps a pretrained vLLM to understand long videos but also improves its accuracy on short-term action recognition.
Authors: Junhao Chen, Xiang Li, Xiaojun Ye, Chao Li, Zhaoxin Fan, Hao Zhao
Abstract: In this paper, we pursue a novel 3D AIGC setting: generating 3D content from IDEAs. The definition of an IDEA is the composition of multimodal inputs including text, image, and 3D models. To our knowledge, this challenging and appealing 3D AIGC setting has not been studied before. We propose the novel framework called Idea-2-3D to achieve this goal, which consists of three agents based upon large multimodel models (LMMs) and several existing algorithmic tools for them to invoke. Specifically, these three LMM-based agents are prompted to do the jobs of prompt generation, model selection and feedback reflection. They work in a cycle that involves both mutual collaboration and criticism. Note that this cycle is done in a fully automatic manner, without any human intervention. The framework then outputs a text prompt to generate 3D models that well align with input IDEAs. We show impressive 3D AIGC results that are beyond any previous methods can achieve. For quantitative comparisons, we construct caption-based baselines using a whole bunch of state-of-the-art 3D AIGC models and demonstrate Idea-2-3D out-performs significantly. In 94.2% of cases, Idea-2-3D meets users' requirements, marking a degree of match between IDEA and 3D models that is 2.3 times higher than baselines. Moreover, in 93.5% of the cases, users agreed that Idea-2-3D was better than baselines. Codes, data and models will made publicly available.
Authors: Alec Helbling, Seongmin Lee, Polo Chau
Abstract: Recently, researchers have proposed powerful systems for generating and manipulating images using natural language instructions. However, it is difficult to precisely specify many common classes of image transformations with text alone. For example, a user may wish to change the location and breed of a particular dog in an image with several similar dogs. This task is quite difficult with natural language alone, and would require a user to write a laboriously complex prompt that both disambiguates the target dog and describes the destination. We propose ClickDiffusion, a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface. We demonstrate that by serializing both an image and a multi-modal instruction into a textual representation it is possible to leverage LLMs to perform precise transformations of the layout and appearance of an image. Code available at https://github.com/poloclub/ClickDiffusion.
Authors: Alexander Vedernikov, Zhaodong Sun, Virpi-Liisa Kykyri, Mikko Pohjola, Miriam Nokia, Xiaobai Li
Abstract: Engagement measurement finds application in healthcare, education, advertisement, and services. The use of physiological and behavioral features is viable, but the impracticality of traditional physiological measurement arises due to the need for contact sensors. We demonstrate the feasibility of unsupervised remote photoplethysmography (rPPG) as an alternative for contact sensors in deriving heart rate variability (HRV) features, then fusing these with behavioral features to measure engagement in online group meetings. Firstly, a unique Engagement Dataset of online interactions among social workers is collected with granular engagement labels, offering insight into virtual meeting dynamics. Secondly, a pre-trained rPPG model is customized to reconstruct accurate rPPG signals from video meetings in an unsupervised manner, enabling the calculation of HRV features. Thirdly, the feasibility of estimating engagement from HRV features using short observation windows, with a notable enhancement when using longer observation windows of two to four minutes, is demonstrated. Fourthly, the effectiveness of behavioral cues is evaluated and fused with physiological data, which further enhances engagement estimation performance. An accuracy of 94% is achieved when only HRV features are used, eliminating the need for contact sensors or ground truth signals. The incorporation of behavioral cues raises the accuracy to 96%. Facial video analysis offers precise engagement measurement, beneficial for future applications.
Authors: Yufei Zhang, Jeffrey O. Kephart, Zijun Cui, Qiang Ji
Abstract: While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce Physics-aware Pretrained Transformer (PhysPT), which improves kinematics-based motion estimates and infers motion forces. PhysPT exploits a Transformer encoder-decoder backbone to effectively learn human dynamics in a self-supervised manner. Moreover, it incorporates physics principles governing human motion. Specifically, we build a physics-based body representation and contact force model. We leverage them to impose novel physics-inspired training losses (i.e., force loss, contact loss, and Euler-Lagrange loss), enabling PhysPT to capture physical properties of the human body and the forces it experiences. Experiments demonstrate that, once trained, PhysPT can be directly applied to kinematics-based estimates to significantly enhance their physical plausibility and generate favourable motion forces. Furthermore, we show that these physically meaningful quantities translate into improved accuracy of an important downstream task: human action recognition.
Authors: Selim Furkan Tekin, Fatih Ilhan, Tiansheng Huang, Sihao Hu, Ka-Ho Chow, Margaret L. Loper, Ling Liu
Abstract: This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The paper makes three original contributions. First, we explore the unique characteristics of few-shot learning to ensemble multiple few-shot (FS) models by creating three alternative fusion channels. Second, we introduce the concept of focal error diversity to learn the most efficient ensemble teaming strategy, rather than assuming that an ensemble of a larger number of base models will outperform those sub-ensembles of smaller size. We develop a focal-diversity ensemble pruning method to effectively prune out the candidate ensembles with low ensemble error diversity and recommend top-$K$ FS ensembles with the highest focal error diversity. Finally, we capture the complex non-linear patterns of ensemble few-shot predictions by designing the learn-to-combine algorithm, which can learn the diverse weight assignments for robust ensemble fusion over different member models. Extensive experiments on representative few-shot benchmarks show that the top-K ensembles recommended by FusionShot can outperform the representative SOTA few-shot models on novel tasks (different distributions and unknown at training), and can prevail over existing few-shot learners in both cross-domain settings and adversarial settings. For reproducibility purposes, FusionShot trained models, results, and code are made available at https://github.com/sftekin/fusionshot
Authors: Shadi Alijani, Jamil Fayyad, Homayoun Najjaran
Abstract: Deep learning models are often evaluated in scenarios where the data distribution is different from those used in the training and validation phases. The discrepancy presents a challenge for accurately predicting the performance of models once deployed on the target distribution. Domain adaptation and generalization are widely recognized as effective strategies for addressing such shifts, thereby ensuring reliable performance. The recent promising results in applying vision transformers in computer vision tasks, coupled with advancements in self-attention mechanisms, have demonstrated their significant potential for robustness and generalization in handling distribution shifts. Motivated by the increased interest from the research community, our paper investigates the deployment of vision transformers in domain adaptation and domain generalization scenarios. For domain adaptation methods, we categorize research into feature-level, instance-level, model-level adaptations, and hybrid approaches, along with other categorizations with respect to diverse strategies for enhancing domain adaptation. Similarly, for domain generalization, we categorize research into multi-domain learning, meta-learning, regularization techniques, and data augmentation strategies. We further classify diverse strategies in research, underscoring the various approaches researchers have taken to address distribution shifts by integrating vision transformers. The inclusion of comprehensive tables summarizing these categories is a distinct feature of our work, offering valuable insights for researchers. These findings highlight the versatility of vision transformers in managing distribution shifts, crucial for real-world applications, especially in critical safety and decision-making scenarios.
Authors: Muhammad Asad, Ihsan Ullah, Ganesh Sistu, Michael G. Madden
Abstract: In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with a lightweight deep network, and we adopt a probabilistic score with reconstruction error. Our methodology calculates the probability of whether the sample comes from the inlier distribution or not. This work makes two key contributions. The first is that we compute the novelty probability by linearizing the manifold that holds the structure of the inlier distribution. This allows us to interpret how the probability is distributed and can be determined in relation to the local coordinates of the manifold tangent space. The second contribution is that we improve the training protocol for the network. Our results indicate that our approach is effective at learning the target class, and it outperforms recent state-of-the-art methods on several benchmark datasets.
Authors: Simindokht Jahangard, Zhixi Cai, Shiki Wen, Hamid Rezatofighi
Abstract: Understanding human social behaviour is crucial in computer vision and robotics. Micro-level observations like individual actions fall short, necessitating a comprehensive approach that considers individual behaviour, intra-group dynamics, and social group levels for a thorough understanding. To address dataset limitations, this paper introduces JRDB-Social, an extension of JRDB. Designed to fill gaps in human understanding across diverse indoor and outdoor social contexts, JRDB-Social provides annotations at three levels: individual attributes, intra-group interactions, and social group context. This dataset aims to enhance our grasp of human social dynamics for robotic applications. Utilizing the recent cutting-edge multi-modal large language models, we evaluated our benchmark to explore their capacity to decipher social human behaviour.
Authors: Swagat Ranjit, Jian Zhang, Bijaya B. Karki
Abstract: It is important to find the polyps in a human system that helps to prevent cancer during medical diagnosis. This research discusses using a dilated convolution module along with a criss cross attention-based network to segment polyps from the endoscopic images of the colon. To gather the context information of all pixels in an image more efficiently, criss-cross attention module has played a vital role. In order to extract maximum information from dataset, data augmentation techniques are employed in the dataset. Rotations, flips, scaling, and contrast along with varying learning rates were implemented to make a better model. Global average pooling was applied over ResNet50 that helped to store the important details of encoder. In our experiment, the proposed architecture's performance was compared with existing models like U-Net, DeepLabV3, PraNet. This architecture outperformed other models on the subset of dataset which has irregular polyp shapes. The combination of dilated convolution module, RCCA, and global average pooling was found to be effective for irregular shapes. Our architecture demonstrates an enhancement, with an average improvement of 3.75% across all metrics when compared to existing models.
Authors: Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka
Abstract: We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since this objective applies to each generation independently, Diffusion-KTO does not require collecting costly pairwise preference data nor training a complex reward model. Instead, our objective requires simple per-image binary feedback signals, e.g. likes or dislikes, which are abundantly available. After fine-tuning using Diffusion-KTO, text-to-image diffusion models exhibit superior performance compared to existing techniques, including supervised fine-tuning and Diffusion-DPO, both in terms of human judgment and automatic evaluation metrics such as PickScore and ImageReward. Overall, Diffusion-KTO unlocks the potential of leveraging readily available per-image binary signals and broadens the applicability of aligning text-to-image diffusion models with human preferences.
Authors: Pei Wang, Zhaowei Cai, Hao Yang, Ashwin Swaminathan, R. Manmatha, Stefano Soatto
Abstract: Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and dynamically accommodate different types of objects without heuristic designs. In addition, the unified architecture allows us to use data augmentation with synthetic masks and captions to further improve model generalization. Experiments demonstrate that MQ-Former can not only effectively handle multiple segmentation datasets and tasks compared to specialized state-of-the-art models with competitive performance, but also generalize better to open-set segmentation tasks, evidenced by over 7 points higher performance than the prior art on the open-vocabulary SeginW benchmark.
Authors: Yi Li, Xin Xie, Lina Lei, Haiyan Fu, Yanqing Guo
Abstract: The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation. Linear relationship acts as the basic assumption in most existing approaches, while applied to different aspects including features, models or labels. However, the linear assumption is hard to conform with the element dimension increases and suffers from the limit that having to obtain both ends of the line. In this paper, we propose a novel rotation-oriented solution and model the continuous generation with an in-plane rotation over the style representation of an image, achieving a network named RoNet. A rotation module is implanted in the generation network to automatically learn the proper plane while disentangling the content and the style of an image. To encourage realistic texture, we also design a patch-based semantic style loss that learns the different styles of the similar object in different domains. We conduct experiments on forest scenes (where the complex texture makes the generation very challenging), faces, streetscapes and the iphone2dslr task. The results validate the superiority of our method in terms of visual quality and continuity.
Authors: Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang
Abstract: Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with extra conditions, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage manifests in its reduced spatial aggregation complexity, rendering it exceptionally adept at processing high-resolution images, thereby eliminating the necessity for windowing or group cached operations. Experimental results on both condition and unconditional image generation tasks demonstrate that Diffison-RWKV achieves performance on par with or surpasses existing CNN or Transformer-based diffusion models in FID and IS metrics while significantly reducing total computation FLOP usage.
Authors: Hai-Dang Huynh-Lam, Ngoc-Phuong Ho-Thi, Minh-Triet Tran, Trung-Nghia Le
Abstract: In this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context. Our method partitions the input video into temporally consecutive segments with clustering information, enabling the injection of temporal awareness into the clustering process, setting it apart from prior cluster-based summarization methods. The resulting temporal-aware clusters are then utilized to compute the final summary, using simple rules for keyframe selection and frame importance scoring. Experimental results on the SumMe dataset demonstrate the effectiveness of our proposed approach, outperforming existing unsupervised methods and achieving comparable performance to state-of-the-art supervised summarization techniques. Our source code is available for reference at \url{https://github.com/hcmus-thesis-gulu/TAC-SUM}.
Authors: Pengxiao Han, Changkun Ye, Jieming Zhou, Jing Zhang, Jie Hong, Xuesong Li
Abstract: Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer learning, and feature augmentation. In recent years, diffusion models have shown an impressive generation ability in many sub-problems of deep computer vision. However, its powerful generation has not been explored in long-tailed problems. We propose a new approach, the Latent-based Diffusion Model for Long-tailed Recognition (LDMLR), as a feature augmentation method to tackle the issue. First, we encode the imbalanced dataset into features using the baseline model. Then, we train a Denoising Diffusion Implicit Model (DDIM) using these encoded features to generate pseudo-features. Finally, we train the classifier using the encoded and pseudo-features from the previous two steps. The model's accuracy shows an improvement on the CIFAR-LT and ImageNet-LT datasets by using the proposed method.
Authors: Yu Cai, Weiwen Zhang, Hao Chen, Kwang-Ting Cheng
Abstract: Anomaly detection (AD) aims at detecting abnormal samples that deviate from the expected normal patterns. Generally, it can be trained on merely normal data without the requirement for abnormal samples, and thereby plays an important role in the recognition of rare diseases and health screening in the medical domain. Despite numerous related studies, we observe a lack of a fair and comprehensive evaluation, which causes some ambiguous conclusions and hinders the development of this field. This paper focuses on building a benchmark with unified implementation and comparison to address this problem. In particular, seven medical datasets with five image modalities, including chest X-rays, brain MRIs, retinal fundus images, dermatoscopic images, and histopathology whole slide images are organized for extensive evaluation. Twenty-seven typical AD methods, including reconstruction and self-supervised learning-based methods, are involved in comparison of image-level anomaly classification and pixel-level anomaly segmentation. Furthermore, we for the first time formally explore the effect of key components in existing methods, clearly revealing unresolved challenges and potential future directions. The datasets and code are available at \url{https://github.com/caiyu6666/MedIAnomaly}.
Authors: Sara Rojas, Julien Philip, Kai Zhang, Sai Bi, Fujun Luan, Bernard Ghanem, Kalyan Sunkavall
Abstract: Recent advancements in diffusion models have shown remarkable proficiency in editing 2D images based on text prompts. However, extending these techniques to edit scenes in Neural Radiance Fields (NeRF) is complex, as editing individual 2D frames can result in inconsistencies across multiple views. Our crucial insight is that a NeRF scene's geometry can serve as a bridge to integrate these 2D edits. Utilizing this geometry, we employ a depth-conditioned ControlNet to enhance the coherence of each 2D image modification. Moreover, we introduce an inpainting approach that leverages the depth information of NeRF scenes to distribute 2D edits across different images, ensuring robustness against errors and resampling challenges. Our results reveal that this methodology achieves more consistent, lifelike, and detailed edits than existing leading methods for text-driven NeRF scene editing.
Authors: Sachini Wickramasinghe, Dhruv Parikh, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Abstract: Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is a key technique used in military applications like remote-sensing image recognition. Vision Transformers (ViTs) are the current state-of-the-art in various computer vision applications, outperforming their CNN counterparts. However, using ViTs for SAR ATR applications is challenging due to (1) standard ViTs require extensive training data to generalize well due to their low locality; the standard SAR datasets, however, have a limited number of labeled training data which reduces the learning capability of ViTs; (2) ViTs have a high parameter count and are computation intensive which makes their deployment on resource-constrained SAR platforms difficult. In this work, we develop a lightweight ViT model that can be trained directly on small datasets without any pre-training by utilizing the Shifted Patch Tokenization (SPT) and Locality Self-Attention (LSA) modules. We directly train this model on SAR datasets which have limited training samples to evaluate its effectiveness for SAR ATR applications. We evaluate our proposed model, that we call VTR (ViT for SAR ATR), on three widely used SAR datasets: MSTAR, SynthWakeSAR, and GBSAR. Further, we propose a novel FPGA accelerator for VTR, in order to enable deployment for real-time SAR ATR applications.
Authors: Xianping Ma, Xiaokang Zhang, Xingchen Ding, Man-On Pun, Siwei Ma
Abstract: Cross-domain semantic segmentation of remote sensing (RS) imagery based on unsupervised domain adaptation (UDA) techniques has significantly advanced deep-learning applications in the geosciences. Recently, with its ingenious and versatile architecture, the Transformer model has been successfully applied in RS-UDA tasks. However, existing UDA methods mainly focus on domain alignment in the high-level feature space. It is still challenging to retain cross-domain local spatial details and global contextual semantics simultaneously, which is crucial for the RS image semantic segmentation task. To address these problems, we propose novel high/low-frequency decomposition (HLFD) techniques to guide representation alignment in cross-domain semantic segmentation. Specifically, HLFD attempts to decompose the feature maps into high- and low-frequency components before performing the domain alignment in the corresponding subspaces. Secondly, to further facilitate the alignment of decomposed features, we propose a fully global-local generative adversarial network, namely GLGAN, to learn domain-invariant detailed and semantic features across domains by leveraging global-local transformer blocks (GLTBs). By integrating HLFD techniques and the GLGAN, a novel UDA framework called FD-GLGAN is developed to improve the cross-domain transferability and generalization capability of semantic segmentation models. Extensive experiments on two fine-resolution benchmark datasets, namely ISPRS Potsdam and ISPRS Vaihingen, highlight the effectiveness and superiority of the proposed approach as compared to the state-of-the-art UDA methods. The source code for this work will be accessible at https://github.com/sstary/SSRS.
Authors: Gwanghyun Kim, Hayeon Kim, Hoigi Seo, Dong Un Kang, Se Young Chun
Abstract: Generating higher-resolution human-centric scenes with details and controls remains a challenge for existing text-to-image diffusion models. This challenge stems from limited training image size, text encoder capacity (limited tokens), and the inherent difficulty of generating complex scenes involving multiple humans. While current methods attempted to address training size limit only, they often yielded human-centric scenes with severe artifacts. We propose BeyondScene, a novel framework that overcomes prior limitations, generating exquisite higher-resolution (over 8K) human-centric scenes with exceptional text-image correspondence and naturalness using existing pretrained diffusion models. BeyondScene employs a staged and hierarchical approach to initially generate a detailed base image focusing on crucial elements in instance creation for multiple humans and detailed descriptions beyond token limit of diffusion model, and then to seamlessly convert the base image to a higher-resolution output, exceeding training image size and incorporating details aware of text and instances via our novel instance-aware hierarchical enlargement process that consists of our proposed high-frequency injected forward diffusion and adaptive joint diffusion. BeyondScene surpasses existing methods in terms of correspondence with detailed text descriptions and naturalness, paving the way for advanced applications in higher-resolution human-centric scene creation beyond the capacity of pretrained diffusion models without costly retraining. Project page: https://janeyeon.github.io/beyond-scene.
Authors: Samah Khawaled, Simon K. Warfield, Moti Freiman
Abstract: Functional Magnetic Resonance Imaging (fMRI) is vital in neuroscience, enabling investigations into brain disorders, treatment monitoring, and brain function mapping. However, head motion during fMRI scans, occurring between shots of slice acquisition, can result in distortion, biased analyses, and increased costs due to the need for scan repetitions. Therefore, retrospective slice-level motion correction through slice-to-volume registration (SVR) is crucial. Previous studies have utilized deep learning (DL) based models to address the SVR task; however, they overlooked the uncertainty stemming from the input stack of slices and did not assign weighting or scoring to each slice. In this work, we introduce an end-to-end SVR model for aligning 2D fMRI slices with a 3D reference volume, incorporating a self-attention mechanism to enhance robustness against input data variations and uncertainties. It utilizes independent slice and volume encoders and a self-attention module to assign pixel-wise scores for each slice. We conducted evaluation experiments on 200 images involving synthetic rigid motion generated from 27 subjects belonging to the test set, from the publicly available Healthy Brain Network (HBN) dataset. Our experimental results demonstrate that our model achieves competitive performance in terms of alignment accuracy compared to state-of-the-art deep learning-based methods (Euclidean distance of $0.93$ [mm] vs. $1.86$ [mm]). Furthermore, our approach exhibits significantly faster registration speed compared to conventional iterative methods ($0.096$ sec. vs. $1.17$ sec.). Our end-to-end SVR model facilitates real-time head motion tracking during fMRI acquisition, ensuring reliability and robustness against uncertainties in inputs. source code, which includes the training and evaluations, will be available soon.
Authors: Samah Khawaled, Moti Freiman
Abstract: The ability to reconstruct high-quality images from undersampled MRI data is vital in improving MRI temporal resolution and reducing acquisition times. Deep learning methods have been proposed for this task, but the lack of verified methods to quantify the uncertainty in the reconstructed images hampered clinical applicability. We introduce "NPB-REC", a non-parametric fully Bayesian framework, for MRI reconstruction from undersampled data with uncertainty estimation. We use Stochastic Gradient Langevin Dynamics during training to characterize the posterior distribution of the network parameters. This enables us to both improve the quality of the reconstructed images and quantify the uncertainty in the reconstructed images. We demonstrate the efficacy of our approach on a multi-coil MRI dataset from the fastMRI challenge and compare it to the baseline End-to-End Variational Network (E2E-VarNet). Our approach outperforms the baseline in terms of reconstruction accuracy by means of PSNR and SSIM ($34.55$, $0.908$ vs. $33.08$, $0.897$, $p<0.01$, acceleration rate $R=8$) and provides uncertainty measures that correlate better with the reconstruction error (Pearson correlation, $R=0.94$ vs. $R=0.91$). Additionally, our approach exhibits better generalization capabilities against anatomical distribution shifts (PSNR and SSIM of $32.38$, $0.849$ vs. $31.63$, $0.836$, $p<0.01$, training on brain data, inference on knee data, acceleration rate $R=8$). NPB-REC has the potential to facilitate the safe utilization of deep learning-based methods for MRI reconstruction from undersampled data. Code and trained models are available at \url{https://github.com/samahkh/NPB-REC}.
Authors: Haibo Jin, Haoxuan Che, Hao Chen
Abstract: Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection faces three problems: 1) The selected confident pseudo-labels often contain data bias, which may hurt model performance; 2) It is not easy to decide a proper threshold for sample selection as the localization task can be sensitive to noisy pseudo-labels; 3) coordinate regression does not output confidence, making selection-based self-training infeasible. To address the above issues, we propose Self-Training for Landmark Detection (STLD), a method that does not require explicit pseudo-label selection. Instead, STLD constructs a task curriculum to deal with confirmation bias, which progressively transitions from more confident to less confident tasks over the rounds of self-training. Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner. Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods consistently in both semi- and omni-supervised settings.
Authors: Zhiyuan Yu, Zheng Qin, Lintao Zheng, Kai Xu
Abstract: Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondence is to the center of the problem. Existing approaches usually treat the scene point cloud as a whole, overlooking the separation of instances. Therefore, point features could be easily polluted by other points from the background or different instances, leading to inaccurate correspondences oblivious to separate instances, especially in cluttered scenes. In this work, we propose MIRETR, Multi-Instance REgistration TRansformer, a coarse-to-fine approach to the extraction of instance-aware correspondences. At the coarse level, it jointly learns instance-aware superpoint features and predicts per-instance masks. With instance masks, the influence from outside of the instance being concerned is minimized, such that highly reliable superpoint correspondences can be extracted. The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks. At last, an efficient candidate selection and refinement algorithm is devised to obtain the final registrations. Extensive experiments on three public benchmarks demonstrate the efficacy of our approach. In particular, MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark. Code and models are available at https://github.com/zhiyuanYU134/MIRETR.
Authors: Jingyi Pan, Zipeng Wang, Lin Wang
Abstract: 3D semantic occupancy prediction is a pivotal task in the field of autonomous driving. Recent approaches have made great advances in 3D semantic occupancy predictions on a single modality. However, multi-modal semantic occupancy prediction approaches have encountered difficulties in dealing with the modality heterogeneity, modality misalignment, and insufficient modality interactions that arise during the fusion of different modalities data, which may result in the loss of important geometric and semantic information. This letter presents a novel multi-modal, i.e., LiDAR-camera 3D semantic occupancy prediction framework, dubbed Co-Occ, which couples explicit LiDAR-camera feature fusion with implicit volume rendering regularization. The key insight is that volume rendering in the feature space can proficiently bridge the gap between 3D LiDAR sweeps and 2D images while serving as a physical regularization to enhance LiDAR-camera fused volumetric representation. Specifically, we first propose a Geometric- and Semantic-aware Fusion (GSFusion) module to explicitly enhance LiDAR features by incorporating neighboring camera features through a K-nearest neighbors (KNN) search. Then, we employ volume rendering to project the fused feature back to the image planes for reconstructing color and depth maps. These maps are then supervised by input images from the camera and depth estimations derived from LiDAR, respectively. Extensive experiments on the popular nuScenes and SemanticKITTI benchmarks verify the effectiveness of our Co-Occ for 3D semantic occupancy prediction. The project page is available at https://rorisis.github.io/Co-Occ_project-page/.
Authors: Xuanyu Yi, Zike Wu, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Hanwang Zhang
Abstract: Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction of student 3D models. Despite their remarkable success, SDS-based methods often encounter geometric artifacts and texture saturation. We find out the crux is the overlooked indiscriminate treatment of diffusion time-steps during optimization: it unreasonably treats the student-teacher knowledge distillation to be equal at all time-steps and thus entangles coarse-grained and fine-grained modeling. Therefore, we propose the Diffusion Time-step Curriculum one-image-to-3D pipeline (DTC123), which involves both the teacher and student models collaborating with the time-step curriculum in a coarse-to-fine manner. Extensive experiments on NeRF4, RealFusion15, GSO and Level50 benchmark demonstrate that DTC123 can produce multi-view consistent, high-quality, and diverse 3D assets. Codes and more generation demos will be released in https://github.com/yxymessi/DTC123.
Authors: Hai-Dang Huynh-Lam, Ngoc-Phuong Ho-Thi, Minh-Triet Tran, Trung-Nghia Le
Abstract: Video summarization is a crucial research area that aims to efficiently browse and retrieve relevant information from the vast amount of video content available today. With the exponential growth of multimedia data, the ability to extract meaningful representations from videos has become essential. Video summarization techniques automatically generate concise summaries by selecting keyframes, shots, or segments that capture the video's essence. This process improves the efficiency and accuracy of various applications, including video surveillance, education, entertainment, and social media. Despite the importance of video summarization, there is a lack of diverse and representative datasets, hindering comprehensive evaluation and benchmarking of algorithms. Existing evaluation metrics also fail to fully capture the complexities of video summarization, limiting accurate algorithm assessment and hindering the field's progress. To overcome data scarcity challenges and improve evaluation, we propose an unsupervised approach that leverages video data structure and information for generating informative summaries. By moving away from fixed annotations, our framework can produce representative summaries effectively. Moreover, we introduce an innovative evaluation pipeline tailored specifically for video summarization. Human participants are involved in the evaluation, comparing our generated summaries to ground truth summaries and assessing their informativeness. This human-centric approach provides valuable insights into the effectiveness of our proposed techniques. Experimental results demonstrate that our training-free framework outperforms existing unsupervised approaches and achieves competitive results compared to state-of-the-art supervised methods.
Authors: Tao Wu, Runyu He, Gangshan Wu, Limin Wang
Abstract: Video-based visual relation detection tasks, such as video scene graph generation, play important roles in fine-grained video understanding. However, current video visual relation detection datasets have two main limitations that hinder the progress of research in this area. First, they do not explore complex human-human interactions in multi-person scenarios. Second, the relation types of existing datasets have relatively low-level semantics and can be often recognized by appearance or simple prior information, without the need for detailed spatio-temporal context reasoning. Nevertheless, comprehending high-level interactions between humans is crucial for understanding complex multi-person videos, such as sports and surveillance videos. To address this issue, we propose a new video visual relation detection task: video human-human interaction detection, and build a dataset named SportsHHI for it. SportsHHI contains 34 high-level interaction classes from basketball and volleyball sports. 118,075 human bounding boxes and 50,649 interaction instances are annotated on 11,398 keyframes. To benchmark this, we propose a two-stage baseline method and conduct extensive experiments to reveal the key factors for a successful human-human interaction detector. We hope that SportsHHI can stimulate research on human interaction understanding in videos and promote the development of spatio-temporal context modeling techniques in video visual relation detection.
Authors: Florentina Tatrin Kurniati, Daniel HF Manongga, Eko Sediyono, Sri Yulianto Joko Prasetyo, Roy Rudolf Huizen
Abstract: In the era of modern technology, object detection using the Gray Level Co-occurrence Matrix (GLCM) extraction method plays a crucial role in object recognition processes. It finds applications in real-time scenarios such as security surveillance and autonomous vehicle navigation, among others. Computational efficiency becomes a critical factor in achieving real-time object detection. Hence, there is a need for a detection model with low complexity and satisfactory accuracy. This research aims to enhance computational efficiency by selecting appropriate features within the GLCM framework. Two classification models, namely K-Nearest Neighbours (K-NN) and Support Vector Machine (SVM), were employed, with the results indicating that K-Nearest Neighbours (K-NN) outperforms SVM in terms of computational complexity. Specifically, K-NN, when utilizing a combination of Correlation, Energy, and Homogeneity features, achieves a 100% accuracy rate with low complexity. Moreover, when using a combination of Energy and Homogeneity features, K-NN attains an almost perfect accuracy level of 99.9889%, while maintaining low complexity. On the other hand, despite SVM achieving 100% accuracy in certain feature combinations, its high or very high complexity can pose challenges, particularly in real-time applications. Therefore, based on the trade-off between accuracy and complexity, the K-NN model with a combination of Correlation, Energy, and Homogeneity features emerges as a more suitable choice for real-time applications that demand high accuracy and low complexity. This research provides valuable insights for optimizing object detection in various applications requiring both high accuracy and rapid responsiveness.
Authors: Hatef Otroshi Shahreza, Christophe Ecabert, Anjith George, Alexander Unnervik, S\'ebastien Marcel, Nicol\`o Di Domenico, Guido Borghi, Davide Maltoni, Fadi Boutros, Julia Vogel, Naser Damer, \'Angela S\'anchez-P\'erez, EnriqueMas-Candela, Jorge Calvo-Zaragoza, Bernardo Biesseck, Pedro Vidal, Roger Granada, David Menotti, Ivan DeAndres-Tame, Simone Maurizio La Cava, Sara Concas, Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez, Gianpaolo Perelli, Giulia Orr\`u, Gian Luca Marcialis, Julian Fierrez
Abstract: Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) and established to investigate the use of synthetic data for training face recognition models. The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones. In the first task, the face recognition backbone was fixed and the dataset size was limited, while the second task provided almost complete freedom on the model backbone, the dataset, and the training pipeline. The submitted models were trained on existing and also new synthetic datasets and used clever methods to improve training with synthetic data. The submissions were evaluated and ranked on a diverse set of seven benchmarking datasets. The paper gives an overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets. Furthermore, the evaluation of submissions is extended to bias assessment across different demography groups. Lastly, an outlook on the current state of the research in training face recognition models using synthetic data is presented, and existing problems as well as potential future directions are also discussed.
Authors: Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu
Abstract: The boom of Generative AI brings opportunities entangled with risks and concerns. In this work, we seek a step toward a universal deepfake detection system with better generalization and robustness, to accommodate the responsible deployment of diverse image generative models. We do so by first scaling up the existing detection task setup from the one-generator to multiple-generators in training, during which we disclose two challenges presented in prior methodological designs. Specifically, we reveal that the current methods tailored for training on one specific generator either struggle to learn comprehensive artifacts from multiple generators or tend to sacrifice their ability to identify fake images from seen generators (i.e., In-Domain performance) to exchange the generalization for unseen generators (i.e., Out-Of-Domain performance). To tackle the above challenges, we propose our Discrepancy Deepfake Detector (D$^3$) framework, whose core idea is to learn the universal artifacts from multiple generators by introducing a parallel network branch that takes a distorted image as extra discrepancy signal to supplement its original counterpart. Extensive scaled-up experiments on the merged UFD and GenImage datasets with six detection models demonstrate the effectiveness of our framework, achieving a 5.3% accuracy improvement in the OOD testing compared to the current SOTA methods while maintaining the ID performance.
Authors: Dong Liang, Zhengyan Xu, Ling Li, Mingqiang Wei, Songcan Chen
Abstract: In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often training a LLE model with strict pixel-correspondence image pairs, we eliminate the need for pixel-correspondence paired training data and instead train with unpaired images. (ii) To address the disregard for negative samples and the inadequacy of their generation in existing methods, we incorporate physics-inspired contrastive learning for LLE and design the Bag of Curves (BoC) method to generate more reasonable negative samples that closely adhere to the underlying physical imaging principle. (iii) To overcome the reliance on semantic ground truths in existing methods, we propose an unsupervised regional segmentation module, ensuring regional brightness consistency while eliminating the dependency on semantic ground truths. Overall, the proposed PIE can effectively learn from unpaired positive/negative samples and smoothly realize non-semantic regional enhancement, which is clearly different from existing LLE efforts. Besides the novel architecture of PIE, we explore the gain of PIE on downstream tasks such as semantic segmentation and face detection. Training on readily available open data and extensive experiments demonstrate that our method surpasses the state-of-the-art LLE models over six independent cross-scenes datasets. PIE runs fast with reasonable GFLOPs in test time, making it easy to use on mobile devices.
Authors: Danpei Zhao, Bo Yuan, Ziqiang Chen, Tian Li, Zhuoran Liu, Wentao Li, Yue Gao
Abstract: Current remote-sensing interpretation models often focus on a single task such as detection, segmentation, or caption. However, the task-specific designed models are unattainable to achieve the comprehensive multi-level interpretation of images. The field also lacks support for multi-task joint interpretation datasets. In this paper, we propose Panoptic Perception, a novel task and a new fine-grained dataset (FineGrip) to achieve a more thorough and universal interpretation for RSIs. The new task, 1) integrates pixel-level, instance-level, and image-level information for universal image perception, 2) captures image information from coarse to fine granularity, achieving deeper scene understanding and description, and 3) enables various independent tasks to complement and enhance each other through multi-task learning. By emphasizing multi-task interactions and the consistency of perception results, this task enables the simultaneous processing of fine-grained foreground instance segmentation, background semantic segmentation, and global fine-grained image captioning. Concretely, the FineGrip dataset includes 2,649 remote sensing images, 12,054 fine-grained instance segmentation masks belonging to 20 foreground things categories, 7,599 background semantic masks for 5 stuff classes and 13,245 captioning sentences. Furthermore, we propose a joint optimization-based panoptic perception model. Experimental results on FineGrip demonstrate the feasibility of the panoptic perception task and the beneficial effect of multi-task joint optimization on individual tasks. The dataset will be publicly available.
Authors: Juan Wen (Zhengzhou University, Computer Vision Lab, ETH Zurich), Yawei Li (Computer Vision Lab, ETH Zurich), Chao Zhang (LAN-XEN, Technology, INC), Weiyan Hou (Zhengzhou University), Radu Timofte (Computer Vision Lab, ETH Zurich, Bayerische Julius-Maximilians-Universit\"at W\"urzburg), Luc Van Gool (Computer Vision Lab, ETH Zurich)
Abstract: We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address restoration challenges. While Transformer models have demonstrated excellent performance in image restoration due to their self-attention mechanism, they face limitations in complex scenarios. Leveraging recent advancements in Transformers and various attention mechanisms, our method utilizes customized attention mechanisms to enhance overall performance. DART, our novel network architecture, employs windowed attention to mimic the selective focusing mechanism of human eyes. By dynamically adjusting receptive fields, it optimally captures the fundamental features crucial for image resolution reconstruction. Efficiency and performance balance are achieved through the LongIR attention mechanism for long sequence image restoration. Integration of attention mechanisms across feature and positional dimensions further enhances the recovery of fine details. Evaluation across five restoration tasks consistently positions DART at the forefront. Upon acceptance, we commit to providing publicly accessible code and models to ensure reproducibility and facilitate further research.
Authors: Mingxin Huang, Hongliang Li, Yuliang Liu, Xiang Bai, Lianwen Jin
Abstract: Modularity plays a crucial role in the development and maintenance of complex systems. While end-to-end text spotting efficiently mitigates the issues of error accumulation and sub-optimal performance seen in traditional two-step methodologies, the two-step methods continue to be favored in many competitions and practical settings due to their superior modularity. In this paper, we introduce Bridging Text Spotting, a novel approach that resolves the error accumulation and suboptimal performance issues in two-step methods while retaining modularity. To achieve this, we adopt a well-trained detector and recognizer that are developed and trained independently and then lock their parameters to preserve their already acquired capabilities. Subsequently, we introduce a Bridge that connects the locked detector and recognizer through a zero-initialized neural network. This zero-initialized neural network, initialized with weights set to zeros, ensures seamless integration of the large receptive field features in detection into the locked recognizer. Furthermore, since the fixed detector and recognizer cannot naturally acquire end-to-end optimization features, we adopt the Adapter to facilitate their efficient learning of these features. We demonstrate the effectiveness of the proposed method through extensive experiments: Connecting the latest detector and recognizer through Bridging Text Spotting, we achieved an accuracy of 83.3% on Total-Text, 69.8% on CTW1500, and 89.5% on ICDAR 2015. The code is available at https://github.com/mxin262/Bridging-Text-Spotting.
Authors: Zaid Khan, Vijay Kumar BG, Samuel Schulter, Yun Fu, Manmohan Chandraker
Abstract: Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs. Training an LLM to write better visual programs is an attractive prospect, but it is unclear how to accomplish this. No dataset of visual programs for training exists, and acquisition of a visual program dataset cannot be easily crowdsourced due to the need for expert annotators. To get around the lack of direct supervision, we explore improving the program synthesis abilities of an LLM using feedback from interactive experience. We propose a method where we exploit existing annotations for a vision-language task to improvise a coarse reward signal for that task, treat the LLM as a policy, and apply reinforced self-training to improve the visual program synthesis ability of the LLM for that task. We describe a series of experiments on object detection, compositional visual question answering, and image-text retrieval, and show that in each case, the self-trained LLM outperforms or performs on par with few-shot frozen LLMs that are an order of magnitude larger. Website: https://zaidkhan.me/ViReP
Authors: Duy-Tho Le, Hengcan Shi, Jianfei Cai, Hamid Rezatofighi
Abstract: Diffusion models have recently gained prominence as powerful deep generative models, demonstrating unmatched performance across various domains. However, their potential in multi-sensor fusion remains largely unexplored. In this work, we introduce DifFUSER, a novel approach that leverages diffusion models for multi-modal fusion in 3D object detection and BEV map segmentation. Benefiting from the inherent denoising property of diffusion, DifFUSER is able to refine or even synthesize sensor features in case of sensor malfunction, thereby improving the quality of the fused output. In terms of architecture, our DifFUSER blocks are chained together in a hierarchical BiFPN fashion, termed cMini-BiFPN, offering an alternative architecture for latent diffusion. We further introduce a Gated Self-conditioned Modulated (GSM) latent diffusion module together with a Progressive Sensor Dropout Training (PSDT) paradigm, designed to add stronger conditioning to the diffusion process and robustness to sensor failures. Our extensive evaluations on the Nuscenes dataset reveal that DifFUSER not only achieves state-of-the-art performance with a 69.1% mIOU in BEV map segmentation tasks but also competes effectively with leading transformer-based fusion techniques in 3D object detection.
Authors: Shizhan Gong, Qi Dou, Farzan Farnia
Abstract: Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often lack desired structures such as sparsity and connectedness in their application to real-world computer vision models. A frequently used approach to inducing sparsity structures into gradient-based saliency maps is to alter the simple gradient scheme using sparsification or norm-based regularization. A drawback with such post-processing methods is their frequently-observed significant loss in fidelity to the original simple gradient map. In this work, we propose to apply adversarial training as an in-processing scheme to train neural networks with structured simple gradient maps. We show a duality relation between the regularized norms of the adversarial perturbations and gradient-based maps, based on which we design adversarial training loss functions promoting sparsity and group-sparsity properties in simple gradient maps. We present several numerical results to show the influence of our proposed norm-based adversarial training methods on the standard gradient-based maps of standard neural network architectures on benchmark image datasets.
Authors: Xiefan Guo, Jinlin Liu, Miaomiao Cui, Jiankai Li, Hongyu Yang, Di Huang
Abstract: Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless alignment between the generated image and the provided prompt persists as a formidable challenge. This paper traces the root of these difficulties to invalid initial noise, and proposes a solution in the form of Initial Noise Optimization (InitNO), a paradigm that refines this noise. Considering text prompts, not all random noises are effective in synthesizing semantically-faithful images. We design the cross-attention response score and the self-attention conflict score to evaluate the initial noise, bifurcating the initial latent space into valid and invalid sectors. A strategically crafted noise optimization pipeline is developed to guide the initial noise towards valid regions. Our method, validated through rigorous experimentation, shows a commendable proficiency in generating images in strict accordance with text prompts. Our code is available at https://github.com/xiefan-guo/initno.
Authors: Ziang Guo, Stepan Perminov, Mikhail Konenkov, Dzmitry Tsetserukou
Abstract: Many established vision perception systems for autonomous driving scenarios ignore the influence of light conditions, one of the key elements for driving safety. To address this problem, we present HawkDrive, a novel perception system with hardware and software solutions. Hardware that utilizes stereo vision perception, which has been demonstrated to be a more reliable way of estimating depth information than monocular vision, is partnered with the edge computing device Nvidia Jetson Xavier AGX. Our software for low light enhancement, depth estimation, and semantic segmentation tasks, is a transformer-based neural network. Our software stack, which enables fast inference and noise reduction, is packaged into system modules in Robot Operating System 2 (ROS2). Our experimental results have shown that the proposed end-to-end system is effective in improving the depth estimation and semantic segmentation performance. Our dataset and codes will be released at https://github.com/ZionGo6/HawkDrive.
Authors: Rajesh B, Keerthana V, Narayana Darapaneni, Anwesh Reddy P
Abstract: Introduction: Music provides an incredible avenue for individuals to express their thoughts and emotions, while also serving as a delightful mode of entertainment for enthusiasts and music lovers. Objectives: This paper presents a comprehensive approach to enhancing the user experience through the integration of emotion recognition, music recommendation, and explainable AI using GRAD-CAM. Methods: The proposed methodology utilizes a ResNet50 model trained on the Facial Expression Recognition (FER) dataset, consisting of real images of individuals expressing various emotions. Results: The system achieves an accuracy of 82% in emotion classification. By leveraging GRAD-CAM, the model provides explanations for its predictions, allowing users to understand the reasoning behind the system's recommendations. The model is trained on both FER and real user datasets, which include labelled facial expressions, and real images of individuals expressing various emotions. The training process involves pre-processing the input images, extracting features through convolutional layers, reasoning with dense layers, and generating emotion predictions through the output layer Conclusion: The proposed methodology, leveraging the Resnet50 model with ROI-based analysis and explainable AI techniques, offers a robust and interpretable solution for facial emotion detection paper.
Authors: Arne Schmidt, Pablo Morales-\'Alvarez, Lee A. D. Cooper, Lee A. Newberg, Andinet Enquobahrie, Aggelos K. Katsaggelos, Rafael Molina
Abstract: Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are 'distracted' by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen's kappa of 0.764 with only 0.69% of the labeled Panda data.
Authors: Lingzhi Liu, Haiyang Zhang, Chengwei Tang, Tiantian Zhang
Abstract: The memory dictionary-based contrastive learning method has achieved remarkable results in the field of unsupervised person Re-ID. However, The method of updating memory based on all samples does not fully utilize the hardest sample to improve the generalization ability of the model, and the method based on hardest sample mining will inevitably introduce false-positive samples that are incorrectly clustered in the early stages of the model. Clustering-based methods usually discard a significant number of outliers, leading to the loss of valuable information. In order to address the issues mentioned before, we propose an adaptive intra-class variation contrastive learning algorithm for unsupervised Re-ID, called AdaInCV. And the algorithm quantitatively evaluates the learning ability of the model for each class by considering the intra-class variations after clustering, which helps in selecting appropriate samples during the training process of the model. To be more specific, two new strategies are proposed: Adaptive Sample Mining (AdaSaM) and Adaptive Outlier Filter (AdaOF). The first one gradually creates more reliable clusters to dynamically refine the memory, while the second can identify and filter out valuable outliers as negative samples.
Authors: Honghu Chen, Yuxin Yao, Juyong Zhang
Abstract: In this paper, we introduce Neural-ABC, a novel parametric model based on neural implicit functions that can represent clothed human bodies with disentangled latent spaces for identity, clothing, shape, and pose. Traditional mesh-based representations struggle to represent articulated bodies with clothes due to the diversity of human body shapes and clothing styles, as well as the complexity of poses. Our proposed model provides a unified framework for parametric modeling, which can represent the identity, clothing, shape and pose of the clothed human body. Our proposed approach utilizes the power of neural implicit functions as the underlying representation and integrates well-designed structures to meet the necessary requirements. Specifically, we represent the underlying body as a signed distance function and clothing as an unsigned distance function, and they can be uniformly represented as unsigned distance fields. Different types of clothing do not require predefined topological structures or classifications, and can follow changes in the underlying body to fit the body. Additionally, we construct poses using a controllable articulated structure. The model is trained on both open and newly constructed datasets, and our decoupling strategy is carefully designed to ensure optimal performance. Our model excels at disentangling clothing and identity in different shape and poses while preserving the style of the clothing. We demonstrate that Neural-ABC fits new observations of different types of clothing. Compared to other state-of-the-art parametric models, Neural-ABC demonstrates powerful advantages in the reconstruction of clothed human bodies, as evidenced by fitting raw scans, depth maps and images. We show that the attributes of the fitted results can be further edited by adjusting their identities, clothing, shape and pose codes.
Authors: Siyu Chen, Kangcheng Liu, Chen Wang, Shenghai Yuan, Jianfei Yang, Lihua Xie
Abstract: Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and the need for extensive labeling. We propose two cost-effective and innovative designs: a self-supervised homographic pre-training for enhancing optical flow learning from pose-only labels and a random patch-based salient point detection strategy for more accurate optical flow patch extraction. These designs eliminate the need for dense optical flow labels for training and significantly improve the generalization capability of the system in diverse and challenging environments. Our pose-only supervised method achieves competitive performance on standard datasets and greater robustness and generalization ability in extreme and unseen scenarios, even compared to dense optical flow-supervised state-of-the-art methods.
Authors: Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri, Kevin Zhang, Michael Kaess, Christopher Metzler, Suren Jayasuriya, Adithya Pediredla
Abstract: Differentiable 3D-Gaussian splatting (GS) is emerging as a prominent technique in computer vision and graphics for reconstructing 3D scenes. GS represents a scene as a set of 3D Gaussians with varying opacities and employs a computationally efficient splatting operation along with analytical derivatives to compute the 3D Gaussian parameters given scene images captured from various viewpoints. Unfortunately, capturing surround view ($360^{\circ}$ viewpoint) images is impossible or impractical in many real-world imaging scenarios, including underwater imaging, rooms inside a building, and autonomous navigation. In these restricted baseline imaging scenarios, the GS algorithm suffers from a well-known 'missing cone' problem, which results in poor reconstruction along the depth axis. In this manuscript, we demonstrate that using transient data (from sonars) allows us to address the missing cone problem by sampling high-frequency data along the depth axis. We extend the Gaussian splatting algorithms for two commonly used sonars and propose fusion algorithms that simultaneously utilize RGB camera data and sonar data. Through simulations, emulations, and hardware experiments across various imaging scenarios, we show that the proposed fusion algorithms lead to significantly better novel view synthesis (5 dB improvement in PSNR) and 3D geometry reconstruction (60% lower Chamfer distance).
Authors: Bonan Liu, Guoyang Zhao, Jianhao Jiao, Guang Cai, Chengyang Li, Handi Yin, Yuyang Wang, Ming Liu, Pan Hui
Abstract: A Colored point cloud, as a simple and efficient 3D representation, has many advantages in various fields, including robotic navigation and scene reconstruction. This representation is now commonly used in 3D reconstruction tasks relying on cameras and LiDARs. However, fusing data from these two types of sensors is poorly performed in many existing frameworks, leading to unsatisfactory mapping results, mainly due to inaccurate camera poses. This paper presents OmniColor, a novel and efficient algorithm to colorize point clouds using an independent 360-degree camera. Given a LiDAR-based point cloud and a sequence of panorama images with initial coarse camera poses, our objective is to jointly optimize the poses of all frames for mapping images onto geometric reconstructions. Our pipeline works in an off-the-shelf manner that does not require any feature extraction or matching process. Instead, we find optimal poses by directly maximizing the photometric consistency of LiDAR maps. In experiments, we show that our method can overcome the severe visual distortion of omnidirectional images and greatly benefit from the wide field of view (FOV) of 360-degree cameras to reconstruct various scenarios with accuracy and stability. The code will be released at https://github.com/liubonan123/OmniColor/.
Authors: Prasun C Tripathi, Sina Tabakhi, Mohammod N I Suvon, Lawrence Sch\"ob, Samer Alabed, Andrew J Swift, Shuo Zhou, Haiping Lu
Abstract: Pulmonary Arterial Wedge Pressure (PAWP) is an essential cardiovascular hemodynamics marker to detect heart failure. In clinical practice, Right Heart Catheterization is considered a gold standard for assessing cardiac hemodynamics while non-invasive methods are often needed to screen high-risk patients from a large population. In this paper, we propose a multimodal learning pipeline to predict PAWP marker. We utilize complementary information from Cardiac Magnetic Resonance Imaging (CMR) scans (short-axis and four-chamber) and Electronic Health Records (EHRs). We extract spatio-temporal features from CMR scans using tensor-based learning. We propose a graph attention network to select important EHR features for prediction, where we model subjects as graph nodes and feature relationships as graph edges using the attention mechanism. We design four feature fusion strategies: early, intermediate, late, and hybrid fusion. With a linear classifier and linear fusion strategies, our pipeline is interpretable. We validate our pipeline on a large dataset of $2,641$ subjects from our ASPIRE registry. The comparative study against state-of-the-art methods confirms the superiority of our pipeline. The decision curve analysis further validates that our pipeline can be applied to screen a large population. The code is available at https://github.com/prasunc/hemodynamics.
Authors: Zhuoxu Huang, Zhenkun Fan, Tao Xu, Jungong Han
Abstract: Point cloud video representation learning is challenging due to complex structures and unordered spatial arrangement. Traditional methods struggle with frame-to-frame correlations and point-wise correspondence tracking. Recently, partial differential equations (PDE) have provided a new perspective in uniformly solving spatial-temporal data information within certain constraints. While tracking tangible point correspondence remains challenging, we propose to formalize point cloud video representation learning as a PDE-solving problem. Inspired by fluid analysis, where PDEs are used to solve the deformation of spatial shape over time, we employ PDE to solve the variations of spatial points affected by temporal information. By modeling spatial-temporal correlations, we aim to regularize spatial variations with temporal features, thereby enhancing representation learning in point cloud videos. We introduce Motion PointNet composed of a PointNet-like encoder and a PDE-solving module. Initially, we construct a lightweight yet effective encoder to model an initial state of the spatial variations. Subsequently, we develop our PDE-solving module in a parameterized latent space, tailored to address the spatio-temporal correlations inherent in point cloud video. The process of solving PDE is guided and refined by a contrastive learning structure, which is pivotal in reshaping the feature distribution, thereby optimizing the feature representation within point cloud video data. Remarkably, our Motion PointNet achieves an impressive accuracy of 97.52% on the MSRAction-3D dataset, surpassing the current state-of-the-art in all aspects while consuming minimal resources (only 0.72M parameters and 0.82G FLOPs).
Authors: Tin Barisin, Illia Horenko
Abstract: Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem as the hyperparameter space for possible network configurations is vast. Here, we introduce a layer-by-layer data-driven pruning method based on the mathematical idea aiming at a computationally-scalable entropic relaxation of the pruning problem. The sparse subnetwork is found from the pre-trained (full) CNN using the network entropy minimization as a sparsity constraint. This allows deploying a numerically scalable algorithm with a sublinear scaling cost. The method is validated on several benchmarks (architectures): (i) MNIST (LeNet) with sparsity 55%-84% and loss in accuracy 0.1%-0.5%, and (ii) CIFAR-10 (VGG-16, ResNet18) with sparsity 73-89% and loss in accuracy 0.1%-0.5%.
Authors: Iury B. de A. Santos, Andr\'e C. P. L. F. de Carvalho
Abstract: The adoption of Deep Learning algorithms in the medical imaging field is a prominent area of research, with high potential for advancing AI-based Computer-aided diagnosis (AI-CAD) solutions. However, current solutions face challenges due to a lack of interpretability features and high data demands, prompting recent efforts to address these issues. In this study, we propose the ProtoAL method, where we integrate an interpretable DL model into the Deep Active Learning (DAL) framework. This approach aims to address both challenges by focusing on the medical imaging context and utilizing an inherently interpretable model based on prototypes. We evaluated ProtoAL on the Messidor dataset, achieving an area under the precision-recall curve of 0.79 while utilizing only 76.54\% of the available labeled data. These capabilities can enhances the practical usability of a DL model in the medical field, providing a means of trust calibration in domain experts and a suitable solution for learning in the data scarcity context often found.
Authors: Hao Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan
Abstract: The key success of existing video super-resolution (VSR) methods stems mainly from exploring spatial and temporal information, which is usually achieved by a recurrent propagation module with an alignment module. However, inaccurate alignment usually leads to aligned features with significant artifacts, which will be accumulated during propagation and thus affect video restoration. Moreover, propagation modules only propagate the same timestep features forward or backward that may fail in case of complex motion or occlusion, limiting their performance for high-quality frame restoration. To address these issues, we propose a collaborative feedback discriminative (CFD) method to correct inaccurate aligned features and model long -range spatial and temporal information for better video reconstruction. In detail, we develop a discriminative alignment correction (DAC) method to adaptively explore information and reduce the influences of the artifacts caused by inaccurate alignment. Then, we propose a collaborative feedback propagation (CFP) module that employs feedback and gating mechanisms to better explore spatial and temporal information of different timestep features from forward and backward propagation simultaneously. Finally, we embed the proposed DAC and CFP into commonly used VSR networks to verify the effectiveness of our method. Quantitative and qualitative experiments on several benchmarks demonstrate that our method can improve the performance of existing VSR models while maintaining a lower model complexity. The source code and pre-trained models will be available at \url{https://github.com/House-Leo/CFDVSR}.
Authors: Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham, Kai-Wei Chang, Nanyun Peng
Abstract: Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the entire image, the depicted event, and the interactions between various objects participating in the event. Existing models heavily rely on high-quality event-annotated training data to understand the event semantics and structures, and they fail to generalize to new event types and domains. In this paper, we propose GenEARL, a training-free generative framework that harness the power of the modern generative models to understand event task descriptions given image contexts to perform the EARL task. Specifically, GenEARL comprises two stages of generative prompting with a frozen vision-language model (VLM) and a frozen large language model (LLM). First, a generative VLM learns the semantics of the event argument roles and generates event-centric object descriptions based on the image. Subsequently, a LLM is prompted with the generated object descriptions with a predefined template for EARL (i.e., assign an object with an event argument role). We show that GenEARL outperforms the contrastive pretraining (CLIP) baseline by 9.4% and 14.2% accuracy for zero-shot EARL on the M2E2 and SwiG datasets, respectively. In addition, we outperform CLIP-Event by 22% precision on M2E2 dataset. The framework also allows flexible adaptation and generalization to unseen domains.
Authors: Guangyuan Li, Chen Rao, Juncheng Mo, Zhanjie Zhang, Wei Xing, Lei Zhao
Abstract: Recently, diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, especially with regard to detailed reconstruction. However, the current DM-based SR reconstruction methods still face the following issues: (1) They require a large number of iterations to reconstruct the final image, which is inefficient and consumes a significant amount of computational resources. (2) The results reconstructed by these methods are often misaligned with the real high-resolution images, leading to remarkable distortion in the reconstructed MR images. To address the aforementioned issues, we propose an efficient diffusion model for multi-contrast MRI SR, named as DiffMSR. Specifically, we apply DM in a highly compact low-dimensional latent space to generate prior knowledge with high-frequency detail information. The highly compact latent space ensures that DM requires only a few simple iterations to produce accurate prior knowledge. In addition, we design the Prior-Guide Large Window Transformer (PLWformer) as the decoder for DM, which can extend the receptive field while fully utilizing the prior knowledge generated by DM to ensure that the reconstructed MR image remains undistorted. Extensive experiments on public and clinical datasets demonstrate that our DiffMSR outperforms state-of-the-art methods.
Authors: Zhimeng Xin, Shiming Chen, Tianxu Wu, Yuanjie Shao, Weiping Ding, Xinge You
Abstract: Object detection as a subfield within computer vision has achieved remarkable progress, which aims to accurately identify and locate a specific object from images or videos. Such methods rely on large-scale labeled training samples for each object category to ensure accurate detection, but obtaining extensive annotated data is a labor-intensive and expensive process in many real-world scenarios. To tackle this challenge, researchers have explored few-shot object detection (FSOD) that combines few-shot learning and object detection techniques to rapidly adapt to novel objects with limited annotated samples. This paper presents a comprehensive survey to review the significant advancements in the field of FSOD in recent years and summarize the existing challenges and solutions. Specifically, we first introduce the background and definition of FSOD to emphasize potential value in advancing the field of computer vision. We then propose a novel FSOD taxonomy method and survey the plentifully remarkable FSOD algorithms based on this fact to report a comprehensive overview that facilitates a deeper understanding of the FSOD problem and the development of innovative solutions. Finally, we discuss the advantages and limitations of these algorithms to summarize the challenges, potential research direction, and development trend of object detection in the data scarcity scenario.
Authors: Jinlong Li, Baolu Li, Zhengzhong Tu, Xinyu Liu, Qing Guo, Felix Juefei-Xu, Runsheng Xu, Hongkai Yu
Abstract: Vision-centric perception systems for autonomous driving have gained considerable attention recently due to their cost-effectiveness and scalability, especially compared to LiDAR-based systems. However, these systems often struggle in low-light conditions, potentially compromising their performance and safety. To address this, our paper introduces LightDiff, a domain-tailored framework designed to enhance the low-light image quality for autonomous driving applications. Specifically, we employ a multi-condition controlled diffusion model. LightDiff works without any human-collected paired data, leveraging a dynamic data degradation process instead. It incorporates a novel multi-condition adapter that adaptively controls the input weights from different modalities, including depth maps, RGB images, and text captions, to effectively illuminate dark scenes while maintaining context consistency. Furthermore, to align the enhanced images with the detection model's knowledge, LightDiff employs perception-specific scores as rewards to guide the diffusion training process through reinforcement learning. Extensive experiments on the nuScenes datasets demonstrate that LightDiff can significantly improve the performance of several state-of-the-art 3D detectors in night-time conditions while achieving high visual quality scores, highlighting its potential to safeguard autonomous driving.
Authors: Xuan Sun, Zhanfu An, Yuyu Liu
Abstract: We investigated domain adaptive semantic segmentation in foggy weather scenarios, which aims to enhance the utilization of unlabeled foggy data and improve the model's adaptability to foggy conditions. Current methods rely on clear images as references, jointly learning defogging and segmentation for foggy images. Despite making some progress, there are still two main drawbacks: (1) the coupling of segmentation and defogging feature representations, resulting in a decrease in semantic representation capability, and (2) the failure to leverage real fog priors in unlabeled foggy data, leading to insufficient model generalization ability. To address these issues, we propose a novel training framework, Decouple Defogging and Semantic learning, called D2SL, aiming to alleviate the adverse impact of defogging tasks on the final segmentation task. In this framework, we introduce a domain-consistent transfer strategy to establish a connection between defogging and segmentation tasks. Furthermore, we design a real fog transfer strategy to improve defogging effects by fully leveraging the fog priors from real foggy images. Our approach enhances the semantic representations required for segmentation during the defogging learning process and maximizes the representation capability of fog invariance by effectively utilizing real fog data. Comprehensive experiments validate the effectiveness of the proposed method.
Authors: Qiaole Dong, Yanwei Fu
Abstract: Optical flow is a classical task that is important to the vision community. Classical optical flow estimation uses two frames as input, whilst some recent methods consider multiple frames to explicitly model long-range information. The former ones limit their ability to fully leverage temporal coherence along the video sequence; and the latter ones incur heavy computational overhead, typically not possible for real-time flow estimation. Some multi-frame-based approaches even necessitate unseen future frames for current estimation, compromising real-time applicability in safety-critical scenarios. To this end, we present MemFlow, a real-time method for optical flow estimation and prediction with memory. Our method enables memory read-out and update modules for aggregating historical motion information in real-time. Furthermore, we integrate resolution-adaptive re-scaling to accommodate diverse video resolutions. Besides, our approach seamlessly extends to the future prediction of optical flow based on past observations. Leveraging effective historical motion aggregation, our method outperforms VideoFlow with fewer parameters and faster inference speed on Sintel and KITTI-15 datasets in terms of generalization performance. At the time of submission, MemFlow also leads in performance on the 1080p Spring dataset. Codes and models will be available at: https://dqiaole.github.io/MemFlow/.
Authors: Hyeongjin Nam, Daniel Sungho Jung, Gyeongsik Moon, Kyoung Mu Lee
Abstract: Human-object contact serves as a strong cue to understand how humans physically interact with objects. Nevertheless, it is not widely explored to utilize human-object contact information for the joint reconstruction of 3D human and object from a single image. In this work, we present a novel joint 3D human-object reconstruction method (CONTHO) that effectively exploits contact information between humans and objects. There are two core designs in our system: 1) 3D-guided contact estimation and 2) contact-based 3D human and object refinement. First, for accurate human-object contact estimation, CONTHO initially reconstructs 3D humans and objects and utilizes them as explicit 3D guidance for contact estimation. Second, to refine the initial reconstructions of 3D human and object, we propose a novel contact-based refinement Transformer that effectively aggregates human features and object features based on the estimated human-object contact. The proposed contact-based refinement prevents the learning of erroneous correlation between human and object, which enables accurate 3D reconstruction. As a result, our CONTHO achieves state-of-the-art performance in both human-object contact estimation and joint reconstruction of 3D human and object. The code is publicly available at https://github.com/dqj5182/CONTHO_RELEASE.
Authors: Weijia Li, Haote Yang, Zhenghao Hu, Juepeng Zheng, Gui-Song Xia, Conghui He
Abstract: 3D building reconstruction from monocular remote sensing images is an important and challenging research problem that has received increasing attention in recent years, owing to its low cost of data acquisition and availability for large-scale applications. However, existing methods rely on expensive 3D-annotated samples for fully-supervised training, restricting their application to large-scale cross-city scenarios. In this work, we propose MLS-BRN, a multi-level supervised building reconstruction network that can flexibly utilize training samples with different annotation levels to achieve better reconstruction results in an end-to-end manner. To alleviate the demand on full 3D supervision, we design two new modules, Pseudo Building Bbox Calculator and Roof-Offset guided Footprint Extractor, as well as new tasks and training strategies for different types of samples. Experimental results on several public and new datasets demonstrate that our proposed MLS-BRN achieves competitive performance using much fewer 3D-annotated samples, and significantly improves the footprint extraction and 3D reconstruction performance compared with current state-of-the-art. The code and datasets of this work will be released at https://github.com/opendatalab/MLS-BRN.git.
Authors: Youze Xue, Binghui Chen, Yifeng Geng, Xuansong Xie, Jiansheng Chen, Hongbing Ma
Abstract: Customized generative text-to-image models have the ability to produce images that closely resemble a given subject. However, in the context of generating advertising images for e-commerce scenarios, it is crucial that the generated subject's identity aligns perfectly with the product being advertised. In order to address the need for strictly-ID preserved advertising image generation, we have developed a Control-Net based customized image generation pipeline and have taken earring model advertising as an example. Our approach facilitates a seamless interaction between the earrings and the model's face, while ensuring that the identity of the earrings remains intact. Furthermore, to achieve a diverse and controllable display, we have proposed a multi-branch cross-attention architecture, which allows for control over the scale, pose, and appearance of the model, going beyond the limitations of text prompts. Our method manages to achieve fine-grained control of the generated model's face, resulting in controllable and captivating advertising effects.
Authors: Binghui Chen, Wenyu Li, Yifeng Geng, Xuansong Xie, Wangmeng Zuo
Abstract: With the development of the large-scale diffusion model, Artificial Intelligence Generated Content (AIGC) techniques are popular recently. However, how to truly make it serve our daily lives remains an open question. To this end, in this paper, we focus on employing AIGC techniques in one filed of E-commerce marketing, i.e., generating hyper-realistic advertising images for displaying user-specified shoes by human. Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes. It consists of three modules: (1) shoe wearable-area detection module (WD), (2) leg-pose synthesis module (LpS) and the final (3) shoe-wearing image generation module (SW). Them three are performed in ordered stages. Compared to baselines, our ShoeModel is shown to generalize better to different type of shoes and has ability of keeping the ID-consistency of the given shoes, as well as automatically producing reasonable interactions with human. Extensive experiments show the effectiveness of our proposed shoe-wearing system. Figure 1 shows the input and output examples of our ShoeModel.
Authors: Chenguang Liu, Chisheng Wang, Feifei Dong, Xin Su, Chuanhua Zhu, Dejin Zhang, Qingquan Li
Abstract: Edge detection is a long standing problem in computer vision. Recent deep learning based algorithms achieve state of-the-art performance in publicly available datasets. Despite the efficiency of these algorithms, their performance, however, relies heavily on the pretrained weights of the backbone network on the ImageNet dataset. This limits heavily the design space of deep learning based edge detectors. Whenever we want to devise a new model, we have to train this new model on the ImageNet dataset first, and then fine tune the model using the edge detection datasets. The comparison would be unfair otherwise. However, it is usually not feasible for many researchers to train a model on the ImageNet dataset due to the limited computation resources. In this work, we study the performance that can be achieved by state-of-the-art deep learning based edge detectors in publicly available datasets when they are trained from scratch, and devise a new network architecture, the multi-stream and multi scale fusion net (msmsfnet), for edge detection. We show in our experiments that by training all models from scratch to ensure the fairness of comparison, out model outperforms state-of-the art deep learning based edge detectors in three publicly available datasets.
Authors: Yuxi Ren, Jie Wu, Yanzuo Lu, Huafeng Kuang, Xin Xia, Xionghui Wang, Qianqian Wang, Yixing Zhu, Pan Xie, Shiyin Wang, Xuefeng Xiao, Yitong Wang, Min Zheng, Lean Fu
Abstract: Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges, including: i) inferior quality; ii) poor consistency; iii) insufficient instrcution adherence; iv) suboptimal generation efficiency. To address these obstacles, we present ByteEdit, an innovative feedback learning framework meticulously designed to Boost, Comply, and Accelerate Generative Image Editing tasks. ByteEdit seamlessly integrates image reward models dedicated to enhancing aesthetics and image-text alignment, while also introducing a dense, pixel-level reward model tailored to foster coherence in the output. Furthermore, we propose a pioneering adversarial and progressive feedback learning strategy to expedite the model's inference speed. Through extensive large-scale user evaluations, we demonstrate that ByteEdit surpasses leading generative image editing products, including Adobe, Canva, and MeiTu, in both generation quality and consistency. ByteEdit-Outpainting exhibits a remarkable enhancement of 388% and 135% in quality and consistency, respectively, when compared to the baseline model. Experiments also verfied that our acceleration models maintains excellent performance results in terms of quality and consistency.
Authors: Peng Tu, Xun Zhou, Mingming Wang, Xiaojun Yang, Bo Peng, Ping Chen, Xiu Su, Yawen Huang, Yefeng Zheng, Chang Xu
Abstract: Neural Radiance Fields (NeRF) have emerged as a paradigm-shifting methodology for the photorealistic rendering of objects and environments, enabling the synthesis of novel viewpoints with remarkable fidelity. This is accomplished through the strategic utilization of object-centric camera poses characterized by significant inter-frame overlap. This paper explores a compelling, alternative utility of NeRF: the derivation of point clouds from aggregated urban landscape imagery. The transmutation of street-view data into point clouds is fraught with complexities, attributable to a nexus of interdependent variables. First, high-quality point cloud generation hinges on precise camera poses, yet many datasets suffer from inaccuracies in pose metadata. Also, the standard approach of NeRF is ill-suited for the distinct characteristics of street-view data from autonomous vehicles in vast, open settings. Autonomous vehicle cameras often record with limited overlap, leading to blurring, artifacts, and compromised pavement representation in NeRF-based point clouds. In this paper, we present NeRF2Points, a tailored NeRF variant for urban point cloud synthesis, notable for its high-quality output from RGB inputs alone. Our paper is supported by a bespoke, high-resolution 20-kilometer urban street dataset, designed for point cloud generation and evaluation. NeRF2Points adeptly navigates the inherent challenges of NeRF-based point cloud synthesis through the implementation of the following strategic innovations: (1) Integration of Weighted Iterative Geometric Optimization (WIGO) and Structure from Motion (SfM) for enhanced camera pose accuracy, elevating street-view data precision. (2) Layered Perception and Integrated Modeling (LPiM) is designed for distinct radiance field modeling in urban environments, resulting in coherent point cloud representations.
Authors: Yifan Yang, Dong Liu, Shuhai Zhang, Zeshuai Deng, Zixiong Huang, Mingkui Tan
Abstract: Reconstructing 3D clothed human involves creating a detailed geometry of individuals in clothing, with applications ranging from virtual try-on, movies, to games. To enable practical and widespread applications, recent advances propose to generate a clothed human from an RGB image. However, they struggle to reconstruct detailed and robust avatars simultaneously. We empirically find that the high-frequency (HF) and low-frequency (LF) information from a parametric model has the potential to enhance geometry details and improve robustness to noise, respectively. Based on this, we propose HiLo, namely clothed human reconstruction with high- and low-frequency information, which contains two components. 1) To recover detailed geometry using HF information, we propose a progressive HF Signed Distance Function to enhance the detailed 3D geometry of a clothed human. We analyze that our progressive learning manner alleviates large gradients that hinder model convergence. 2) To achieve robust reconstruction against inaccurate estimation of the parametric model by using LF information, we propose a spatial interaction implicit function. This function effectively exploits the complementary spatial information from a low-resolution voxel grid of the parametric model. Experimental results demonstrate that HiLo outperforms the state-of-the-art methods by 10.43% and 9.54% in terms of Chamfer distance on the Thuman2.0 and CAPE datasets, respectively. Additionally, HiLo demonstrates robustness to noise from the parametric model, challenging poses, and various clothing styles.
Authors: Butian Xiong, Nanjun Zheng, Zhen Li
Abstract: We introduce a novel large-scale scene reconstruction benchmark that utilizes newly developed 3D representation approaches: Gaussian Splatting and Neural Radiance Fields, on our expansive GauU-Scene V2 dataset. GauU-Scene V2 encompasses over 6.5 square kilometers and features a comprehensive RGB dataset coupled with LiDAR ground truth. This dataset offers a unique blend of urban and academic environments for advanced spatial analysis, covering more than 6.5 km2. We also provide detailed supplementary information on data collection protocols. Furthermore, we present an easy-to-follow pipeline to align the COLMAP sparse point cloud with the detailed LiDAR dataset. Our evaluation of U-Scene, which includes a detailed analysis across various novel viewpoints using image-based metrics such as SSIM, LPIPS, and PSNR, shows contradictory results when applying geometric-based metrics, such as Chamfer distance. This leads to doubts about the reliability of current image-based measurement matrices and geometric extraction methods on Gaussian Splatting. We also make the dataset available on the following anonymous project page
Authors: Zihan Liu, Hanyi Wang, Yaoyu Kang, Shilin Wang
Abstract: Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector capable of identifying images from diverse sources. Existing methods struggle to generalize across unseen generative models when provided with limited sample sources. Inspired by the zero-shot transferability of pre-trained vision-language models, we seek to harness the nontrivial visual-world knowledge and descriptive proficiency of CLIP-ViT to generalize over unknown domains. This paper presents a novel parameter-efficient fine-tuning approach, mixture of low-rank experts, to fully exploit CLIP-ViT's potential while preserving knowledge and expanding capacity for transferable detection. We adapt only the MLP layers of deeper ViT blocks via an integration of shared and separate LoRAs within an MoE-based structure. Extensive experiments on public benchmarks show that our method achieves superiority over state-of-the-art approaches in cross-generator generalization and robustness to perturbations. Remarkably, our best-performing ViT-L/14 variant requires training only 0.08% of its parameters to surpass the leading baseline by +3.64% mAP and +12.72% avg.Acc across unseen diffusion and autoregressive models. This even outperforms the baseline with just 0.28% of the training data. Our code and pre-trained models will be available at https://github.com/zhliuworks/CLIPMoLE.
Authors: Huan Zhong, Chen Wu, Ziqi Xiao
Abstract: Change detection, as a research hotspot in the field of remote sensing, has witnessed continuous development and progress. However, the discrimination of boundary details remains a significant bottleneck due to the complexity of surrounding elements between change areas and backgrounds. Discriminating the boundaries of large change areas results in misalignment, while connecting boundaries occurs for small change targets. To address the above issues, a novel network based on the localization-then-refinement strategy is proposed in this paper, namely LRNet. LRNet consists of two stages: localization and refinement. In the localization stage, a three-branch encoder simultaneously extracts original image features and their differential features for interactive localization of the position of each change area. To minimize information loss during feature extraction, learnable optimal pooling (LOP) is proposed to replace the widely used max-pooling. Additionally, this process is trainable and contributes to the overall optimization of the network. To effectively interact features from different branches and accurately locate change areas of various sizes, change alignment attention (C2A) and hierarchical change alignment module (HCA) are proposed. In the refinement stage, the localization results from the localization stage are corrected by constraining the change areas and change edges through the edge-area alignment module (E2A). Subsequently, the decoder, combined with the difference features strengthened by C2A in the localization phase, refines change areas of different sizes, ultimately achieving accurate boundary discrimination of change areas. The proposed LRNet outperforms 13 other state-of-the-art methods in terms of comprehensive evaluation metrics and provides the most precise boundary discrimination results on the LEVIR-CD and WHU-CD datasets.
Authors: Qingshan Hou, Shuai Cheng, Peng Cao, Jinzhu Yang, Xiaoli Liu, Osmar R. Zaiane, Yih Chung Tham
Abstract: Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images pose great challenges for models to extract key lesion features. Disease diagnosis methods guided by contrastive learning (CL) have shown significant advantages in lesion feature representation. Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs. In this work, we propose a clinical-oriented multi-level CL framework that aims to enhance the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, thereby enabling more accurate disease diagnosis from low-quality medical images. Specifically, we first construct multi-level positive and negative pairs to enhance the model's comprehensive recognition capability of lesion features by integrating information from different levels and qualities of medical images. Moreover, to improve the quality of the learned lesion embeddings, we introduce a dynamic hard sample mining method based on self-paced learning. The proposed CL framework is validated on two public medical image datasets, EyeQ and Chest X-ray, demonstrating superior performance compared to other state-of-the-art disease diagnostic methods.
Authors: Jiangnan Tang, Jingya Wang, Kaiyang Ji, Lan Xu, Jingyi Yu, Ye Shi
Abstract: Estimating full-body human motion via sparse tracking signals from head-mounted displays and hand controllers in 3D scenes is crucial to applications in AR/VR. One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities. To help resolve this ambiguous problem, we introduce a new framework to combine rich contextual information provided by scenes to benefit full-body motion tracking from sparse observations. To estimate plausible human motions given sparse tracking signals and 3D scenes, we develop $\text{S}^2$Fusion, a unified framework fusing \underline{S}cene and sparse \underline{S}ignals with a conditional dif\underline{Fusion} model. $\text{S}^2$Fusion first extracts the spatial-temporal relations residing in the sparse signals via a periodic autoencoder, and then produces time-alignment feature embedding as additional inputs. Subsequently, by drawing initial noisy motion from a pre-trained prior, $\text{S}^2$Fusion utilizes conditional diffusion to fuse scene geometry and sparse tracking signals to generate full-body scene-aware motions. The sampling procedure of $\text{S}^2$Fusion is further guided by a specially designed scene-penetration loss and phase-matching loss, which effectively regularizes the motion of the lower body even in the absence of any tracking signals, making the generated motion much more plausible and coherent. Extensive experimental results have demonstrated that our $\text{S}^2$Fusion outperforms the state-of-the-art in terms of estimation quality and smoothness.
Authors: Fatemeh Asghari, Mohammad Reza Soheili, Faezeh Gholamrezaie
Abstract: The global fashion industry plays a pivotal role in the global economy, and addressing fundamental issues within the industry is crucial for developing innovative solutions. One of the most pressing challenges in the fashion industry is the mismatch between body shapes and the garments of individuals they purchase. This issue is particularly prevalent among individuals with non-ideal body shapes, exacerbating the challenges faced. Considering inter-individual variability in body shapes is essential for designing and producing garments that are widely accepted by consumers. Traditional methods for determining human body shape are limited due to their low accuracy, high costs, and time-consuming nature. New approaches, utilizing digital imaging and deep neural networks (DNN), have been introduced to identify human body shape. In this study, the Style4BodyShape dataset is used for classifying body shapes into five categories: Rectangle, Triangle, Inverted Triangle, Hourglass, and Apple. In this paper, the body shape segmentation of a person is extracted from the image, disregarding the surroundings and background. Then, Various pre-trained models, such as ResNet18, ResNet34, ResNet50, VGG16, VGG19, and Inception v3, are used to classify the segmentation results. Among these pre-trained models, the Inception V3 model demonstrates superior performance regarding f1-score evaluation metric and accuracy compared to the other models.
Authors: Renlong Wu, Zhilu Zhang, Yu Yang, Wangmeng Zuo
Abstract: When zooming between dual cameras on a mobile, noticeable jumps in geometric content and image color occur in the preview, inevitably affecting the user's zoom experience. In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview. The frame interpolation (FI) technique is a potential solution but struggles with ground-truth collection. To address the issue, we suggest a data factory solution where continuous virtual cameras are assembled to generate DCSZ data by rendering reconstructed 3D models of the scene. In particular, we propose a novel dual-camera smooth zoom Gaussian Splatting (ZoomGS), where a camera-specific encoding is introduced to construct a specific 3D model for each virtual camera. With the proposed data factory, we construct a synthetic dataset for DCSZ, and we utilize it to fine-tune FI models. In addition, we collect real-world dual-zoom images without ground-truth for evaluation. Extensive experiments are conducted with multiple FI methods. The results show that the fine-tuned FI models achieve a significant performance improvement over the original ones on DCSZ task. The datasets, codes, and pre-trained models will be publicly available.
Authors: Hou-I Liu, Christine Wu, Jen-Hao Cheng, Wenhao Chai, Shian-Yun Wang, Gaowen Liu, Jenq-Neng Hwang, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Monocular 3D object detection (Mono3D) is an indispensable research topic in autonomous driving, thanks to the cost-effective monocular camera sensors and its wide range of applications. Since the image perspective has depth ambiguity, the challenges of Mono3D lie in understanding 3D scene geometry and reconstructing 3D object information from a single image. Previous methods attempted to transfer 3D information directly from the LiDAR-based teacher to the camera-based student. However, a considerable gap in feature representation makes direct cross-modal distillation inefficient, resulting in a significant performance deterioration between the LiDAR-based teacher and the camera-based student. To address this issue, we propose the Teaching Assistant Knowledge Distillation (MonoTAKD) to break down the learning objective by integrating intra-modal distillation with cross-modal residual distillation. In particular, we employ a strong camera-based teaching assistant model to distill powerful visual knowledge effectively through intra-modal distillation. Subsequently, we introduce the cross-modal residual distillation to transfer the 3D spatial cues. By acquiring both visual knowledge and 3D spatial cues, the predictions of our approach are rigorously evaluated on the KITTI 3D object detection benchmark and achieve state-of-the-art performance in Mono3D.
Authors: Gyeongjin Kang, Younggeun Lee, Eunbyung Park
Abstract: Neural Radiance Fields (NeRF) have achieved huge success in effectively capturing and representing 3D objects and scenes. However, several factors have impeded its further proliferation as next-generation 3D media. To establish a ubiquitous presence in everyday media formats, such as images and videos, it is imperative to devise a solution that effectively fulfills three key objectives: fast encoding and decoding time, compact model sizes, and high-quality renderings. Despite significant advancements, a comprehensive algorithm that adequately addresses all objectives has yet to be fully realized. In this work, we present CodecNeRF, a neural codec for NeRF representations, consisting of a novel encoder and decoder architecture that can generate a NeRF representation in a single forward pass. Furthermore, inspired by the recent parameter-efficient finetuning approaches, we develop a novel finetuning method to efficiently adapt the generated NeRF representations to a new test instance, leading to high-quality image renderings and compact code sizes. The proposed CodecNeRF, a newly suggested encoding-decoding-finetuning pipeline for NeRF, achieved unprecedented compression performance of more than 150x and 20x reduction in encoding time while maintaining (or improving) the image quality on widely used 3D object datasets, such as ShapeNet and Objaverse.
Authors: Yigang Zhao Chaowei Zheng, Jiannan Su, GuangyongChen, MinGan
Abstract: Non-Local Attention (NLA) is a powerful technique for capturing long-range feature correlations in deep single image super-resolution (SR). However, NLA suffers from high computational complexity and memory consumption, as it requires aggregating all non-local feature information for each query response and recalculating the similarity weight distribution for different abstraction levels of features. To address these challenges, we propose a novel Learnable Collaborative Attention (LCoA) that introduces inductive bias into non-local modeling. Our LCoA consists of two components: Learnable Sparse Pattern (LSP) and Collaborative Attention (CoA). LSP uses the k-means clustering algorithm to dynamically adjust the sparse attention pattern of deep features, which reduces the number of non-local modeling rounds compared with existing sparse solutions. CoA leverages the sparse attention pattern and weights learned by LSP, and co-optimizes the similarity matrix across different abstraction levels, which avoids redundant similarity matrix calculations. The experimental results show that our LCoA can reduce the non-local modeling time by about 83% in the inference stage. In addition, we integrate our LCoA into a deep Learnable Collaborative Attention Network (LCoAN), which achieves competitive performance in terms of inference time, memory consumption, and reconstruction quality compared with other state-of-the-art SR methods.
Authors: Dongjing Shan, guiqiang chen
Abstract: Vision Transformers (ViTs) have achieved impressive results in large-scale image classification. However, when training from scratch on small datasets, there is still a significant performance gap between ViTs and Convolutional Neural Networks (CNNs), which is attributed to the lack of inductive bias. To address this issue, we propose a Graph-based Vision Transformer (GvT) that utilizes graph convolutional projection and graph-pooling. In each block, queries and keys are calculated through graph convolutional projection based on the spatial adjacency matrix, while dot-product attention is used in another graph convolution to generate values. When using more attention heads, the queries and keys become lower-dimensional, making their dot product an uninformative matching function. To overcome this low-rank bottleneck in attention heads, we employ talking-heads technology based on bilinear pooled features and sparse selection of attention tensors. This allows interaction among filtered attention scores and enables each attention mechanism to depend on all queries and keys. Additionally, we apply graph-pooling between two intermediate blocks to reduce the number of tokens and aggregate semantic information more effectively. Our experimental results show that GvT produces comparable or superior outcomes to deep convolutional networks and surpasses vision transformers without pre-training on large datasets. The code for our proposed model is publicly available on the website.
Authors: Yingsen Zeng, Yujie Zhong, Chengjian Feng, Lin Ma
Abstract: Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instance, most descriptions in MR involve multiple actions from TAD. In this paper, we aim to investigate the potential synergy between TAD and MR. Firstly, we propose a unified architecture, termed Unified Moment Detection (UniMD), for both TAD and MR. It transforms the inputs of the two tasks, namely actions for TAD or events for MR, into a common embedding space, and utilizes two novel query-dependent decoders to generate a uniform output of classification score and temporal segments. Secondly, we explore the efficacy of two task fusion learning approaches, pre-training and co-training, in order to enhance the mutual benefits between TAD and MR. Extensive experiments demonstrate that the proposed task fusion learning scheme enables the two tasks to help each other and outperform the separately trained counterparts. Impressively, UniMD achieves state-of-the-art results on three paired datasets Ego4D, Charades-STA, and ActivityNet. Our code will be released at https://github.com/yingsen1/UniMD.
Authors: Aofan Jiang, Chaoqin Huang, Qing Cao, Yuchen Xu, Zi Zeng, Kang Chen, Ya Zhang, Yanfeng Wang
Abstract: The electrocardiogram (ECG) is an essential tool for diagnosing heart disease, with computer-aided systems improving diagnostic accuracy and reducing healthcare costs. Despite advancements, existing systems often miss rare cardiac anomalies that could be precursors to serious, life-threatening issues or alterations in the cardiac macro/microstructure. We address this gap by focusing on self-supervised anomaly detection (AD), training exclusively on normal ECGs to recognize deviations indicating anomalies. We introduce a novel self-supervised learning framework for ECG AD, utilizing a vast dataset of normal ECGs to autonomously detect and localize cardiac anomalies. It proposes a novel masking and restoration technique alongside a multi-scale cross-attention module, enhancing the model's ability to integrate global and local signal features. The framework emphasizes accurate localization of anomalies within ECG signals, ensuring the method's clinical relevance and reliability. To reduce the impact of individual variability, the approach further incorporates crucial patient-specific information from ECG reports, such as age and gender, thus enabling accurate identification of a broad spectrum of cardiac anomalies, including rare ones. Utilizing an extensive dataset of 478,803 ECG graphic reports from real-world clinical practice, our method has demonstrated exceptional effectiveness in AD across all tested conditions, regardless of their frequency of occurrence, significantly outperforming existing models. It achieved superior performance metrics, including an AUROC of 91.2%, an F1 score of 83.7%, a sensitivity rate of 84.2%, a specificity of 83.0%, and a precision of 75.6% with a fixed recall rate of 90%. It has also demonstrated robust localization capabilities, with an AUROC of 76.5% and a Dice coefficient of 65.3% for anomaly localization.
Authors: Weiwei Cao, Jianpeng Zhang, Yingda Xia, Tony C. W. Mok, Zi Li, Xianghua Ye, Le Lu, Jian Zheng, Yuxing Tang, Ling Zhang
Abstract: Radiologists highly desire fully automated versatile AI for medical imaging interpretation. However, the lack of extensively annotated large-scale multi-disease datasets has hindered the achievement of this goal. In this paper, we explore the feasibility of leveraging language as a naturally high-quality supervision for chest CT imaging. In light of the limited availability of image-report pairs, we bootstrap the understanding of 3D chest CT images by distilling chest-related diagnostic knowledge from an extensively pre-trained 2D X-ray expert model. Specifically, we propose a language-guided retrieval method to match each 3D CT image with its semantically closest 2D X-ray image, and perform pair-wise and semantic relation knowledge distillation. Subsequently, we use contrastive learning to align images and reports within the same patient while distinguishing them from the other patients. However, the challenge arises when patients have similar semantic diagnoses, such as healthy patients, potentially confusing if treated as negatives. We introduce a robust contrastive learning that identifies and corrects these false negatives. We train our model with over 12,000 pairs of chest CT images and radiology reports. Extensive experiments across multiple scenarios, including zero-shot learning, report generation, and fine-tuning processes, demonstrate the model's feasibility in interpreting chest CT images.
Authors: Yuanfeng Xu, Yuhao Chen, Zhongzhan Huang, Zijian He, Guangrun Wang, Philip Torr, Liang Lin
Abstract: Recent video editing advancements rely on accurate pose sequences to animate subjects. However, these efforts are not suitable for cross-species animation due to pose misalignment between species (for example, the poses of a cat differs greatly from that of a pig due to differences in body structure). In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background. The key technique used in our AnimateZoo is subject alignment, which includes two steps. First, we improve appearance feature extraction by integrating a Laplacian detail booster and a prompt-tuning identity extractor. These components are specifically designed to capture essential appearance information, including identity and fine details. Second, we align shape features and address conflicts from differing subjects by introducing a scale-information remover. This ensures accurate cross-species animation. Moreover, we introduce two high-quality animal video datasets featuring a wide variety of species. Trained on these extensive datasets, our model is capable of generating videos characterized by accurate movements, consistent appearance, and high-fidelity frames, without the need for the pre-inference fine-tuning that prior arts required. Extensive experiments showcase the outstanding performance of our method in cross-species action following tasks, demonstrating exceptional shape adaptation capability. The project page is available at https://justinxu0.github.io/AnimateZoo/.
Authors: Yu Lei, Guoshuai Sheng, Fangfang Li, Quanxue Gao, Cheng Deng, Qin Li
Abstract: Zero-shot learning(ZSL) aims to recognize new classes without prior exposure to their samples, relying on semantic knowledge from observed classes. However, current attention-based models may overlook the transferability of visual features and the distinctiveness of attribute localization when learning regional features in images. Additionally, they often overlook shared attributes among different objects. Highly discriminative attribute features are crucial for identifying and distinguishing unseen classes. To address these issues, we propose an innovative approach called High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning (HDAFL). HDAFL optimizes visual features by learning attribute features to obtain discriminative visual embeddings. Specifically, HDAFL utilizes multiple convolutional kernels to automatically learn discriminative regions highly correlated with attributes in images, eliminating irrelevant interference in image features. Furthermore, we introduce a Transformer-based attribute discrimination encoder to enhance the discriminative capability among attributes. Simultaneously, the method employs contrastive loss to alleviate dataset biases and enhance the transferability of visual features, facilitating better semantic transfer between seen and unseen classes. Experimental results demonstrate the effectiveness of HDAFL across three widely used datasets.
Authors: Zijin Yang, Kai Zeng, Kejiang Chen, Han Fang, Weiming Zhang, Nenghai Yu
Abstract: Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. However, existing methods often compromise the model performance or require additional training, which is undesirable for operators and users. To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of offending content. Our watermark embedding is free of model parameter modifications and thus is plug-and-play. We map the watermark to latent representations following a standard Gaussian distribution, which is indistinguishable from latent representations obtained from the non-watermarked diffusion model. Therefore we can achieve watermark embedding with lossless performance, for which we also provide theoretical proof. Furthermore, since the watermark is intricately linked with image semantics, it exhibits resilience to lossy processing and erasure attempts. The watermark can be extracted by Denoising Diffusion Implicit Models (DDIM) inversion and inverse sampling. We evaluate Gaussian Shading on multiple versions of Stable Diffusion, and the results demonstrate that Gaussian Shading not only is performance-lossless but also outperforms existing methods in terms of robustness.
Authors: Yutong Xie, Qi Chen, Sinuo Wang, Minh-Son To, Iris Lee, Ee Win Khoo, Kerolos Hendy, Daniel Koh, Yong Xia, Qi Wu
Abstract: Current vision-language pre-training (VLP) methodologies predominantly depend on paired image-text datasets, a resource that is challenging to acquire in radiology due to privacy considerations and labelling complexities. Data augmentation provides a practical solution to overcome the issue of data scarcity, however, most augmentation methods exhibit a limited focus, prioritising either image or text augmentation exclusively. Acknowledging this limitation, our objective is to devise a framework capable of concurrently augmenting medical image and text data. We design a Pairwise Augmentation (PairAug) approach that contains an Inter-patient Augmentation (InterAug) branch and an Intra-patient Augmentation (IntraAug) branch. Specifically, the InterAug branch of our approach generates radiology images using synthesised yet plausible reports derived from a Large Language Model (LLM). The generated pairs can be considered a collection of new patient cases since they are artificially created and may not exist in the original dataset. In contrast, the IntraAug branch uses newly generated reports to manipulate images. This process allows us to create new paired data for each individual with diverse medical conditions. Our extensive experiments on various downstream tasks covering medical image classification zero-shot and fine-tuning analysis demonstrate that our PairAug, concurrently expanding both image and text data, substantially outperforms image-/text-only expansion baselines and advanced medical VLP baselines. Our code is released at \url{https://github.com/YtongXie/PairAug}.
Authors: Jianghao Wu, Dong Guo, Guotai Wang, Qiang Yue, Huijun Yu, Kang Li, Shaoting Zhang
Abstract: Adapting a medical image segmentation model to a new domain is important for improving its cross-domain transferability, and due to the expensive annotation process, Unsupervised Domain Adaptation (UDA) is appealing where only unlabeled images are needed for the adaptation. Existing UDA methods are mainly based on image or feature alignment with adversarial training for regularization, and they are limited by insufficient supervision in the target domain. In this paper, we propose an enhanced Filtered Pseudo Label (FPL+)-based UDA method for 3D medical image segmentation. It first uses cross-domain data augmentation to translate labeled images in the source domain to a dual-domain training set consisting of a pseudo source-domain set and a pseudo target-domain set. To leverage the dual-domain augmented images to train a pseudo label generator, domain-specific batch normalization layers are used to deal with the domain shift while learning the domain-invariant structure features, generating high-quality pseudo labels for target-domain images. We then combine labeled source-domain images and target-domain images with pseudo labels to train a final segmentor, where image-level weighting based on uncertainty estimation and pixel-level weighting based on dual-domain consensus are proposed to mitigate the adverse effect of noisy pseudo labels. Experiments on three public multi-modal datasets for Vestibular Schwannoma, brain tumor and whole heart segmentation show that our method surpassed ten state-of-the-art UDA methods, and it even achieved better results than fully supervised learning in the target domain in some cases.
Authors: Demetris Lappas, Vasileios Argyriou, Dimitrios Makris
Abstract: We introduce Dynamic Distinction Learning (DDL) for Video Anomaly Detection, a novel video anomaly detection methodology that combines pseudo-anomalies, dynamic anomaly weighting, and a distinction loss function to improve detection accuracy. By training on pseudo-anomalies, our approach adapts to the variability of normal and anomalous behaviors without fixed anomaly thresholds. Our model showcases superior performance on the Ped2, Avenue and ShanghaiTech datasets, where individual models are tailored for each scene. These achievements highlight DDL's effectiveness in advancing anomaly detection, offering a scalable and adaptable solution for video surveillance challenges.
Authors: Haifeng Wang, Hao Xu, Jun Wang, Jian Zhou, Ke Deng
Abstract: Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications. Existing deep-learning-based methods for this problem either process each surgical video as a series of independent images without considering their dependence, or rely on complicated deep learning models to count for dependence of video frames. In this study, we revealed from exploratory data analysis that surgical videos enjoy relatively simple semantic structure, where the presence of surgical phases and tools can be well modeled by a compact hidden Markov model (HMM). Based on this observation, we propose an HMM-stabilized deep learning method for tool presence detection. A wide range of experiments confirm that the proposed approaches achieve better performance with lower training and running costs, and support more flexible ways to construct and utilize training data in scenarios where not all surgery videos of interest are extensively labelled. These results suggest that popular deep learning approaches with over-complicated model structures may suffer from inefficient utilization of data, and integrating ingredients of deep learning and statistical learning wisely may lead to more powerful algorithms that enjoy competitive performance, transparent interpretation and convenient model training simultaneously.
Authors: Pingping Zhang, Tianyu Yan, Yang Liu, Huchuan Lu
Abstract: As an important pillar of underwater intelligence, Marine Animal Segmentation (MAS) involves segmenting animals within marine environments. Previous methods don't excel in extracting long-range contextual features and overlook the connectivity between discrete pixels. Recently, Segment Anything Model (SAM) offers a universal framework for general segmentation tasks. Unfortunately, trained with natural images, SAM does not obtain the prior knowledge from marine images. In addition, the single-position prompt of SAM is very insufficient for prior guidance. To address these issues, we propose a novel feature learning framework, named Dual-SAM for high-performance MAS. To this end, we first introduce a dual structure with SAM's paradigm to enhance feature learning of marine images. Then, we propose a Multi-level Coupled Prompt (MCP) strategy to instruct comprehensive underwater prior information, and enhance the multi-level features of SAM's encoder with adapters. Subsequently, we design a Dilated Fusion Attention Module (DFAM) to progressively integrate multi-level features from SAM's encoder. Finally, instead of directly predicting the masks of marine animals, we propose a Criss-Cross Connectivity Prediction (C$^3$P) paradigm to capture the inter-connectivity between discrete pixels. With dual decoders, it generates pseudo-labels and achieves mutual supervision for complementary feature representations, resulting in considerable improvements over previous techniques. Extensive experiments verify that our proposed method achieves state-of-the-art performances on five widely-used MAS datasets. The code is available at https://github.com/Drchip61/Dual_SAM.
Authors: Jinpeng Wang, Bin Chen, Qiang Zhang, Zaiqiao Meng, Shangsong Liang, Shu-Tao Xia
Abstract: Deep quantization methods have shown high efficiency on large-scale image retrieval. However, current models heavily rely on ground-truth information, hindering the application of quantization in label-hungry scenarios. A more realistic demand is to learn from inexhaustible uploaded images that are associated with informal tags provided by amateur users. Though such sketchy tags do not obviously reveal the labels, they actually contain useful semantic information for supervising deep quantization. To this end, we propose Weakly-Supervised Deep Hyperspherical Quantization (WSDHQ), which is the first work to learn deep quantization from weakly tagged images. Specifically, 1) we use word embeddings to represent the tags and enhance their semantic information based on a tag correlation graph. 2) To better preserve semantic information in quantization codes and reduce quantization error, we jointly learn semantics-preserving embeddings and supervised quantizer on hypersphere by employing a well-designed fusion layer and tailor-made loss functions. Extensive experiments show that WSDHQ can achieve state-of-art performance on weakly-supervised compact coding. Code is available at https://github.com/gimpong/AAAI21-WSDHQ.
Authors: Gang Qu, Ping Wang, Xin Yuan
Abstract: Single-pixel imaging (SPI) is a potential computational imaging technique which produces image by solving an illposed reconstruction problem from few measurements captured by a single-pixel detector. Deep learning has achieved impressive success on SPI reconstruction. However, previous poor reconstruction performance and impractical imaging model limit its real-world applications. In this paper, we propose a deep unfolding network with hybrid-attention Transformer on Kronecker SPI model, dubbed HATNet, to improve the imaging quality of real SPI cameras. Specifically, we unfold the computation graph of the iterative shrinkagethresholding algorithm (ISTA) into two alternative modules: efficient tensor gradient descent and hybrid-attention multiscale denoising. By virtue of Kronecker SPI, the gradient descent module can avoid high computational overheads rooted in previous gradient descent modules based on vectorized SPI. The denoising module is an encoder-decoder architecture powered by dual-scale spatial attention for high- and low-frequency aggregation and channel attention for global information recalibration. Moreover, we build a SPI prototype to verify the effectiveness of the proposed method. Extensive experiments on synthetic and real data demonstrate that our method achieves the state-of-the-art performance. The source code and pre-trained models are available at https://github.com/Gang-Qu/HATNet-SPI.
Authors: Jiankai Tang, Xinyi Li, Jiacheng Liu, Xiyuxing Zhang, Zeyu Wang, Yuntao Wang
Abstract: Remote photoplethysmography (rPPG) emerges as a promising method for non-invasive, convenient measurement of vital signs, utilizing the widespread presence of cameras. Despite advancements, existing datasets fall short in terms of size and diversity, limiting comprehensive evaluation under diverse conditions. This paper presents an in-depth analysis of the VitalVideo dataset, the largest real-world rPPG dataset to date, encompassing 893 subjects and 6 Fitzpatrick skin tones. Our experimentation with six unsupervised methods and three supervised models demonstrates that datasets comprising a few hundred subjects(i.e., 300 for UBFC-rPPG, 500 for PURE, and 700 for MMPD-Simple) are sufficient for effective rPPG model training. Our findings highlight the importance of diversity and consistency in skin tones for precise performance evaluation across different datasets.
Authors: Shenghai Yuan, Jinfa Huang, Yujun Shi, Yongqi Xu, Ruijie Zhu, Bin Lin, Xinhua Cheng, Li Yuan, Jiebo Luo
Abstract: Recent advances in Text-to-Video generation (T2V) have achieved remarkable success in synthesizing high-quality general videos from textual descriptions. A largely overlooked problem in T2V is that existing models have not adequately encoded physical knowledge of the real world, thus generated videos tend to have limited motion and poor variations. In this paper, we propose \textbf{MagicTime}, a metamorphic time-lapse video generation model, which learns real-world physics knowledge from time-lapse videos and implements metamorphic generation. First, we design a MagicAdapter scheme to decouple spatial and temporal training, encode more physical knowledge from metamorphic videos, and transform pre-trained T2V models to generate metamorphic videos. Second, we introduce a Dynamic Frames Extraction strategy to adapt to metamorphic time-lapse videos, which have a wider variation range and cover dramatic object metamorphic processes, thus embodying more physical knowledge than general videos. Finally, we introduce a Magic Text-Encoder to improve the understanding of metamorphic video prompts. Furthermore, we create a time-lapse video-text dataset called \textbf{ChronoMagic}, specifically curated to unlock the metamorphic video generation ability. Extensive experiments demonstrate the superiority and effectiveness of MagicTime for generating high-quality and dynamic metamorphic videos, suggesting time-lapse video generation is a promising path toward building metamorphic simulators of the physical world.
Authors: Fanjie Kong, Yanbei Chen, Jiarui Cai, Davide Modolo
Abstract: Open-world detection poses significant challenges, as it requires the detection of any object using either object class labels or free-form texts. Existing related works often use large-scale manual annotated caption datasets for training, which are extremely expensive to collect. Instead, we propose to transfer knowledge from vision-language models (VLMs) to enrich the open-vocabulary descriptions automatically. Specifically, we bootstrap dense synthetic captions using pre-trained VLMs to provide rich descriptions on different regions in images, and incorporate these captions to train a novel detector that generalizes to novel concepts. To mitigate the noise caused by hallucination in synthetic captions, we also propose a novel hyperbolic vision-language learning approach to impose a hierarchy between visual and caption embeddings. We call our detector ``HyperLearner''. We conduct extensive experiments on a wide variety of open-world detection benchmarks (COCO, LVIS, Object Detection in the Wild, RefCOCO) and our results show that our model consistently outperforms existing state-of-the-art methods, such as GLIP, GLIPv2 and Grounding DINO, when using the same backbone.
Authors: Valentin Koch, Sophia J. Wagner, Salome Kazeminia, Ece Sancar, Matthias Hehr, Julia Schnabel, Tingying Peng, Carsten Marr
Abstract: In hematology, computational models offer significant potential to improve diagnostic accuracy, streamline workflows, and reduce the tedious work of analyzing single cells in peripheral blood or bone marrow smears. However, clinical adoption of computational models has been hampered by the lack of generalization due to large batch effects, small dataset sizes, and poor performance in transfer learning from natural images. To address these challenges, we introduce DinoBloom, the first foundation model for single cell images in hematology, utilizing a tailored DINOv2 pipeline. Our model is built upon an extensive collection of 13 diverse, publicly available datasets of peripheral blood and bone marrow smears, the most substantial open-source cohort in hematology so far, comprising over 380,000 white blood cell images. To assess its generalization capability, we evaluate it on an external dataset with a challenging domain shift. We show that our model outperforms existing medical and non-medical vision models in (i) linear probing and k-nearest neighbor evaluations for cell-type classification on blood and bone marrow smears and (ii) weakly supervised multiple instance learning for acute myeloid leukemia subtyping by a large margin. A family of four DinoBloom models (small, base, large, and giant) can be adapted for a wide range of downstream applications, be a strong baseline for classification problems, and facilitate the assessment of batch effects in new datasets. All models are available at github.com/marrlab/DinoBloom.
Authors: Saravanabalagi Ramachandran, Jonathan Horgan, Ganesh Sistu, John McDonald
Abstract: Hierarchical topological representations can significantly reduce search times within mapping and localization algorithms. Although recent research has shown the potential for such approaches, limited consideration has been given to the suitability and comparative performance of different global feature representations within this context. In this work, we evaluate state-of-the-art hand-crafted and learned global descriptors using a hierarchical topological mapping technique on benchmark datasets and present results of a comprehensive evaluation of the impact of the global descriptor used. Although learned descriptors have been incorporated into place recognition methods to improve retrieval accuracy and enhance overall recall, the problem of scalability and efficiency when applied to longer trajectories has not been adequately addressed in a majority of research studies. Based on our empirical analysis of multiple runs, we identify that continuity and distinctiveness are crucial characteristics for an optimal global descriptor that enable efficient and scalable hierarchical mapping, and present a methodology for quantifying and contrasting these characteristics across different global descriptors. Our study demonstrates that the use of global descriptors based on an unsupervised learned Variational Autoencoder (VAE) excels in these characteristics and achieves significantly lower runtime. It runs on a consumer grade desktop, up to 2.3x faster than the second best global descriptor, NetVLAD, and up to 9.5x faster than the hand-crafted descriptor, PHOG, on the longest track evaluated (St Lucia, 17.6 km), without sacrificing overall recall performance.
Authors: Shenbagaraj Kannapiran, Sreenithy Chandran, Suren Jayasuriya, Spring Berman
Abstract: The study of non-line-of-sight (NLOS) imaging is growing due to its many potential applications, including rescue operations and pedestrian detection by self-driving cars. However, implementing NLOS imaging on a moving camera remains an open area of research. Existing NLOS imaging methods rely on time-resolved detectors and laser configurations that require precise optical alignment, making it difficult to deploy them in dynamic environments. This work proposes a data-driven approach to NLOS imaging, PathFinder, that can be used with a standard RGB camera mounted on a small, power-constrained mobile robot, such as an aerial drone. Our experimental pipeline is designed to accurately estimate the 2D trajectory of a person who moves in a Manhattan-world environment while remaining hidden from the camera's field-of-view. We introduce a novel approach to process a sequence of dynamic successive frames in a line-of-sight (LOS) video using an attention-based neural network that performs inference in real-time. The method also includes a preprocessing selection metric that analyzes images from a moving camera which contain multiple vertical planar surfaces, such as walls and building facades, and extracts planes that return maximum NLOS information. We validate the approach on in-the-wild scenes using a drone for video capture, thus demonstrating low-cost NLOS imaging in dynamic capture environments.
Authors: Shiyi Zhang, Wenxun Dai, Sujia Wang, Xiangwei Shen, Jiwen Lu, Jie Zhou, Yansong Tang
Abstract: Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios. However, most existing methods and datasets focus on single-person short-sequence scenes, hindering the application of AQA in more complex situations. To address this issue, we construct a new multi-person long-form video dataset for action quality assessment named LOGO. Distinguished in scenario complexity, our dataset contains 200 videos from 26 artistic swimming events with 8 athletes in each sample along with an average duration of 204.2 seconds. As for richness in annotations, LOGO includes formation labels to depict group information of multiple athletes and detailed annotations on action procedures. Furthermore, we propose a simple yet effective method to model relations among athletes and reason about the potential temporal logic in long-form videos. Specifically, we design a group-aware attention module, which can be easily plugged into existing AQA methods, to enrich the clip-wise representations based on contextual group information. To benchmark LOGO, we systematically conduct investigations on the performance of several popular methods in AQA and action segmentation. The results reveal the challenges our dataset brings. Extensive experiments also show that our approach achieves state-of-the-art on the LOGO dataset. The dataset and code will be released at \url{https://github.com/shiyi-zh0408/LOGO }.
Authors: Liqiang Jing, Xinya Du
Abstract: Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give the sequence-level reward for the whole response; and (3)Annotation cost is time-consuming and labor-intensive. To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward. Specifically, We first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm. Extensive experiments are conducted on hallucination and general benchmarks, demonstrating the superior performance of our proposed method. Notably, compared with previous models trained with the RL-based aligning method, our proposed method is effective even with fewer parameters.
Authors: Md. Shahriar Rahman Anuvab, Mishkat Sultana, Md. Atif Hossain, Shashwata Das, Suvarthi Chowdhury, Rafeed Rahman, Dibyo Fabian Dofadar, Shahriar Rahman Rana
Abstract: Automatic License Plate Recognition (ALPR) is an integral component of an intelligent transport system with extensive applications in secure transportation, vehicle-to-vehicle communication, stolen vehicles detection, traffic violations, and traffic flow management. The existing license plate detection system focuses on one-shot learners or pre-trained models that operate with a geometric bounding box, limiting the model's performance. Furthermore, continuous video data streams uploaded to the central server result in network and complexity issues. To combat this, PlateSegFL was introduced, which implements U-Net-based segmentation along with Federated Learning (FL). U-Net is well-suited for multi-class image segmentation tasks because it can analyze a large number of classes and generate a pixel-level segmentation map for each class. Federated Learning is used to reduce the quantity of data required while safeguarding the user's privacy. Different computing platforms, such as mobile phones, are able to collaborate on the development of a standard prediction model where it makes efficient use of one's time; incorporates more diverse data; delivers projections in real-time; and requires no physical effort from the user; resulting around 95% F1 score.
Authors: Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, Yu Kong
Abstract: Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. However, traditional approaches primarily deploy models to discriminate among discrete emotion categories, and lack the fine granularity and reasoning capability for complex facial behaviors. The advent of Multi-modal Large Language Models (MLLMs) has been proven successful in general visual understanding tasks. However, directly harnessing MLLMs for FABA is challenging due to the scarcity of datasets and benchmarks, neglecting facial prior knowledge, and low training efficiency. To address these challenges, we introduce (i) an instruction-following dataset for two FABA tasks, e.g., emotion and action unit recognition, (ii) a benchmark FABA-Bench with a new metric considering both recognition and generation ability, and (iii) a new MLLM "EmoLA" as a strong baseline to the community. Our initiative on the dataset and benchmarks reveal the nature and rationale of facial affective behaviors, i.e., fine-grained facial movement, interpretability, and reasoning. Moreover, to build an effective and efficient FABA MLLM, we introduce a facial prior expert module with face structure knowledge and a low-rank adaptation module into pre-trained MLLM. We conduct extensive experiments on FABA-Bench and four commonly-used FABA datasets. The results demonstrate that the proposed facial prior expert can boost the performance and EmoLA achieves the best results on our FABA-Bench. On commonly-used FABA datasets, EmoLA is competitive rivaling task-specific state-of-the-art models.
Authors: Shir Nitzan, Maya Gilad, Moti Freiman
Abstract: Effective surgical planning for breast cancer hinges on accurately predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). Diffusion-weighted MRI (DWI) and machine learning offer a non-invasive approach for early pCR assessment. However, most machine-learning models require manual tumor segmentation, a cumbersome and error-prone task. We propose a deep learning model employing "Size-Adaptive Lesion Weighting" for automatic DWI tumor segmentation to enhance pCR prediction accuracy. Despite histopathological changes during NAC complicating DWI image segmentation, our model demonstrates robust performance. Utilizing the BMMR2 challenge dataset, it matches human experts in pCR prediction pre-NAC with an area under the curve (AUC) of 0.76 vs. 0.796, and surpasses standard automated methods mid-NAC, with an AUC of 0.729 vs. 0.654 and 0.576. Our approach represents a significant advancement in automating breast cancer treatment planning, enabling more reliable pCR predictions without manual segmentation.
Authors: Shiwei Jin, Peng Liu, Zhen Wang, Lei Wang, Ning Bi, Truong Nguyen
Abstract: Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors, which is an effective condition for facial expression manipulation. However, publicly available datasets containing intensity annotations for multiple AUs remain severely limited, often featuring a restricted number of subjects. This limitation places challenges to the AU intensity manipulation in images due to disentanglement issues, leading researchers to resort to other large datasets with pretrained AU intensity estimators for pseudo labels. In addressing this constraint and fully leveraging manual annotations of AU intensities for precise manipulation, we introduce AUEditNet. Our proposed model achieves impressive intensity manipulation across 12 AUs, trained effectively with only 18 subjects. Utilizing a dual-branch architecture, our approach achieves comprehensive disentanglement of facial attributes and identity without necessitating additional loss functions or implementing with large batch sizes. This approach offers a potential solution to achieve desired facial attribute editing despite the dataset's limited subject count. Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool. AUEditNet allows conditioning by either intensity values or target images, eliminating the need for constructing AU combinations for specific facial expression synthesis. Moreover, AU intensity estimation, as a downstream task, validates the consistency between real and edited images, confirming the effectiveness of our proposed AU intensity manipulation method.
Authors: Zihan Wang, Bowen Li, Chen Wang, Sebastian Scherer
Abstract: Few-shot object detection has drawn increasing attention in the field of robotic exploration, where robots are required to find unseen objects with a few online provided examples. Despite recent efforts have been made to yield online processing capabilities, slow inference speeds of low-powered robots fail to meet the demands of real-time detection-making them impractical for autonomous exploration. Existing methods still face performance and efficiency challenges, mainly due to unreliable features and exhaustive class loops. In this work, we propose a new paradigm AirShot, and discover that, by fully exploiting the valuable correlation map, AirShot can result in a more robust and faster few-shot object detection system, which is more applicable to robotics community. The core module Top Prediction Filter (TPF) can operate on multi-scale correlation maps in both the training and inference stages. During training, TPF supervises the generation of a more representative correlation map, while during inference, it reduces looping iterations by selecting top-ranked classes, thus cutting down on computational costs with better performance. Surprisingly, this dual functionality exhibits general effectiveness and efficiency on various off-the-shelf models. Exhaustive experiments on COCO2017, VOC2014, and SubT datasets demonstrate that TPF can significantly boost the efficacy and efficiency of most off-the-shelf models, achieving up to 36.4% precision improvements along with 56.3% faster inference speed. Code and Data are at: https://github.com/ImNotPrepared/AirShot.
Authors: Chiara Plizzari, Shubham Goel, Toby Perrett, Jacob Chalk, Angjoo Kanazawa, Dima Damen
Abstract: As humans move around, performing their daily tasks, they are able to recall where they have positioned objects in their environment, even if these objects are currently out of sight. In this paper, we aim to mimic this spatial cognition ability. We thus formulate the task of Out of Sight, Not Out of Mind - 3D tracking active objects using observations captured through an egocentric camera. We introduce Lift, Match and Keep (LMK), a method which lifts partial 2D observations to 3D world coordinates, matches them over time using visual appearance, 3D location and interactions to form object tracks, and keeps these object tracks even when they go out-of-view of the camera - hence keeping in mind what is out of sight. We test LMK on 100 long videos from EPIC-KITCHENS. Our results demonstrate that spatial cognition is critical for correctly locating objects over short and long time scales. E.g., for one long egocentric video, we estimate the 3D location of 50 active objects. Of these, 60% can be correctly positioned in 3D after 2 minutes of leaving the camera view.
Authors: Yimu Wang, Shuai Yuan, Xiangru Jian, Wei Pang, Mushi Wang, Ning Yu
Abstract: While recent progress in video-text retrieval has been driven by the exploration of powerful model architectures and training strategies, the representation learning ability of video-text retrieval models is still limited due to low-quality and scarce training data annotations. To address this issue, we present a novel video-text learning paradigm, HaVTR, which augments video and text data to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames. In addition, inspired by the recent advancement in visual and language generative models, we propose a more powerful augmentation method through textual paraphrasing and video stylization using large language models (LLMs) and visual generative models (VGMs). Further, to bring richer information into video and text, we propose a hallucination-based augmentation method, where we use LLMs and VGMs to generate and add new relevant information to the original data. Benefiting from the enriched data, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of HaVTR over existing methods.
Authors: Ziyang Wang, Jian-Qing Zheng, Chao Ma, Tao Guo
Abstract: Image registration, a critical process in medical imaging, involves aligning different sets of medical imaging data into a single unified coordinate system. Deep learning networks, such as the Convolutional Neural Network (CNN)-based VoxelMorph, Vision Transformer (ViT)-based TransMorph, and State Space Model (SSM)-based MambaMorph, have demonstrated effective performance in this domain. The recent Visual State Space Model (VMamba), which incorporates a cross-scan module with SSM, has exhibited promising improvements in modeling global-range dependencies with efficient computational cost in computer vision tasks. This paper hereby introduces an exploration of VMamba with image registration, named VMambaMorph. This novel hybrid VMamba-CNN network is designed specifically for 3D image registration. Utilizing a U-shaped network architecture, VMambaMorph computes the deformation field based on target and source volumes. The VMamba-based block with 2D cross-scan module is redesigned for 3D volumetric feature processing, and a fine-grained feature extraction module is proposed for high-dimensional feature learning. We validate VMambaMorph using a public benchmark brain MR-CT registration dataset, comparing its performance against current state-of-the-art methods. The results indicate that VMambaMorph achieves competitive registration quality. The code for VMambaMorph is available on GitHub.
Authors: Yujian Xiong, Wenhui Zhu, Zhong-Lin Lu, Yalin Wang
Abstract: The reconstruction of human visual inputs from brain activity, particularly through functional Magnetic Resonance Imaging (fMRI), holds promising avenues for unraveling the mechanisms of the human visual system. Despite the significant strides made by deep learning methods in improving the quality and interpretability of visual reconstruction, there remains a substantial demand for high-quality, long-duration, subject-specific 7-Tesla fMRI experiments. The challenge arises in integrating diverse smaller 3-Tesla datasets or accommodating new subjects with brief and low-quality fMRI scans. In response to these constraints, we propose a novel framework that generates enhanced 3T fMRI data through an unsupervised Generative Adversarial Network (GAN), leveraging unpaired training across two distinct fMRI datasets in 7T and 3T, respectively. This approach aims to overcome the limitations of the scarcity of high-quality 7-Tesla data and the challenges associated with brief and low-quality scans in 3-Tesla experiments. In this paper, we demonstrate the reconstruction capabilities of the enhanced 3T fMRI data, highlighting its proficiency in generating superior input visual images compared to data-intensive methods trained and tested on a single subject.
Authors: Shihong Wang, Ruixun Liu, Kaiyu Li, Jiawei Jiang, Xiangyong Cao
Abstract: In Generalized Few-shot Segmentation (GFSS), a model is trained with a large corpus of base class samples and then adapted on limited samples of novel classes. This paper focuses on the relevance between base and novel classes, and improves GFSS in two aspects: 1) mining the similarity between base and novel classes to promote the learning of novel classes, and 2) mitigating the class imbalance issue caused by the volume difference between the support set and the training set. Specifically, we first propose a similarity transition matrix to guide the learning of novel classes with base class knowledge. Then, we leverage the Label-Distribution-Aware Margin (LDAM) loss and Transductive Inference to the GFSS task to address the problem of class imbalance as well as overfitting the support set. In addition, by extending the probability transition matrix, the proposed method can mitigate the catastrophic forgetting of base classes when learning novel classes. With a simple training phase, our proposed method can be applied to any segmentation network trained on base classes. We validated our methods on the adapted version of OpenEarthMap. Compared to existing GFSS baselines, our method excels them all from 3% to 7% and ranks second in the OpenEarthMap Land Cover Mapping Few-Shot Challenge at the completion of this paper. Code: https://github.com/earth-insights/ClassTrans
Authors: Nazifa Azam Khan, Mikolaj Cieslak, Ian McQuillan
Abstract: Artificial neural networks are often used to identify features of crop plants. However, training their models requires many annotated images, which can be expensive and time-consuming to acquire. Procedural models of plants, such as those developed with Lindenmayer-systems (L-systems) can be created to produce visually realistic simulations, and hence images of plant simulations, where annotations are implicitly known. These synthetic images can either augment or completely replace real images in training neural networks for phenotyping tasks. In this paper, we systematically vary amounts of real and synthetic images used for training in both maize and canola to better understand situations where synthetic images generated from L-systems can help prediction on real images. This work also explores the degree to which realism in the synthetic images improves prediction. Furthermore, we see how neural network predictions can be used to help calibrate L-systems themselves, creating a feedback loop.
Authors: Irwandi Hipiny, Johari Abdullah, Noor Alamshah Bolhassan
Abstract: The manual extraction method of Agarwood resinous compound is laborious work, requires skilled workers, and is subject to human errors. Commercial Agarwood industries have been actively exploring using Computer Numerical Control (CNC) machines to replace human effort for this particular task. The CNC machine accepts a G-code script produced from a binary image in which the wood region that needs to be chiselled off is marked with (0, 0, 0) as its RGB value. Rather than requiring a human expert to perform the region marking, we propose using a Deep learning image segmentation method instead. Our setup involves a camera that captures the cross-section image and then passes the image file to a computer. The computer performs the automated image segmentation and feeds the CNC machine with a G-code script. In this article, we report the initial segmentation results achieved using a state-of-the-art Deep learning segmentation method and discuss potential improvements to refine the segmentation accuracy.
Authors: Zijia Lu, Bing Shuai, Yanbei Chen, Zhenlin Xu, Davide Modolo
Abstract: In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.
Authors: Yurong You, Cheng Perng Phoo, Carlos Andres Diaz-Ruiz, Katie Z Luo, Wei-Lun Chao, Mark Campbell, Bharath Hariharan, Kilian Q Weinberger
Abstract: Accurate 3D object detection is crucial to autonomous driving. Though LiDAR-based detectors have achieved impressive performance, the high cost of LiDAR sensors precludes their widespread adoption in affordable vehicles. Camera-based detectors are cheaper alternatives but often suffer inferior performance compared to their LiDAR-based counterparts due to inherent depth ambiguities in images. In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data. Specifically, at inference time, we assume that the camera-based detectors have access to multiple unlabeled LiDAR scans from past traversals at locations of interest (potentially from other high-end vehicles equipped with LiDAR sensors). Under this setup, we proposed a novel, simple, and end-to-end trainable framework, termed AsyncDepth, to effectively extract relevant features from asynchronous LiDAR traversals of the same location for monocular 3D detectors. We show consistent and significant performance gain (up to 9 AP) across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost.
Authors: Haimei Zhao, Jing Zhang, Zhuo Chen, Shanshan Zhao, Dacheng Tao
Abstract: LiDAR semantic segmentation (LSS) is a critical task in autonomous driving and has achieved promising progress. However, prior LSS methods are conventionally investigated and evaluated on datasets within the same domain in clear weather. The robustness of LSS models in unseen scenes and all weather conditions is crucial for ensuring safety and reliability in real applications. To this end, we propose UniMix, a universal method that enhances the adaptability and generalizability of LSS models. UniMix first leverages physically valid adverse weather simulation to construct a Bridge Domain, which serves to bridge the domain gap between the clear weather scenes and the adverse weather scenes. Then, a Universal Mixing operator is defined regarding spatial, intensity, and semantic distributions to create the intermediate domain with mixed samples from given domains. Integrating the proposed two techniques into a teacher-student framework, UniMix efficiently mitigates the domain gap and enables LSS models to learn weather-robust and domain-invariant representations. We devote UniMix to two main setups: 1) unsupervised domain adaption, adapting the model from the clear weather source domain to the adverse weather target domain; 2) domain generalization, learning a model that generalizes well to unseen scenes in adverse weather. Extensive experiments validate the effectiveness of UniMix across different tasks and datasets, all achieving superior performance over state-of-the-art methods. The code will be released.
Authors: Fengrui Tian, Yueqi Duan, Angtian Wang, Jianfei Guo, Shaoyi Du
Abstract: In this work, we pioneer Semantic Flow, a neural semantic representation of dynamic scenes from monocular videos. In contrast to previous NeRF methods that reconstruct dynamic scenes from the colors and volume densities of individual points, Semantic Flow learns semantics from continuous flows that contain rich 3D motion information. As there is 2D-to-3D ambiguity problem in the viewing direction when extracting 3D flow features from 2D video frames, we consider the volume densities as opacity priors that describe the contributions of flow features to the semantics on the frames. More specifically, we first learn a flow network to predict flows in the dynamic scene, and propose a flow feature aggregation module to extract flow features from video frames. Then, we propose a flow attention module to extract motion information from flow features, which is followed by a semantic network to output semantic logits of flows. We integrate the logits with volume densities in the viewing direction to supervise the flow features with semantic labels on video frames. Experimental results show that our model is able to learn from multiple dynamic scenes and supports a series of new tasks such as instance-level scene editing, semantic completions, dynamic scene tracking and semantic adaption on novel scenes. Codes are available at https://github.com/tianfr/Semantic-Flow/.
Authors: Junlin Hou, Jilan Xu, Rui Feng, Hao Chen
Abstract: Due to the complexity of medical image acquisition and the difficulty of annotation, medical image datasets inevitably contain noise. Noisy data with wrong labels affects the robustness and generalization ability of deep neural networks. Previous noise learning methods mainly considered noise arising from images being mislabeled, i.e. label noise, assuming that all mislabeled images are of high image quality. However, medical images are prone to suffering extreme quality issues, i.e. data noise, where discriminative visual features are missing for disease diagnosis. In this paper, we propose a noise learning framework, termed as QMix, that learns a robust disease diagnosis model under mixed noise. QMix alternates between sample separation and quality-aware semisupervised training in each training epoch. In the sample separation phase, we design a joint uncertainty-loss criterion to effectively separate (1) correctly labeled images; (2) mislabeled images with high quality and (3) mislabeled images with low quality. In the semi-supervised training phase, we train a disease diagnosis model to learn robust feature representation from the separated samples. Specifically, we devise a sample-reweighing loss to mitigate the effect of mislabeled images with low quality during training. Meanwhile, a contrastive enhancement loss is proposed to further distinguish mislabeled images with low quality from correctly labeled images. QMix achieved state-of-the-art disease diagnosis performance on five public retinal image datasets and exhibited substantial improvement on robustness against mixed noise.
Authors: Zhiyuan Yang, Ryan Rad
Abstract: Solar Photovoltaic (PV) technology is increasingly recognized as a pivotal solution in the global pursuit of clean and renewable energy. This technology addresses the urgent need for sustainable energy alternatives by converting solar power into electricity without greenhouse gas emissions. It not only curtails global carbon emissions but also reduces reliance on finite, non-renewable energy sources. In this context, monitoring solar panel farms becomes essential for understanding and facilitating the worldwide shift toward clean energy. This study contributes to this effort by developing the first comprehensive global dataset of multispectral satellite imagery of solar panel farms. This dataset is intended to form the basis for training robust machine learning models, which can accurately map and analyze the expansion and distribution of solar panel farms globally. The insights gained from this endeavor will be instrumental in guiding informed decision-making for a sustainable energy future. https://github.com/yzyly1992/GloSoFarID
Authors: Qinglu Min, Jie Zhao, Zhihao Zhang, Chen Min
Abstract: Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties for deep depth based MVS approaches. Regression based loss leads to inaccurate continuous results by computing mathematical expectation, while classification based loss outputs discretized depth values. To this end, we then propose a novel loss function, named adaptive Wasserstein loss, which is able to narrow down the difference between the true and predicted probability distributions of depth. Besides, a simple but effective offset module is introduced to better achieve sub-pixel prediction accuracy. Extensive experiments on different benchmarks, including DTU, Tanks and Temples and BlendedMVS, show that the proposed method with the adaptive Wasserstein loss and the offset module achieves state-of-the-art performance.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Chun-Hung Sun, Kuang-Ming Wu
Abstract: Traditional defect classification approaches are facing with two barriers. (1) Insufficient training data and unstable data quality. Collecting sufficient defective sample is expensive and time-costing, consequently leading to dataset variance. It introduces the difficulty on recognition and learning. (2) Over-dependence on visual modality. When the image pattern and texture is monotonic for all defect classes in a given dataset, the performance of conventional AOI system cannot be guaranteed. In scenarios where image quality is compromised due to mechanical failures or when defect information is inherently difficult to discern, the performance of deep models cannot be guaranteed. A main question is, "how to solve those two problems when they occur at the same time?" The feasible strategy is to explore another feature within dataset and combine an eminent vision-language model (VLM) and Large-Language model (LLM) with their astonishing zero-shot capability. In this work, we propose the special ASE dataset, including rich data description recorded on image, for defect classification, but the defect feature is uneasy to learn directly. Secondly, We present the prompting for VLM-LLM against defect classification with the proposed ASE dataset to activate extra-modality feature from images to enhance performance. Then, We design the novel progressive feature alignment (PFA) block to refine image-text feature to alleviate the difficulty of alignment under few-shot scenario. Finally, the proposed Cross-modality attention fusion (CMAF) module can effectively fuse different modality feature. Experiment results have demonstrated our method's effectiveness over several defect classification methods for the ASE dataset.
Authors: Yufeng Yue, Yinan Deng, Jiahui Wang, Yi Yang
Abstract: Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying. However, existing algorithms usually rely on conflicting raw observations as training data, resulting in poor map performance. In this paper, we propose LGSDF, an ESDF continual Global learning algorithm aided by Local updating. At the front end, axis-aligned grids are dynamically updated by pre-processed sensor observations, where incremental fusion alleviates estimation error caused by limited viewing directions. At the back end, a randomly initialized implicit ESDF neural network performs continual self-supervised learning guided by these grids to generate smooth and continuous maps. The results on multiple scenes show that LGSDF can construct more accurate ESDF maps and meshes compared with SOTA (State Of The Art) explicit and implicit mapping algorithms. The source code of LGSDF is publicly available at https://github.com/BIT-DYN/LGSDF.
Authors: Chenhao Xu, Chang-Tsun Li, Chee Peng Lim, Douglas Creighton
Abstract: While the Vision Transformer (ViT) architecture gains prominence in computer vision and attracts significant attention from multimedia communities, its deficiency in prior knowledge (inductive bias) regarding shift, scale, and rotational invariance necessitates pre-training on large-scale datasets. Furthermore, the growing layers and parameters in both ViT and convolutional neural networks (CNNs) impede their applicability to mobile multimedia services, primarily owing to the constrained computational resources on edge devices. To mitigate the aforementioned challenges, this paper introduces a novel horizontally scalable vision transformer (HSViT). Specifically, a novel image-level feature embedding allows ViT to better leverage the inductive bias inherent in the convolutional layers. Based on this, an innovative horizontally scalable architecture is designed, which reduces the number of layers and parameters of the models while facilitating collaborative training and inference of ViT models across multiple nodes. The experimental results depict that, without pre-training on large-scale datasets, HSViT achieves up to 10% higher top-1 accuracy than state-of-the-art schemes, ascertaining its superior preservation of inductive bias. The code is available at https://github.com/xuchenhao001/HSViT.
Authors: Babak Poorebrahim Gilkalaye, Shubhabrata Mukherjee, Reza Derakhshani
Abstract: Given the irrevocability of biometric samples and mounting privacy concerns, biometric template security and secure matching are among the essential features of any well-designed modern biometric system. In this paper, we propose an obfuscation method that hides the biometric template information with just enough chaff. The main idea is to reduce the number of chaff points to a practical level by creating n sub-templates from the original template and hiding each sub-template with m chaff points. During verification, s closest vectors to the biometric query are retrieved from each vault and then combined to generate hash values that are compared with the stored hash value. We demonstrate the effectiveness of synthetic facial images, generated by a Generative Adversarial Network (GAN), as ``random chaff points'' within a secure-vault authorization system. This approach safeguards user identities during training and deployment. We tested our protocol using the AT&T, GT, and LFW face datasets, with the ROC areas under the curve being 0.99, 0.99, and 0.90, respectively. These numbers were close to those of the unprotected templates, showing that our method does not adversely affect accuracy.
Authors: Changan Chen, Kumar Ashutosh, Rohit Girdhar, David Harwath, Kristen Grauman
Abstract: We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Whereas existing methods rely on curated data with known audio-visual correspondence, our multimodal contrastive-consensus coding (MC3) embedding reinforces the associations between audio, language, and vision when all modality pairs agree, while diminishing those associations when any one pair does not. We show our approach can successfully discover how the long tail of human actions sound from egocentric video, outperforming an array of recent multimodal embedding techniques on two datasets (Ego4D and EPIC-Sounds) and multiple cross-modal tasks.
Authors: Nan Zhou, Jiaxin Chen, Di Huang
Abstract: Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby neglecting the usage of task-relevant information encoded in prompt tokens across layers. Additionally, existing prompt structures are prone to interference from task-irrelevant noise in input images, which can do harm to the sharing of task-relevant information. In this paper, we propose a novel VPT approach, \textbf{iVPT}. It innovatively incorporates a cross-layer dynamic connection (CDC) for input prompt tokens from adjacent layers, enabling effective sharing of task-relevant information. Furthermore, we design a dynamic aggregation (DA) module that facilitates selective sharing of information between layers. The combination of CDC and DA enhances the flexibility of the attention process within the VPT framework. Building upon these foundations, iVPT introduces an attentive reinforcement (AR) mechanism, by automatically identifying salient image tokens, which are further enhanced by prompt tokens in an additive manner. Extensive experiments on 24 image classification and semantic segmentation benchmarks clearly demonstrate the advantage of the proposed iVPT, compared to the state-of-the-art counterparts.
Authors: George Leotescu, Daniel Voinea, Alin-Ionut Popa
Abstract: The transformer is a powerful data modelling framework responsible for remarkable performance on a wide range of tasks. However, they are limited in terms of scalability as it is suboptimal and inefficient to process long-sequence data. To this purpose we introduce BLRP (Bidirectional Long-Range Parser), a novel and versatile attention mechanism designed to increase performance and efficiency on long-sequence tasks. It leverages short and long range heuristics in the form of a local sliding window approach combined with a global bidirectional latent space synthesis technique. We show the benefits and versatility of our approach on vision and language domains by demonstrating competitive results against state-of-the-art methods on the Long-Range-Arena and CIFAR benchmarks together with ablations demonstrating the computational efficiency.
Authors: Jingxin Wang, Renxiang Guan, Kainan Gao, Zihao Li, Hao Li, Xianju Li, Chang Tang
Abstract: Hyperspectral image (HSI) clustering is a challenging task due to its high complexity. Despite subspace clustering shows impressive performance for HSI, traditional methods tend to ignore the global-local interaction in HSI data. In this study, we proposed a multi-level graph subspace contrastive learning (MLGSC) for HSI clustering. The model is divided into the following main parts. Graph convolution subspace construction: utilizing spectral and texture feautures to construct two graph convolution views. Local-global graph representation: local graph representations were obtained by step-by-step convolutions and a more representative global graph representation was obtained using an attention-based pooling strategy. Multi-level graph subspace contrastive learning: multi-level contrastive learning was conducted to obtain local-global joint graph representations, to improve the consistency of the positive samples between views, and to obtain more robust graph embeddings. Specifically, graph-level contrastive learning is used to better learn global representations of HSI data. Node-level intra-view and inter-view contrastive learning is designed to learn joint representations of local regions of HSI. The proposed model is evaluated on four popular HSI datasets: Indian Pines, Pavia University, Houston, and Xu Zhou. The overall accuracies are 97.75%, 99.96%, 92.28%, and 95.73%, which significantly outperforms the current state-of-the-art clustering methods.
Authors: Yingtao Tian
Abstract: Chinese, Japanese, and Korean (CJK), with a vast number of native speakers, has profound influence on society and culture. The typesetting of CJK languages carries a wide range of requirements due to the complexity of their scripts and unique literary traditions. A critical aspect of this typesetting process is that CJK fonts need to provide a set of consistent-looking glyphs for approximately one hundred thousand characters. However, creating such a font is inherently labor-intensive and expensive, which significantly hampers the development of new CJK fonts for typesetting, historical, aesthetic, or artistic purposes. To bridge this gap, we are motivated by recent advancements in diffusion-based generative models and propose a novel diffusion method for generating glyphs in a targeted style from a \emph{single} conditioned, standard glyph form. Our experiments show that our method is capable of generating fonts of both printed and hand-written styles, the latter of which presents a greater challenge. Moreover, our approach shows remarkable zero-shot generalization capabilities for non-CJK but Chinese-inspired scripts. We also show our method facilitates smooth style interpolation and generates bitmap images suitable for vectorization, which is crucial in the font creation process. In summary, our proposed method opens the door to high-quality, generative model-assisted font creation for CJK characters, for both typesetting and artistic endeavors.
Authors: Swati Jindal, Mohit Yadav, Roberto Manduchi
Abstract: Gaze is an essential prompt for analyzing human behavior and attention. Recently, there has been an increasing interest in determining gaze direction from facial videos. However, video gaze estimation faces significant challenges, such as understanding the dynamic evolution of gaze in video sequences, dealing with static backgrounds, and adapting to variations in illumination. To address these challenges, we propose a simple and novel deep learning model designed to estimate gaze from videos, incorporating a specialized attention module. Our method employs a spatial attention mechanism that tracks spatial dynamics within videos. This technique enables accurate gaze direction prediction through a temporal sequence model, adeptly transforming spatial observations into temporal insights, thereby significantly improving gaze estimation accuracy. Additionally, our approach integrates Gaussian processes to include individual-specific traits, facilitating the personalization of our model with just a few labeled samples. Experimental results confirm the efficacy of the proposed approach, demonstrating its success in both within-dataset and cross-dataset settings. Specifically, our proposed approach achieves state-of-the-art performance on the Gaze360 dataset, improving by $2.5^\circ$ without personalization. Further, by personalizing the model with just three samples, we achieved an additional improvement of $0.8^\circ$. The code and pre-trained models are available at \url{https://github.com/jswati31/stage}.
Authors: Jaewoo Jeong, Daehee Park, Kuk-Jin Yoon
Abstract: Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In this paper, we propose an interaction-aware trajectory-conditioned long-term multi-agent human pose forecasting model, utilizing a coarse-to-fine prediction approach: multi-modal global trajectories are initially forecasted, followed by respective local pose forecasts conditioned on each mode. In doing so, our Trajectory2Pose model introduces a graph-based agent-wise interaction module for a reciprocal forecast of local motion-conditioned global trajectory and trajectory-conditioned local pose. Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments. Furthermore, we address the lack of long-term (6s+) multi-agent (5+) datasets by constructing a new dataset from real-world images and 2D annotations, enabling a comprehensive evaluation of our proposed model. State-of-the-art prediction performance on both complex and simpler datasets confirms the generalized effectiveness of our method. The code is available at https://github.com/Jaewoo97/T2P.
Authors: Dingxi Zhang, Zhuoxun Chen, Yu-Jie Yuan, Fang-Lue Zhang, Zhenliang He, Shiguang Shan, Lin Gao
Abstract: With the rapid development of XR, 3D generation and editing are becoming more and more important, among which, stylization is an important tool of 3D appearance editing. It can achieve consistent 3D artistic stylization given a single reference style image and thus is a user-friendly editing way. However, recent NeRF-based 3D stylization methods face efficiency issues that affect the actual user experience and the implicit nature limits its ability to transfer the geometric pattern styles. Additionally, the ability for artists to exert flexible control over stylized scenes is considered highly desirable, fostering an environment conducive to creative exploration. In this paper, we introduce StylizedGS, a 3D neural style transfer framework with adaptable control over perceptual factors based on 3D Gaussian Splatting (3DGS) representation. The 3DGS brings the benefits of high efficiency. We propose a GS filter to eliminate floaters in the reconstruction which affects the stylization effects before stylization. Then the nearest neighbor-based style loss is introduced to achieve stylization by fine-tuning the geometry and color parameters of 3DGS, while a depth preservation loss with other regularizations is proposed to prevent the tampering of geometry content. Moreover, facilitated by specially designed losses, StylizedGS enables users to control color, stylized scale and regions during the stylization to possess customized capabilities. Our method can attain high-quality stylization results characterized by faithful brushstrokes and geometric consistency with flexible controls. Extensive experiments across various scenes and styles demonstrate the effectiveness and efficiency of our method concerning both stylization quality and inference FPS.
Authors: Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng, Zhi Yu, Cong Yao
Abstract: Recently, leveraging large language models (LLMs) or multimodal large language models (MLLMs) for document understanding has been proven very promising. However, previous works that employ LLMs/MLLMs for document understanding have not fully explored and utilized the document layout information, which is vital for precise document understanding. In this paper, we propose LayoutLLM, an LLM/MLLM based method for document understanding. The core of LayoutLLM is a layout instruction tuning strategy, which is specially designed to enhance the comprehension and utilization of document layouts. The proposed layout instruction tuning strategy consists of two components: Layout-aware Pre-training and Layout-aware Supervised Fine-tuning. To capture the characteristics of document layout in Layout-aware Pre-training, three groups of pre-training tasks, corresponding to document-level, region-level and segment-level information, are introduced. Furthermore, a novel module called layout chain-of-thought (LayoutCoT) is devised to enable LayoutLLM to focus on regions relevant to the question and generate accurate answers. LayoutCoT is effective for boosting the performance of document understanding. Meanwhile, it brings a certain degree of interpretability, which could facilitate manual inspection and correction. Experiments on standard benchmarks show that the proposed LayoutLLM significantly outperforms existing methods that adopt open-source 7B LLMs/MLLMs for document understanding. The training data of the LayoutLLM is publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/LayoutLLM
Authors: Xiaofan Li, Zhizhong Zhang, Xin Tan, Chengwei Chen, Yanyun Qu, Yuan Xie, Lizhuang Ma
Abstract: The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering. For automated scenarios, we first use conventional prompt learning with many-class paradigm as the baseline to automatically learn prompts but found that it can not work well in one-class anomaly detection. To address the above problem, this paper proposes a one-class prompt learning method for few-shot anomaly detection, termed PromptAD. First, we propose semantic concatenation which can transpose normal prompts into anomaly prompts by concatenating normal prompts with anomaly suffixes, thus constructing a large number of negative samples used to guide prompt learning in one-class setting. Furthermore, to mitigate the training challenge caused by the absence of anomaly images, we introduce the concept of explicit anomaly margin, which is used to explicitly control the margin between normal prompt features and anomaly prompt features through a hyper-parameter. For image-level/pixel-level anomaly detection, PromptAD achieves first place in 11/12 few-shot settings on MVTec and VisA.
Authors: Y. Wang, A. Gao, Y. Gong, Y. Zeng
Abstract: Recently, a surge of 3D style transfer methods has been proposed that leverage the scene reconstruction power of a pre-trained neural radiance field (NeRF). To successfully stylize a scene this way, one must first reconstruct a photo-realistic radiance field from collected images of the scene. However, when only sparse input views are available, pre-trained few-shot NeRFs often suffer from high-frequency artifacts, which are generated as a by-product of high-frequency details for improving reconstruction quality. Is it possible to generate more faithful stylized scenes from sparse inputs by directly optimizing encoding-based scene representation with target style? In this paper, we consider the stylization of sparse-view scenes in terms of disentangling content semantics and style textures. We propose a coarse-to-fine sparse-view scene stylization framework, where a novel hierarchical encoding-based neural representation is designed to generate high-quality stylized scenes directly from implicit scene representations. We also propose a new optimization strategy with content strength annealing to achieve realistic stylization and better content preservation. Extensive experiments demonstrate that our method can achieve high-quality stylization of sparse-view scenes and outperforms fine-tuning-based baselines in terms of stylization quality and efficiency.
Authors: Giang Nguyen, Mohammad Reza Taesiri, Sunnie S. Y. Kim, Anh Nguyen
Abstract: Via thousands of papers in Explainable AI (XAI), attention maps \cite{vaswani2017attention} and feature attribution maps \cite{bansal2020sam} have been established as a common means for explaining the input features that are important to AI's decisions. It is an interesting but unexplored question whether allowing users to edit the importance scores of input features at test time would improve the human-AI team's accuracy on downstream tasks. In this paper, we address this question by taking CHM-Corr, a state-of-the-art, ante-hoc explanation method \cite{taesiri2022visual} that first predicts patch-wise correspondences between the input and the training-set images, and then uses them to make classification decisions. We build an interactive interface on top of CHM-Corr, enabling users to directly edit the initial feature attribution map provided by CHM-Corr. Via our CHM-Corr++ interface, users gain insights into if, when, and how the model changes its outputs, enhancing understanding beyond static explanations. Our user study with 18 machine learning researchers who performed $\sim$1,400 decisions shows that our interactive approach does not improve user accuracy on CUB-200 bird image classification over static explanations. This challenges the belief that interactivity inherently boosts XAI effectiveness~\cite{sokol2020one,sun2022exploring,shen2024towards,singh2024rethinking,mindlin2024beyond,lakkaraju2022rethinking,cheng2019explaining,liu2021understanding} and raises needs for future research. Our work contributes to the field by open-sourcing an interactive tool for manipulating model attention, and it lays the groundwork for future research to enable effective human-AI interaction in computer vision. We release code and data on \href{https://anonymous.4open.science/r/CHMCorrPlusPlus/}{github}. Our interface are available \href{http://137.184.82.109:7080/}{here}.
URLs: https://anonymous.4open.science/r/CHMCorrPlusPlus/, http://137.184.82.109:7080/
Authors: Xu Wu, XianXu Hou, Zhihui Lai, Jie Zhou, Ya-nan Zhang, Witold Pedrycz, Linlin Shen
Abstract: Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion.
Authors: Junseo Park, Beomseok Ko, Hyeryung Jang
Abstract: Recent advancements in text-to-image models, such as Stable Diffusion, have demonstrated their ability to synthesize visual images through natural language prompts. One approach of personalizing text-to-image models, exemplified by DreamBooth, fine-tunes the pre-trained model by binding unique text identifiers with a few images of a specific subject. Although existing fine-tuning methods have demonstrated competence in rendering images according to the styles of famous painters, it is still challenging to learn to produce images encapsulating distinct art styles due to abstract and broad visual perceptions of stylistic attributes such as lines, shapes, textures, and colors. In this paper, we introduce a new method, Single-StyleForge, for personalization. It fine-tunes pre-trained text-to-image diffusion models to generate diverse images in specified styles from text prompts. By using around 15-20 images of the target style, the approach establishes a foundational binding of a unique token identifier with a broad range of the target style. It also utilizes auxiliary images to strengthen this binding, resulting in offering specific guidance on representing elements such as persons in a target style-consistent manner. In addition, we present ways to improve the quality of style and text-image alignment through a method called Multi-StyleForge, which inherits the strategy used in StyleForge and learns tokens in multiple. Experimental evaluation conducted on six distinct artistic styles demonstrates substantial improvements in both the quality of generated images and the perceptual fidelity metrics, such as FID, KID, and CLIP scores.
Authors: Judy X Yang, Jun Zhou, Jing Wang, Hui Tian, Alan Wee Chung Liew
Abstract: Band selection in hyperspectral imaging (HSI) is critical for optimising data processing and enhancing analytical accuracy. Traditional approaches have predominantly concentrated on analysing spectral and pixel characteristics within individual bands independently. These approaches overlook the potential benefits of integrating multiple data sources, such as Light Detection and Ranging (LiDAR), and is further challenged by the limited availability of labeled data in HSI processing, which represents a significant obstacle. To address these challenges, this paper introduces a novel unsupervised band selection framework that incorporates attention mechanisms and an Autoencoder for reconstruction-based band selection. Our methodology distinctively integrates HSI with LiDAR data through an attention score, using a convolutional Autoencoder to process the combined feature mask. This fusion effectively captures essential spatial and spectral features and reduces redundancy in hyperspectral datasets. A comprehensive comparative analysis of our innovative fused band selection approach is performed against existing unsupervised band selection and fusion models. We used data sets such as Houston 2013, Trento, and MUUFLE for our experiments. The results demonstrate that our method achieves superior classification accuracy and significantly outperforms existing models. This enhancement in HSI band selection, facilitated by the incorporation of LiDAR features, underscores the considerable advantages of integrating features from different sources.
Authors: Jiaxiu Jiang, Yabo Zhang, Kailai Feng, Xiaohe Wu, Wangmeng Zuo
Abstract: Customized text-to-image generation aims to synthesize instantiations of user-specified concepts and has achieved unprecedented progress in handling individual concept. However, when extending to multiple customized concepts, existing methods exhibit limitations in terms of flexibility and fidelity, only accommodating the combination of limited types of models and potentially resulting in a mix of characteristics from different concepts. In this paper, we introduce the Multi-concept guidance for Multi-concept customization, termed MC$^2$, for improved flexibility and fidelity. MC$^2$ decouples the requirements for model architecture via inference time optimization, allowing the integration of various heterogeneous single-concept customized models. It adaptively refines the attention weights between visual and textual tokens, directing image regions to focus on their associated words while diminishing the impact of irrelevant ones. Extensive experiments demonstrate that MC$^2$ even surpasses previous methods that require additional training in terms of consistency with input prompt and reference images. Moreover, MC$^2$ can be extended to elevate the compositional capabilities of text-to-image generation, yielding appealing results. Code will be publicly available at https://github.com/JIANGJiaXiu/MC-2.
Authors: Ping Wang, Lishun Wang, Xin Yuan
Abstract: Video snapshot compressive imaging (SCI) aims to capture a sequence of video frames with only a single shot of a 2D detector, whose backbones rest in optical modulation patterns (also known as masks) and a computational reconstruction algorithm. Advanced deep learning algorithms and mature hardware are putting video SCI into practical applications. Yet, there are two clouds in the sunshine of SCI: i) low dynamic range as a victim of high temporal multiplexing, and ii) existing deep learning algorithms' degradation on real system. To address these challenges, this paper presents a deep optics framework to jointly optimize masks and a reconstruction network. Specifically, we first propose a new type of structural mask to realize motion-aware and full-dynamic-range measurement. Considering the motion awareness property in measurement domain, we develop an efficient network for video SCI reconstruction using Transformer to capture long-term temporal dependencies, dubbed Res2former. Moreover, sensor response is introduced into the forward model of video SCI to guarantee end-to-end model training close to real system. Finally, we implement the learned structural masks on a digital micro-mirror device. Experimental results on synthetic and real data validate the effectiveness of the proposed framework. We believe this is a milestone for real-world video SCI. The source code and data are available at https://github.com/pwangcs/DeepOpticsSCI.
Authors: Xiahan Chen, Mingjian Chen, Sanli Tang, Yi Niu, Jiang Zhu
Abstract: 3D object detection based on roadside cameras is an additional way for autonomous driving to alleviate the challenges of occlusion and short perception range from vehicle cameras. Previous methods for roadside 3D object detection mainly focus on modeling the depth or height of objects, neglecting the stationary of cameras and the characteristic of inter-frame consistency. In this work, we propose a novel framework, namely MOSE, for MOnocular 3D object detection with Scene cuEs. The scene cues are the frame-invariant scene-specific features, which are crucial for object localization and can be intuitively regarded as the height between the surface of the real road and the virtual ground plane. In the proposed framework, a scene cue bank is designed to aggregate scene cues from multiple frames of the same scene with a carefully designed extrinsic augmentation strategy. Then, a transformer-based decoder lifts the aggregated scene cues as well as the 3D position embeddings for 3D object location, which boosts generalization ability in heterologous scenes. The extensive experiment results on two public benchmarks demonstrate the state-of-the-art performance of the proposed method, which surpasses the existing methods by a large margin.
Authors: Haitian Zhang, Chang Xu, Xinya Wang, Bingde Liu, Guang Hua, Lei Yu, Wen Yang
Abstract: Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly rely on ordinary cameras, but these frame-based sensors usually have high latency and limited dynamic range, leading to safety risks in real-world scenarios. In this study, we turn to a new modality enabled by the so-called event camera, featured by its sub-millisecond latency and high dynamic range, for robust CAOD. We propose Detecting Every Object in Events (DEOE), an approach tailored for achieving high-speed, class-agnostic open-world object detection in event-based vision. Built upon the fast event-based backbone: recurrent vision transformer, we jointly consider the spatial and temporal consistencies to identify potential objects. The discovered potential objects are assimilated as soft positive samples to avoid being suppressed as background. Moreover, we introduce a disentangled objectness head to separate the foreground-background classification and novel object discovery tasks, enhancing the model's generalization in localizing novel objects while maintaining a strong ability to filter out the background. Extensive experiments confirm the superiority of our proposed DEOE in comparison with three strong baseline methods that integrate the state-of-the-art event-based object detector with advancements in RGB-based CAOD. Our code is available at https://github.com/Hatins/DEOE.
Authors: Valerio Biscione, Dong Yin, Gaurav Malhotra, Marin Dujmovic, Milton L. Montero, Guillermo Puebla, Federico Adolfi, Rachel F. Heaton, John E. Hummel, Benjamin D. Evans, Karim Habashy, Jeffrey S. Bowers
Abstract: Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox MindSet: Vision, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible at https://github.com/MindSetVision/mindset-vision. We test ResNet-152 on each of these methods as an example of how the toolbox can be used.
Authors: Su-Xi Yu, Jing-Yuan He, Yi Wang, Yu-Jiao Cai, Jun Yang, Bo Lin, Wei-Bin Yang, Jian Ruan
Abstract: Graves' disease is a common condition that is diagnosed clinically by determining the smoothness of the thyroid texture and its morphology in ultrasound images. Currently, the most widely used approach for the automated diagnosis of Graves' disease utilizes Convolutional Neural Networks (CNNs) for both feature extraction and classification. However, these methods demonstrate limited efficacy in capturing texture features. Given the high capacity of wavelets in describing texture features, this research integrates learnable wavelet modules utilizing the Lifting Scheme into CNNs and incorporates a parallel wavelet branch into the ResNet18 model to enhance texture feature extraction. Our model can analyze texture features in spatial and frequency domains simultaneously, leading to optimized classification accuracy. We conducted experiments on collected ultrasound datasets and publicly available natural image texture datasets, our proposed network achieved 97.27% accuracy and 95.60% recall on ultrasound datasets, 60.765% accuracy on natural image texture datasets, surpassing the accuracy of ResNet and conrming the effectiveness of our approach.
Authors: Mikael Skog, Oleksandr Kotlyar, Vladim\'ir Kubelka, Martin Magnusson
Abstract: Autonomous driving technology is increasingly being used on public roads and in industrial settings such as mines. While it is essential to detect pedestrians, vehicles, or other obstacles, adverse field conditions negatively affect the performance of classical sensors such as cameras or lidars. Radar, on the other hand, is a promising modality that is less affected by, e.g., dust, smoke, water mist or fog. In particular, modern 4D imaging radars provide target responses across the range, vertical angle, horizontal angle and Doppler velocity dimensions. We propose TMVA4D, a CNN architecture that leverages this 4D radar modality for semantic segmentation. The CNN is trained to distinguish between the background and person classes based on a series of 2D projections of the 4D radar data that include the elevation, azimuth, range, and Doppler velocity dimensions. We also outline the process of compiling a novel dataset consisting of data collected in industrial settings with a car-mounted 4D radar and describe how the ground-truth labels were generated from reference thermal images. Using TMVA4D on this dataset, we achieve an mIoU score of 78.2% and an mDice score of 86.1%, evaluated on the two classes background and person
Authors: Philipp Rigoll, Laurenz Adolph, Lennart Ries, Eric Sax
Abstract: Perception systems, especially cameras, are the eyes of automated driving systems. Ensuring that they function reliably and robustly is therefore an important building block in the automation of vehicles. There are various approaches to test the perception of automated driving systems. Ultimately, however, it always comes down to the investigation of the behavior of perception systems under specific input data. Camera images are a crucial part of the input data. Image data sets are therefore collected for the testing of automated driving systems, but it is non-trivial to find specific images in these data sets. Thanks to recent developments in neural networks, there are now methods for sorting the images in a data set according to their similarity to a prompt in natural language. In order to further automate the provision of search results, we make a contribution by automating the threshold definition in these sorted results and returning only the images relevant to the prompt as a result. Our focus is on preventing false positives and false negatives equally. It is also important that our method is robust and in the case that our assumptions are not fulfilled, we provide a fallback solution.
Authors: Giuseppe Macario
Abstract: This work proposes a WebXR-based cross-platform conceptual architecture, leveraging the A-Frame and Networked-Aframe frameworks, in order to facilitate the development of an open, accessible, and interoperable metaverse. By introducing the concept of spatial web app, this research contributes to the discourse on the metaverse, offering an architecture that democratizes access to virtual environments and extended reality through the web, and aligns with Tim Berners-Lee's original vision of the World Wide Web as an open platform in the digital realm.
Authors: Zhiqi Huang, Huixin Xiong, Haoyu Wang, Longguang Wang, Zhiheng Li
Abstract: Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the control of objects in the generated images. However, existing methods still suffer limited accuracy when the relationship between the foreground and background is complicated. To address this issue, we develop a framework termed Mask-ControlNet by introducing an additional mask prompt. Specifically, we first employ large vision models to obtain masks to segment the objects of interest in the reference image. Then, the object images are employed as additional prompts to facilitate the diffusion model to better understand the relationship between foreground and background regions during image generation. Experiments show that the mask prompts enhance the controllability of the diffusion model to maintain higher fidelity to the reference image while achieving better image quality. Comparison with previous text-to-image generation methods demonstrates our method's superior quantitative and qualitative performance on the benchmark datasets.
Authors: Yu-Hsi Chen
Abstract: Automated data labeling techniques are crucial for accelerating the development of deep learning models, particularly in complex medical imaging applications. However, ensuring accuracy and efficiency remains challenging. This paper presents iterative refinement strategies for automated data labeling in facial landmark diagnosis to enhance accuracy and efficiency for deep learning models in medical applications, including dermatology, plastic surgery, and ophthalmology. Leveraging feedback mechanisms and advanced algorithms, our approach iteratively refines initial labels, reducing reliance on manual intervention while improving label quality. Through empirical evaluation and case studies, we demonstrate the effectiveness of our proposed strategies in deep learning tasks across medical imaging domains. Our results highlight the importance of iterative refinement in automated data labeling to enhance the capabilities of deep learning systems in medical imaging applications.
Authors: David Hagens, Jan Knaup, Elke Hergenr\"other, Andreas Weinmann
Abstract: The automation of games using Deep Reinforcement Learning Strategies (DRL) is a well-known challenge in AI research. While for feature extraction in a video game typically the whole image is used, this is hardly practical for many real world games. Instead, using a smaller game state reducing the dimension of the parameter space to include essential parameters only seems to be a promising approach. In the game of Foosball, a compact and comprehensive game state description consists of the positional shifts and rotations of the figures and the position of the ball over time. In particular, velocities and accelerations can be derived from consecutive time samples of the game state. In this paper, a figure detection system to determine the game state in Foosball is presented. We capture a dataset containing the rotations of the rods which were measured using accelerometers and the positional shifts were derived using traditional Computer Vision techniques (in a laboratory setting). This dataset is utilized to train Convolutional Neural Network (CNN) based end-to-end regression models to predict the rotations and shifts of each rod. We present an evaluation of our system using different state-of-the-art CNNs as base architectures for the regression model. We show that our system is able to predict the game state with high accuracy. By providing data for both black and white teams, the presented system is intended to provide the required data for future developments of Imitation Learning techniques w.r.t. to observing human players.
Authors: Hassan Keshvarikhojasteh, Josien Pluim, Mitko Veta
Abstract: This paper introduces MAD-MIL, a Multi-head Attention-based Deep Multiple Instance Learning model, designed for weakly supervised Whole Slide Images (WSIs) classification in digital pathology. Inspired by the multi-head attention mechanism of the Transformer, MAD-MIL simplifies model complexity while achieving competitive results against advanced models like CLAM and DS-MIL. Evaluated on the MNIST-BAGS and public datasets, including TUPAC16, TCGA BRCA, TCGA LUNG, and TCGA KIDNEY, MAD-MIL consistently outperforms ABMIL. This demonstrates enhanced information diversity, interpretability, and efficiency in slide representation. The model's effectiveness, coupled with fewer trainable parameters and lower computational complexity makes it a promising solution for automated pathology workflows. Our code is available at https://github.com/tueimage/MAD-MIL.
Authors: Sai Bhargav Rongali, Sarthak Mehrotra, Ankit Jha, Mohamad Hassan N C, Shirsha Bose, Tanisha Gupta, Mainak Singha, Biplab Banerjee
Abstract: In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we present a novel setting: Across Domain Generalized Category Discovery (AD-GCD) and bring forth CDAD-NET (Class Discoverer Across Domains) as a remedy. CDAD-NET is architected to synchronize potential known class samples across both the labeled (source) and unlabeled (target) datasets, while emphasizing the distinct categorization of the target data. To facilitate this, we propose an entropy-driven adversarial learning strategy that accounts for the distance distributions of target samples relative to source-domain class prototypes. Parallelly, the discriminative nature of the shared space is upheld through a fusion of three metric learning objectives. In the source domain, our focus is on refining the proximity between samples and their affiliated class prototypes, while in the target domain, we integrate a neighborhood-centric contrastive learning mechanism, enriched with an adept neighborsmining approach. To further accentuate the nuanced feature interrelation among semantically aligned images, we champion the concept of conditional image inpainting, underscoring the premise that semantically analogous images prove more efficacious to the task than their disjointed counterparts. Experimentally, CDAD-NET eclipses existing literature with a performance increment of 8-15% on three AD-GCD benchmarks we present.
Authors: Dazhong Shen, Guanglu Song, Zeyue Xue, Fu-Yun Wang, Yu Liu
Abstract: Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space. However, we argue that a global CFG scale results in spatial inconsistency on varying semantic strengths and suboptimal image quality. To address this problem, we present a novel approach, Semantic-aware Classifier-Free Guidance (S-CFG), to customize the guidance degrees for different semantic units in text-to-image diffusion models. Specifically, we first design a training-free semantic segmentation method to partition the latent image into relatively independent semantic regions at each denoising step. In particular, the cross-attention map in the denoising U-net backbone is renormalized for assigning each patch to the corresponding token, while the self-attention map is used to complete the semantic regions. Then, to balance the amplification of diverse semantic units, we adaptively adjust the CFG scales across different semantic regions to rescale the text guidance degrees into a uniform level. Finally, extensive experiments demonstrate the superiority of S-CFG over the original CFG strategy on various text-to-image diffusion models, without requiring any extra training cost. our codes are available at https://github.com/SmilesDZgk/S-CFG.
Authors: Artur Xarles, Sergio Escalera, Thomas B. Moeslund, Albert Clap\'es
Abstract: In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame representations, high output temporal resolution to maintain prediction precision, and the necessity to capture information at different temporal scales to handle events with varying dynamics. It tackles these challenges through its specifically designed architecture, featuring an encoder-decoder for leveraging multiple temporal scales and achieving high output temporal resolution, along with temporal modules designed to increase token discriminability. Leveraging these characteristics, T-DEED achieves SOTA performance on the FigureSkating and FineDiving datasets.
Authors: Khoi Do, Duong Nguyen, Nguyen H. Tran, Viet Dung Nguyen
Abstract: Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization, and 2) pixel-wise class-specific loss adaptation (PCLA). First, the class-wise gradient magnitude homogenization helps alleviate the imbalance among label masks by ensuring equal consideration of the class-wise impact on model updates. Second, PCLA tackles the detrimental impact of both rare classes within the long-tailed distribution and inaccurate predictions from previous training stages by encouraging learning classes with low prediction confidence and guarding against forgetting classes with high confidence. This combined approach fosters robust learning while preventing the model from forgetting previously learned knowledge. PAT exhibits significant performance improvements, surpassing the current state-of-the-art by 2.2% in the NyU dataset. Moreover, it enhances overall pixel-wise accuracy by 2.85% and intersection over union value by 2.07%, with a particularly notable declination of 0.39% in detecting rare classes compared to Balance Logits Variation, as demonstrated on the three popular datasets, i.e., OxfordPetIII, CityScape, and NYU.
Authors: Maksym Ivashechkin, Oscar Mendez, Richard Bowden
Abstract: 3D hand pose estimation from images has seen considerable interest from the literature, with new methods improving overall 3D accuracy. One current challenge is to address hand-to-hand interaction where self-occlusions and finger articulation pose a significant problem to estimation. Little work has applied physical constraints that minimize the hand intersections that occur as a result of noisy estimation. This work addresses the intersection of hands by exploiting an occupancy network that represents the hand's volume as a continuous manifold. This allows us to model the probability distribution of points being inside a hand. We designed an intersection loss function to minimize the likelihood of hand-to-point intersections. Moreover, we propose a new hand mesh parameterization that is superior to the commonly used MANO model in many respects including lower mesh complexity, underlying 3D skeleton extraction, watertightness, etc. On the benchmark InterHand2.6M dataset, the models trained using our intersection loss achieve better results than the state-of-the-art by significantly decreasing the number of hand intersections while lowering the mean per-joint positional error. Additionally, we demonstrate superior performance for 3D hand uplift on Re:InterHand and SMILE datasets and show reduced hand-to-hand intersections for complex domains such as sign-language pose estimation.
Authors: Benedetta Liberatori, Alessandro Conti, Paolo Rota, Yiming Wang, Elisa Ricci
Abstract: Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While effective, training-based ZS-TAL approaches assume the availability of labeled data for supervised learning, which can be impractical in some applications. Furthermore, the training process naturally induces a domain bias into the learned model, which may adversely affect the model's generalization ability to arbitrary videos. These considerations prompt us to approach the ZS-TAL problem from a radically novel perspective, relaxing the requirement for training data. To this aim, we introduce a novel method that performs Test-Time adaptation for Temporal Action Localization (T3AL). In a nutshell, T3AL adapts a pre-trained Vision and Language Model (VLM). T3AL operates in three steps. First, a video-level pseudo-label of the action category is computed by aggregating information from the entire video. Then, action localization is performed adopting a novel procedure inspired by self-supervised learning. Finally, frame-level textual descriptions extracted with a state-of-the-art captioning model are employed for refining the action region proposals. We validate the effectiveness of T3AL by conducting experiments on the THUMOS14 and the ActivityNet-v1.3 datasets. Our results demonstrate that T3AL significantly outperforms zero-shot baselines based on state-of-the-art VLMs, confirming the benefit of a test-time adaptation approach.
Authors: Meenakshi Sarkar, Debasish Ghose
Abstract: Long-term video generation and prediction remain challenging tasks in computer vision, particularly in partially observable scenarios where cameras are mounted on moving platforms. The interaction between observed image frames and the motion of the recording agent introduces additional complexities. To address these issues, we introduce the Action-Conditioned Video Generation (ACVG) framework, a novel approach that investigates the relationship between actions and generated image frames through a deep dual Generator-Actor architecture. ACVG generates video sequences conditioned on the actions of robots, enabling exploration and analysis of how vision and action mutually influence one another in dynamic environments. We evaluate the framework's effectiveness on an indoor robot motion dataset which consists of sequences of image frames along with the sequences of actions taken by the robotic agent, conducting a comprehensive empirical study comparing ACVG to other state-of-the-art frameworks along with a detailed ablation study.
Authors: Gregory Sech, Giulio Poggi, Marina Ljubenovic, Marco Fiorucci, Arianna Traviglia
Abstract: Hyperspectral data recorded from satellite platforms are often ill-suited for geo-archaeological prospection due to low spatial resolution. The established potential of hyperspectral data from airborne sensors in identifying archaeological features has, on the other side, generated increased interest in enhancing hyperspectral data to achieve higher spatial resolution. This improvement is crucial for detecting traces linked to sub-surface geo-archaeological features and can make satellite hyperspectral acquisitions more suitable for archaeological research. This research assesses the usability of pansharpened PRISMA satellite products in geo-archaeological prospections. Three pan-sharpening methods (GSA, MTF-GLP and HySure) are compared quantitatively and qualitatively and tested over the archaeological landscape of Aquileia (Italy). The results suggest that the application of pansharpening techniques makes hyperspectral satellite imagery highly suitable, under certain conditions, to the identification of sub-surface archaeological features of small and large size.
Authors: Lluis Castrejon, Thomas Mensink, Howard Zhou, Vittorio Ferrari, Andre Araujo, Jasper Uijlings
Abstract: Combining Large Language Models (LLMs) with external specialized tools (LLMs+tools) is a recent paradigm to solve multimodal tasks such as Visual Question Answering (VQA). While this approach was demonstrated to work well when optimized and evaluated for each individual benchmark, in practice it is crucial for the next generation of real-world AI systems to handle a broad range of multimodal problems. Therefore we pose the VQA problem from a unified perspective and evaluate a single system on a varied suite of VQA tasks including counting, spatial reasoning, OCR-based reasoning, visual pointing, external knowledge, and more. In this setting, we demonstrate that naively applying the LLM+tools approach using the combined set of all tools leads to poor results. This motivates us to introduce HAMMR: HierArchical MultiModal React. We start from a multimodal ReAct-based system and make it hierarchical by enabling our HAMMR agents to call upon other specialized agents. This enhances the compositionality of the LLM+tools approach, which we show to be critical for obtaining high accuracy on generic VQA. Concretely, on our generic VQA suite, HAMMR outperforms the naive LLM+tools approach by 19.5%. Additionally, HAMMR achieves state-of-the-art results on this task, outperforming the generic standalone PaLI-X VQA model by 5.0%.
Authors: He Wang, Pengcheng Guo, Xucheng Wan, Huan Zhou, Lei Xie
Abstract: Automatic lip-reading (ALR) aims to automatically transcribe spoken content from a speaker's silent lip motion captured in video. Current mainstream lip-reading approaches only use a single visual encoder to model input videos of a single scale. In this paper, we propose to enhance lipreading by incorporating multi-scale video data and multi-encoder. Specifically, we first propose a novel multi-scale lip extraction algorithm based on the size of the speaker's face and an enhanced ResNet3D visual front-end (VFE) to extract lip features at different scales. For the multi-encoder, in addition to the mainstream Transformer and Conformer, we also incorporate the recently proposed Branchformer and EBranchformer as visual encoders. In the experiments, we explore the influence of different video data scales and encoders on ALR system performance and fuse the texts transcribed by all ALR systems using recognizer output voting error reduction (ROVER). Finally, our proposed approach placed second in the ICME 2024 ChatCLR Challenge Task 2, with a 21.52% reduction in character error rate (CER) compared to the official baseline on the evaluation set.
Authors: Baiyi Li, Edmond S. L. Ho, Hubert P. H. Shum, He Wang
Abstract: Close and continuous interaction with rich contacts is a crucial aspect of human activities (e.g. hugging, dancing) and of interest in many domains like activity recognition, motion prediction, character animation, etc. However, acquiring such skeletal motion is challenging. While direct motion capture is expensive and slow, motion editing/generation is also non-trivial, as complex contact patterns with topological and geometric constraints have to be retained. To this end, we propose a new deep learning method for two-body skeletal interaction motion augmentation, which can generate variations of contact-rich interactions with varying body sizes and proportions while retaining the key geometric/topological relations between two bodies. Our system can learn effectively from a relatively small amount of data and generalize to drastically different skeleton sizes. Through exhaustive evaluation and comparison, we show it can generate high-quality motions, has strong generalizability and outperforms traditional optimization-based methods and alternative deep learning solutions.
Authors: Hamed Haghighi, Amir Samadi, Mehrdad Dianati, Valentina Donzella, Kurt Debattista
Abstract: Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling. However, DMs often fail to realistically model Lidar raydrop noise due to their inherent denoising process. To retain the strength of iterative sampling while enhancing the generation of raydrop noise, we introduce LidarGRIT, a generative model that uses auto-regressive transformers to iteratively sample the range images in the latent space rather than image space. Furthermore, LidarGRIT utilises VQ-VAE to separately decode range images and raydrop masks. Our results show that LidarGRIT achieves superior performance compared to SOTA models on KITTI-360 and KITTI odometry datasets. Code available at:https://github.com/hamedhaghighi/LidarGRIT.
Authors: Raveerat Jaturapitpornchai, Giulio Poggi, Gregory Sech, Ziga Kokalj, Marco Fiorucci, Arianna Traviglia
Abstract: Deep learning methods in LiDAR-based archaeological research often leverage visualisation techniques derived from Digital Elevation Models to enhance characteristics of archaeological objects present in the images. This paper investigates the impact of visualisations on deep learning performance through a comprehensive testing framework. The study involves the use of eight semantic segmentation models to evaluate seven diverse visualisations across two study areas, encompassing five archaeological classes. Experimental results reveal that the choice of appropriate visualisations can influence performance by up to 8%. Yet, pinpointing one visualisation that outperforms the others in segmenting all archaeological classes proves challenging. The observed performance variation, reaching up to 25% across different model configurations, underscores the importance of thoughtfully selecting model configurations and LiDAR visualisations for successfully segmenting archaeological objects.
Authors: Jiapeng Wu, Yichen Liu
Abstract: Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap of object bounding boxes leads to confusion among closely located objects. Nevertheless, humans naturally perceive the depth of elements in a scene when observing 2D videos. Inspired by this, even though the bounding boxes of objects are close on the camera plane, we can differentiate them in the depth dimension, thereby establishing a 3D perception of the objects. (ii) For videos with rapidly irregular camera motion, abrupt changes in object positions can result in ID switches. However, if the camera pose are known, we can compensate for the errors in linear motion models. In this paper, we propose \textit{DepthMOT}, which achieves: (i) detecting and estimating scene depth map \textit{end-to-end}, (ii) compensating the irregular camera motion by camera pose estimation. Extensive experiments demonstrate the superior performance of DepthMOT in VisDrone-MOT and UAVDT datasets. The code will be available at \url{https://github.com/JackWoo0831/DepthMOT}.
Authors: Saman Motamed, Wouter Van Gansbeke, Luc Van Gool
Abstract: With recent advances in image and video diffusion models for content creation, a plethora of techniques have been proposed for customizing their generated content. In particular, manipulating the cross-attention layers of Text-to-Image (T2I) diffusion models has shown great promise in controlling the shape and location of objects in the scene. Transferring image-editing techniques to the video domain, however, is extremely challenging as object motion and temporal consistency are difficult to capture accurately. In this work, we take a first look at the role of cross-attention in Text-to-Video (T2V) diffusion models for zero-shot video editing. While one-shot models have shown potential in controlling motion and camera movement, we demonstrate zero-shot control over object shape, position and movement in T2V models. We show that despite the limitations of current T2V models, cross-attention guidance can be a promising approach for editing videos.
Authors: Jacob Chalk, Jaesung Huh, Evangelos Kazakos, Andrew Zisserman, Dima Damen
Abstract: Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale interval queries, outperforming SOTA on EPIC-KITCHENS-100 for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of integrating the two modalities and modelling their time intervals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM
Authors: Mahsa Ehsanpour, Ian Reid, Hamid Rezatofighi
Abstract: For a complete comprehension of multi-person scenes, it is essential to go beyond basic tasks like detection and tracking. Higher-level tasks, such as understanding the interactions and social activities among individuals, are also crucial. Progress towards models that can fully understand scenes involving multiple people is hindered by a lack of sufficient annotated data for such high-level tasks. To address this challenge, we introduce Social-MAE, a simple yet effective transformer-based masked autoencoder framework for multi-person human motion data. The framework uses masked modeling to pre-train the encoder to reconstruct masked human joint trajectories, enabling it to learn generalizable and data efficient representations of motion in human crowded scenes. Social-MAE comprises a transformer as the MAE encoder and a lighter-weight transformer as the MAE decoder which operates on multi-person joints' trajectory in the frequency domain. After the reconstruction task, the MAE decoder is replaced with a task-specific decoder and the model is fine-tuned end-to-end for a variety of high-level social tasks. Our proposed model combined with our pre-training approach achieves the state-of-the-art results on various high-level social tasks, including multi-person pose forecasting, social grouping, and social action understanding. These improvements are demonstrated across four popular multi-person datasets encompassing both human 2D and 3D body pose.
Authors: Minheng Ni, Yeli Shen, Lei Zhang, Wangmeng Zuo
Abstract: With recent advancements in visual synthesis, there is a growing risk of encountering images with detrimental effects, such as hate, discrimination, or privacy violations. The research on transforming harmful images into responsible ones remains unexplored. In this paper, we formulate a new task, responsible visual editing, which entails modifying specific concepts within an image to render it more responsible while minimizing changes. However, the concept that needs to be edited is often abstract, making it challenging to locate what needs to be modified and plan how to modify it. To tackle these challenges, we propose a Cognitive Editor (CoEditor) that harnesses the large multimodal model through a two-stage cognitive process: (1) a perceptual cognitive process to focus on what needs to be modified and (2) a behavioral cognitive process to strategize how to modify. To mitigate the negative implications of harmful images on research, we create a transparent and public dataset, AltBear, which expresses harmful information using teddy bears instead of humans. Experiments demonstrate that CoEditor can effectively comprehend abstract concepts within complex scenes and significantly surpass the performance of baseline models for responsible visual editing. We find that the AltBear dataset corresponds well to the harmful content found in real images, offering a consistent experimental evaluation, thereby providing a safer benchmark for future research. Moreover, CoEditor also shows great results in general editing. We release our code and dataset at https://github.com/kodenii/Responsible-Visual-Editing.
URLs: https://github.com/kodenii/Responsible-Visual-Editing.
Authors: Yue-Hua Han, Tai-Ming Huang, Shu-Tzu Lo, Po-Han Huang, Kai-Lung Hua, Jun-Cheng Chen
Abstract: With the rise of deep learning, generative models have enabled the creation of highly realistic synthetic images, presenting challenges due to their potential misuse. While research in Deepfake detection has grown rapidly in response, many detection methods struggle with unseen Deepfakes generated by new synthesis techniques. To address this generalisation challenge, we propose a novel Deepfake detection approach by adapting rich information encoded inside the Foundation Models with rich information encoded inside, specifically using the image encoder from CLIP which has demonstrated strong zero-shot capability for downstream tasks. Inspired by the recent advances of parameter efficient fine-tuning, we propose a novel side-network-based decoder to extract spatial and temporal cues from the given video clip, with the promotion of the Facial Component Guidance (FCG) to guidencourage the spatial feature to include features of key facial parts for more robust and general Deepfake detection. Through extensive cross-dataset evaluations, our approach exhibits superior effectiveness in identifying unseen Deepfake samples, achieving notable performance improvementsuccess even with limited training samples and manipulation types. Our model secures an average performance enhancement of 0.9% AUROC in cross-dataset assessments comparing with state-of-the-art methods, especiallytablishing a significant lead of achieving 4.4% improvement on the challenging DFDC dataset.
Authors: Michael Deutges, Ario Sadafi, Nassir Navab, Carsten Marr
Abstract: Diagnosis of hematological malignancies depends on accurate identification of white blood cells in peripheral blood smears. Deep learning techniques are emerging as a viable solution to scale and optimize this process by automatic identification of cells in laboratories. However, these techniques face several challenges such as limited generalizability, sensitivity to domain shifts and lack of explainability. Here, we are introducing a novel approach based on neural cellular automata (NCA) for white blood cell classification. We test our approach on three datasets of white blood cell images and show that we achieve competitive performance compared to conventional methods. Our NCA-based method is significantly smaller in terms of parameters and exhibits robustness to domain shifts. Furthermore, the architecture is inherently explainable, providing insights into the decision process for each classification, helping experts understand and validate model predictions. Results demonstrate that NCA not only can be used for image classification, but also address key challenges of conventional methods, indicating a high potential for applicability in clinical practice.
Authors: Jiacheng Zhang, Jie Wu, Yuxi Ren, Xin Xia, Huafeng Kuang, Pan Xie, Jiashi Li, Xuefeng Xiao, Weilin Huang, Min Zheng, Lean Fu, Guanbin Li
Abstract: Diffusion models have revolutionized the field of image generation, leading to the proliferation of high-quality models and diverse downstream applications. However, despite these significant advancements, the current competitive solutions still suffer from several limitations, including inferior visual quality, a lack of aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL incorporates three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which optimizes inference speed. In-depth experiments and extensive user studies validate the superior performance of our proposed method in enhancing both the quality of generated models and their acceleration. For instance, UniFL surpasses ImageReward by 17% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57% and 20% in 4-step inference. Moreover, we have verified the efficacy of our approach in downstream tasks, including Lora, ControlNet, and AnimateDiff.
Authors: Zhipeng Zhang, Zhimin Wei, Guolei Sun, Peng Wang, Luc Van Gool
Abstract: In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks. However, they encounter a main challenge of action ambiguity, illustrated by the vagueness like whether to beat or carry a drum, and the complexities involved in processing intricate scenes. Moreover, it is important for human intervention to rectify robot errors in time. To address these issues, we introduce Self-Explainable Affordance learning (SEA) with embodied caption. This innovation enables robots to articulate their intentions and bridge the gap between explainable vision-language caption and visual affordance learning. Due to a lack of appropriate dataset, we unveil a pioneering dataset and metrics tailored for this task, which integrates images, heatmaps, and embodied captions. Furthermore, we propose a novel model to effectively combine affordance grounding with self-explanation in a simple but efficient manner. Extensive quantitative and qualitative experiments demonstrate our method's effectiveness.
Authors: Yating Wang, Ran Yi, Ke Fan, Jinkun Hao, Jiangbo Lu, Lizhuang Ma
Abstract: Face meshes in consistent topology serve as the foundation for many face-related applications, such as 3DMM constrained face reconstruction and expression retargeting. Traditional methods commonly acquire topology uniformed face meshes by two separate steps: multi-view stereo (MVS) to reconstruct shapes followed by non-rigid registration to align topology, but struggles with handling noise and non-lambertian surfaces. Recently neural volume rendering techniques have been rapidly evolved and shown great advantages in 3D reconstruction or novel view synthesis. Our goal is to leverage the superiority of neural volume rendering into multi-view reconstruction of face mesh with consistent topology. We propose a mesh volume rendering method that enables directly optimizing mesh geometry while preserving topology, and learning implicit features to model complex facial appearance from multi-view images. The key innovation lies in spreading sparse mesh features into the surrounding space to simulate radiance field required for volume rendering, which facilitates backpropagation of gradients from images to mesh geometry and implicit appearance features. Our proposed feature spreading module exhibits deformation invariance, enabling photorealistic rendering seamlessly after mesh editing. We conduct experiments on multi-view face image dataset to evaluate the reconstruction and implement an application for photorealistic rendering of animated face mesh.
Authors: Guokai Zhang, Lanjun Wang, Yuting Su, An-An Liu
Abstract: Nowadays, the family of Stable Diffusion (SD) models has gained prominence for its high quality outputs and scalability. This has also raised security concerns on social media, as malicious users can create and disseminate harmful content. Existing approaches involve training components or entire SDs to embed a watermark in generated images for traceability and responsibility attribution. However, in the era of AI-generated content (AIGC), the rapid iteration of SDs renders retraining with watermark models costly. To address this, we propose a training-free plug-and-play watermark framework for SDs. Without modifying any components of SDs, we embed diverse watermarks in the latent space, adapting to the denoising process. Our experimental findings reveal that our method effectively harmonizes image quality and watermark invisibility. Furthermore, it performs robustly under various attacks. We also have validated that our method is generalized to multiple versions of SDs, even without retraining the watermark model.
Authors: Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci
Abstract: While excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing parameters via model pruning is a viable solution. However, existing techniques for VLMs are task-specific, and thus require pruning the network from scratch for each new task of interest. In this work, we explore a new direction: Task-Agnostic Vision-Language Pruning (TA-VLP). Given a pretrained VLM, the goal is to find a unique pruned counterpart transferable to multiple unknown downstream tasks. In this challenging setting, the transferable representations already encoded in the pretrained model are a key aspect to preserve. Thus, we propose Multimodal Flow Pruning (MULTIFLOW), a first, gradient-free, pruning framework for TA-VLP where: (i) the importance of a parameter is expressed in terms of its magnitude and its information flow, by incorporating the saliency of the neurons it connects; and (ii) pruning is driven by the emergent (multimodal) distribution of the VLM parameters after pretraining. We benchmark eight state-of-the-art pruning algorithms in the context of TA-VLP, experimenting with two VLMs, three vision-language tasks, and three pruning ratios. Our experimental results show that MULTIFLOW outperforms recent sophisticated, combinatorial competitors in the vast majority of the cases, paving the way towards addressing TA-VLP. The code is publicly available at https://github.com/FarinaMatteo/multiflow.
Authors: Fengrui Tian, Yaoyao Liu, Adam Kortylewski, Yueqi Duan, Shaoyi Du, Alan Yuille, Angtian Wang
Abstract: 3D object pose estimation is a challenging task. Previous works always require thousands of object images with annotated poses for learning the 3D pose correspondence, which is laborious and time-consuming for labeling. In this paper, we propose to learn a category-level 3D object pose estimator without pose annotations. Instead of using manually annotated images, we leverage diffusion models (e.g., Zero-1-to-3) to generate a set of images under controlled pose differences and propose to learn our object pose estimator with those images. Directly using the original diffusion model leads to images with noisy poses and artifacts. To tackle this issue, firstly, we exploit an image encoder, which is learned from a specially designed contrastive pose learning, to filter the unreasonable details and extract image feature maps. Additionally, we propose a novel learning strategy that allows the model to learn object poses from those generated image sets without knowing the alignment of their canonical poses. Experimental results show that our method has the capability of category-level object pose estimation from a single shot setting (as pose definition), while significantly outperforming other state-of-the-art methods on the few-shot category-level object pose estimation benchmarks.
Authors: Maxence Bideaux, Alice Phe, Mohamed Chaouch, Bertrand Luvison, Quoc-Cuong Pham
Abstract: We introduce 3D-COCO, an extension of the original MS-COCO dataset providing 3D models and 2D-3D alignment annotations. 3D-COCO was designed to achieve computer vision tasks such as 3D reconstruction or image detection configurable with textual, 2D image, and 3D CAD model queries. We complete the existing MS-COCO dataset with 28K 3D models collected on ShapeNet and Objaverse. By using an IoU-based method, we match each MS-COCO annotation with the best 3D models to provide a 2D-3D alignment. The open-source nature of 3D-COCO is a premiere that should pave the way for new research on 3D-related topics. The dataset and its source codes is available at https://kalisteo.cea.fr/index.php/coco3d-object-detection-and-reconstruction/
URLs: https://kalisteo.cea.fr/index.php/coco3d-object-detection-and-reconstruction/
Authors: Sihao Lin, Pumeng Lyu, Dongrui Liu, Tao Tang, Xiaodan Liang, Andy Song, Xiaojun Chang
Abstract: Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and require same memory costs. This paper introduces a novel strategy that simplifies vision transformers and reduces computational load through the selective removal of non-essential attention layers, guided by entropy considerations. We identify that regarding the attention layer in bottom blocks, their subsequent MLP layers, i.e. two feed-forward layers, can elicit the same entropy quantity. Meanwhile, the accompanied MLPs are under-exploited since they exhibit smaller feature entropy compared to those MLPs in the top blocks. Therefore, we propose to integrate the uninformative attention layers into their subsequent counterparts by degenerating them into identical mapping, yielding only MLP in certain transformer blocks. Experimental results on ImageNet-1k show that the proposed method can remove 40% attention layer of DeiT-B, improving throughput and memory bound without performance compromise. Code is available at https://github.com/sihaoevery/lambda_vit.
Authors: Xiaoyan Cong, Yue Wu, Qifeng Chen, Chenyang Lei
Abstract: We propose a framework for automatic colorization that allows for iterative editing and modifications. The core of our framework lies in an imagination module: by understanding the content within a grayscale image, we utilize a pre-trained image generation model to generate multiple images that contain the same content. These images serve as references for coloring, mimicking the process of human experts. As the synthesized images can be imperfect or different from the original grayscale image, we propose a Reference Refinement Module to select the optimal reference composition. Unlike most previous end-to-end automatic colorization algorithms, our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples. Extensive experiments demonstrate the superiority of our framework over existing automatic colorization algorithms in editability and flexibility. Project page: https://xy-cong.github.io/imagine-colorization.
Authors: Xingyu Zheng, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai Wang, Zixiang Zhao, Jinyang Guo, Xianglong Liu
Abstract: With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. In this paper, we propose BinaryDM, a novel accurate quantization-aware training approach to push the weights of diffusion models towards the limit of 1-bit. Firstly, we present a Learnable Multi-basis Binarizer (LMB) to recover the representations generated by the binarized DM, which improves the information in details of representations crucial to the DM. Secondly, a Low-rank Representation Mimicking (LRM) is applied to enhance the binarization-aware optimization of the DM, alleviating the optimization direction ambiguity caused by fine-grained alignment. Moreover, a progressive initialization strategy is applied to training DMs to avoid convergence difficulties. Comprehensive experiments demonstrate that BinaryDM achieves significant accuracy and efficiency gains compared to SOTA quantization methods of DMs under ultra-low bit-widths. As the first binarization method for diffusion models, BinaryDM achieves impressive 16.0 times FLOPs and 27.1 times storage savings with 1-bit weight and 4-bit activation, showcasing its substantial advantages and potential for deploying DMs on resource-limited scenarios.
Authors: Sergey Kastryulin, Artem Konev, Alexander Shishenya, Eugene Lyapustin, Artem Khurshudov, Alexander Tselousov, Nikita Vinokurov, Denis Kuznedelev, Alexander Markovich, Grigoriy Livshits, Alexey Kirillov, Anastasiia Tabisheva, Liubov Chubarova, Marina Kaminskaia, Alexander Ustyuzhanin, Artemii Shvetsov, Daniil Shlenskii, Valerii Startsev, Dmitrii Kornilov, Mikhail Romanov, Artem Babenko, Sergei Ovcharenko, Valentin Khrulkov
Abstract: In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF). During the development of YaART, we especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before. In particular, we comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice. Furthermore, we demonstrate that models trained on smaller datasets of higher-quality images can successfully compete with those trained on larger datasets, establishing a more efficient scenario of diffusion models training. From the quality perspective, YaART is consistently preferred by users over many existing state-of-the-art models.
Authors: Jiannan Ge, Lingxi Xie, Hongtao Xie, Pandeng Li, Xiaopeng Zhang, Yongdong Zhang, Qi Tian
Abstract: A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accuracy of seen classes rather than unseen classes, while the latter is the true target to pursue. This issue becomes more significant in zero-shot image segmentation because the stronger (i.e., pixel-level) supervision brings a larger gap between seen and unseen classes. To mitigate it, we propose a novel architecture named AlignZeg, which embodies a comprehensive improvement of the segmentation pipeline, including proposal extraction, classification, and correction, to better fit the goal of zero-shot segmentation. (1) Mutually-Refined Proposal Extraction. AlignZeg harnesses a mutual interaction between mask queries and visual features, facilitating detailed class-agnostic mask proposal extraction. (2) Generalization-Enhanced Proposal Classification. AlignZeg introduces synthetic data and incorporates multiple background prototypes to allocate a more generalizable feature space. (3) Predictive Bias Correction. During the inference stage, AlignZeg uses a class indicator to find potential unseen class proposals followed by a prediction postprocess to correct the prediction bias. Experiments demonstrate that AlignZeg markedly enhances zero-shot semantic segmentation, as shown by an average 3.8% increase in hIoU, primarily attributed to a 7.1% improvement in identifying unseen classes, and we further validate that the improvement comes from alleviating the objective misalignment issue.
Authors: Giordano Cicchetti, Danilo Comminiello
Abstract: Real-world documents may suffer various forms of degradation, often resulting in lower accuracy in optical character recognition (OCR) systems. Therefore, a crucial preprocessing step is essential to eliminate noise while preserving text and key features of documents. In this paper, we propose NAF-DPM, a novel generative framework based on a diffusion probabilistic model (DPM) designed to restore the original quality of degraded documents. While DPMs are recognized for their high-quality generated images, they are also known for their large inference time. To mitigate this problem we provide the DPM with an efficient nonlinear activation-free (NAF) network and we employ as a sampler a fast solver of ordinary differential equations, which can converge in a few iterations. To better preserve text characters, we introduce an additional differentiable module based on convolutional recurrent neural networks, simulating the behavior of an OCR system during training. Experiments conducted on various datasets showcase the superiority of our approach, achieving state-of-the-art performance in terms of pixel-level and perceptual similarity metrics. Furthermore, the results demonstrate a notable character error reduction made by OCR systems when transcribing real-world document images enhanced by our framework. Code and pre-trained models are available at https://github.com/ispamm/NAF-DPM.
Authors: Xiaoyi Bao, Siyang Sun, Shuailei Ma, Kecheng Zheng, Yuxin Guo, Guosheng Zhao, Yun Zheng, Xingang Wang
Abstract: The reasoning segmentation task, which demands a nuanced comprehension of intricate queries to accurately pinpoint object regions, is attracting increasing attention. However, Multi-modal Large Language Models (MLLM) often find it difficult to accurately localize the objects described in complex reasoning contexts. We believe that the act of reasoning segmentation should mirror the cognitive stages of human visual search, where each step is a progressive refinement of thought toward the final object. Thus we introduce the Chains of Reasoning and Segmenting (CoReS) and find this top-down visual hierarchy indeed enhances the visual search process. Specifically, we propose a dual-chain structure that generates multi-modal, chain-like outputs to aid the segmentation process. Furthermore, to steer the MLLM's outputs into this intended hierarchy, we incorporate in-context inputs as guidance. Extensive experiments demonstrate the superior performance of our CoReS, which surpasses the state-of-the-art method by 7.1\% on the ReasonSeg dataset. The code will be released at https://github.com/baoxiaoyi/CoReS.
Authors: Kunpeng Song, Yizhe Zhu, Bingchen Liu, Qing Yan, Ahmed Elgammal, Xiao Yang
Abstract: In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly evolve, the demand for robust image-to-image translation grows. Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text prompt information to produce valuable image features, facilitating an image diffusion model. To better leverage the generated features, we further introduce a novel self-attention shortcut method that efficiently transfers image features to an image diffusion model, improving the resemblance of the target object in generated images. Remarkably, as a tuning-free plug-and-play module, our model requires only a single reference image and outperforms existing methods in generating images with high detail fidelity, enhanced identity-preservation and prompt faithfulness. Our work is open-source, thereby providing universal access to these advancements.
Authors: Olaf D\"unkel, Tim Salzmann, Florian Pfaff
Abstract: Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains underexplored. Probabilistic models of the human pose can benefit from approaches that rigorously consider the rotational nature of human joints. For this purpose, we introduce HuProSO3, a normalizing flow model that operates on a high-dimensional product space of SO(3) manifolds, modeling the joint distribution for human joints with three degrees of freedom. HuProSO3's advantage over state-of-the-art approaches is demonstrated through its superior modeling accuracy in three different applications and its capability to evaluate the exact likelihood. This work not only addresses the technical challenge of learning densities on SO(3) manifolds, but it also has broader implications for domains where the probabilistic regression of correlated 3D rotations is of importance.
Authors: Heyuan Li, Ce Chen, Tianhao Shi, Yuda Qiu, Sizhe An, Guanying Chen, Xiaoguang Han
Abstract: While recent advances in 3D-aware Generative Adversarial Networks (GANs) have aided the development of near-frontal view human face synthesis, the challenge of comprehensively synthesizing a full 3D head viewable from all angles still persists. Although PanoHead proves the possibilities of using a large-scale dataset with images of both frontal and back views for full-head synthesis, it often causes artifacts for back views. Based on our in-depth analysis, we found the reasons are mainly twofold. First, from network architecture perspective, we found each plane in the utilized tri-plane/tri-grid representation space tends to confuse the features from both sides, causing "mirroring" artifacts (e.g., the glasses appear in the back). Second, from data supervision aspect, we found that existing discriminator training in 3D GANs mainly focuses on the quality of the rendered image itself, and does not care much about its plausibility with the perspective from which it was rendered. This makes it possible to generate "face" in non-frontal views, due to its easiness to fool the discriminator. In response, we propose SphereHead, a novel tri-plane representation in the spherical coordinate system that fits the human head's geometric characteristics and efficiently mitigates many of the generated artifacts. We further introduce a view-image consistency loss for the discriminator to emphasize the correspondence of the camera parameters and the images. The combination of these efforts results in visually superior outcomes with significantly fewer artifacts. Our code and dataset are publicly available at https://lhyfst.github.io/spherehead.
Authors: Jooyeon Kim, Eulrang Cho, Sehyung Kim, Hyunwoo J. Kim
Abstract: Open-vocabulary object detection (OVD) has been studied with Vision-Language Models (VLMs) to detect novel objects beyond the pre-trained categories. Previous approaches improve the generalization ability to expand the knowledge of the detector, using 'positive' pseudo-labels with additional 'class' names, e.g., sock, iPod, and alligator. To extend the previous methods in two aspects, we propose Retrieval-Augmented Losses and visual Features (RALF). Our method retrieves related 'negative' classes and augments loss functions. Also, visual features are augmented with 'verbalized concepts' of classes, e.g., worn on the feet, handheld music player, and sharp teeth. Specifically, RALF consists of two modules: Retrieval Augmented Losses (RAL) and Retrieval-Augmented visual Features (RAF). RAL constitutes two losses reflecting the semantic similarity with negative vocabularies. In addition, RAF augments visual features with the verbalized concepts from a large language model (LLM). Our experiments demonstrate the effectiveness of RALF on COCO and LVIS benchmark datasets. We achieve improvement up to 3.4 box AP$_{50}^{\text{N}}$ on novel categories of the COCO dataset and 3.6 mask AP$_{\text{r}}$ gains on the LVIS dataset. Code is available at https://github.com/mlvlab/RALF .
Authors: Ionut M. Motoi, Leonardo Saraceni, Daniele Nardi, Thomas A. Ciarfuglia
Abstract: Satellite imagery is crucial for tasks like environmental monitoring and urban planning. Typically, it relies on semantic segmentation or Land Use Land Cover (LULC) classification to categorize each pixel. Despite the advancements brought about by Deep Neural Networks (DNNs), their performance in segmentation tasks is hindered by challenges such as limited availability of labeled data, class imbalance and the inherent variability and complexity of satellite images. In order to mitigate those issues, our study explores the effectiveness of a Cut-and-Paste augmentation technique for semantic segmentation in satellite images. We adapt this augmentation, which usually requires labeled instances, to the case of semantic segmentation. By leveraging the connected components in the semantic segmentation labels, we extract instances that are then randomly pasted during training. Using the DynamicEarthNet dataset and a U-Net model for evaluation, we found that this augmentation significantly enhances the mIoU score on the test set from 37.9 to 44.1. This finding highlights the potential of the Cut-and-Paste augmentation to improve the generalization capabilities of semantic segmentation models in satellite imagery.
Authors: Xinya Chen, Hanlei Guo, Yanrui Bin, Shangzhan Zhang, Yuanbo Yang, Yue Wang, Yujun Shen, Yiyi Liao
Abstract: Collecting accurate camera poses of training images has been shown to well serve the learning of 3D-aware generative adversarial networks (GANs) yet can be quite expensive in practice. This work targets learning 3D-aware GANs from unposed images, for which we propose to perform on-the-fly pose estimation of training images with a learned template feature field (TeFF). Concretely, in addition to a generative radiance field as in previous approaches, we ask the generator to also learn a field from 2D semantic features while sharing the density from the radiance field. Such a framework allows us to acquire a canonical 3D feature template leveraging the dataset mean discovered by the generative model, and further efficiently estimate the pose parameters on real data. Experimental results on various challenging datasets demonstrate the superiority of our approach over state-of-the-art alternatives from both the qualitative and the quantitative perspectives.
Authors: Jing Gu, Yilin Wang, Nanxuan Zhao, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Xin Eric Wang
Abstract: Effective editing of personal content holds a pivotal role in enabling individuals to express their creativity, weaving captivating narratives within their visual stories, and elevate the overall quality and impact of their visual content. Therefore, in this work, we introduce SwapAnything, a novel framework that can swap any objects in an image with personalized concepts given by the reference, while keeping the context unchanged. Compared with existing methods for personalized subject swapping, SwapAnything has three unique advantages: (1) precise control of arbitrary objects and parts rather than the main subject, (2) more faithful preservation of context pixels, (3) better adaptation of the personalized concept to the image. First, we propose targeted variable swapping to apply region control over latent feature maps and swap masked variables for faithful context preservation and initial semantic concept swapping. Then, we introduce appearance adaptation, to seamlessly adapt the semantic concept into the original image in terms of target location, shape, style, and content during the image generation process. Extensive results on both human and automatic evaluation demonstrate significant improvements of our approach over baseline methods on personalized swapping. Furthermore, SwapAnything shows its precise and faithful swapping abilities across single object, multiple objects, partial object, and cross-domain swapping tasks. SwapAnything also achieves great performance on text-based swapping and tasks beyond swapping such as object insertion.
Authors: Keen You, Haotian Zhang, Eldon Schoop, Floris Weers, Amanda Swearngin, Jeffrey Nichols, Yinfei Yang, Zhe Gan
Abstract: Recent advancements in multimodal large language models (MLLMs) have been noteworthy, yet, these general-domain MLLMs often fall short in their ability to comprehend and interact effectively with user interface (UI) screens. In this paper, we present Ferret-UI, a new MLLM tailored for enhanced understanding of mobile UI screens, equipped with referring, grounding, and reasoning capabilities. Given that UI screens typically exhibit a more elongated aspect ratio and contain smaller objects of interest (e.g., icons, texts) than natural images, we incorporate "any resolution" on top of Ferret to magnify details and leverage enhanced visual features. Specifically, each screen is divided into 2 sub-images based on the original aspect ratio (i.e., horizontal division for portrait screens and vertical division for landscape screens). Both sub-images are encoded separately before being sent to LLMs. We meticulously gather training samples from an extensive range of elementary UI tasks, such as icon recognition, find text, and widget listing. These samples are formatted for instruction-following with region annotations to facilitate precise referring and grounding. To augment the model's reasoning ability, we further compile a dataset for advanced tasks, including detailed description, perception/interaction conversations, and function inference. After training on the curated datasets, Ferret-UI exhibits outstanding comprehension of UI screens and the capability to execute open-ended instructions. For model evaluation, we establish a comprehensive benchmark encompassing all the aforementioned tasks. Ferret-UI excels not only beyond most open-source UI MLLMs, but also surpasses GPT-4V on all the elementary UI tasks.
Authors: Bo He, Hengduo Li, Young Kyun Jang, Menglin Jia, Xuefei Cao, Ashish Shah, Abhinav Shrivastava, Ser-Nam Lim
Abstract: With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video information in a memory bank. This allows our model to reference historical video content for long-term analysis without exceeding LLMs' context length constraints or GPU memory limits. Our memory bank can be seamlessly integrated into current multimodal LLMs in an off-the-shelf manner. We conduct extensive experiments on various video understanding tasks, such as long-video understanding, video question answering, and video captioning, and our model can achieve state-of-the-art performances across multiple datasets. Code available at https://boheumd.github.io/MA-LMM/.
Authors: Alberto Hojel, Yutong Bai, Trevor Darrell, Amir Globerson, Amir Bar
Abstract: Visual Prompting is a technique for teaching models to perform a visual task via in-context examples, without any additional training. In this work, we analyze the activations of MAE-VQGAN, a recent Visual Prompting model, and find task vectors, activations that encode task-specific information. Equipped with this insight, we demonstrate that it is possible to identify the task vectors and use them to guide the network towards performing different tasks without providing any input-output examples. To find task vectors, we compute the average intermediate activations per task and use the REINFORCE algorithm to search for the subset of task vectors. The resulting task vectors guide the model towards performing a task better than the original model without the need for input-output examples.
Authors: Wenguan Wang, Yi Yang, Yunhe Pan
Abstract: Visual knowledge is a new form of knowledge representation that can encapsulate visual concepts and their relations in a succinct, comprehensive, and interpretable manner, with a deep root in cognitive psychology. As the knowledge about the visual world has been identified as an indispensable component of human cognition and intelligence, visual knowledge is poised to have a pivotal role in establishing machine intelligence. With the recent advance of Artificial Intelligence (AI) techniques, large AI models (or foundation models) have emerged as a potent tool capable of extracting versatile patterns from broad data as implicit knowledge, and abstracting them into an outrageous amount of numeric parameters. To pave the way for creating visual knowledge empowered AI machines in this coming wave, we present a timely review that investigates the origins and development of visual knowledge in the pre-big model era, and accentuates the opportunities and unique role of visual knowledge in the big model era.
Authors: Mo Kordzanganeh, Danial Keshvary, Nariman Arian
Abstract: Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced denoising diffusion policy optimisation (DDPO), which accounts for the iterative denoising nature of the generation by modelling it as a Markov chain with a final reward. As the reward is a single value that determines the model's performance on the entire image, the model has to navigate a very sparse reward landscape and so requires a large sample count. In this work, we extend the DDPO by presenting the Pixel-wise Policy Optimisation (PXPO) algorithm, which can take feedback for each pixel, providing a more nuanced reward to the model.
Authors: Kurran Singh, Tim Magoun, John J. Leonard
Abstract: Enabling robots to understand the world in terms of objects is a critical building block towards higher level autonomy. The success of foundation models in vision has created the ability to segment and identify nearly all objects in the world. However, utilizing such objects to localize the robot and build an open-set semantic map of the world remains an open research question. In this work, a system of identifying, localizing, and encoding objects is tightly coupled with probabilistic graphical models for performing open-set semantic simultaneous localization and mapping (SLAM). Results are presented demonstrating that the proposed lightweight object encoding can be used to perform more accurate object-based SLAM than existing open-set methods, closed-set methods, and geometric methods while incurring a lower computational overhead than existing open-set mapping methods.
Authors: Yang Zheng, Qingqing Zhao, Guandao Yang, Wang Yifan, Donglai Xiang, Florian Dubost, Dmitry Lagun, Thabo Beeler, Federico Tombari, Leonidas Guibas, Gordon Wetzstein
Abstract: Modeling and rendering photorealistic avatars is of crucial importance in many applications. Existing methods that build a 3D avatar from visual observations, however, struggle to reconstruct clothed humans. We introduce PhysAvatar, a novel framework that combines inverse rendering with inverse physics to automatically estimate the shape and appearance of a human from multi-view video data along with the physical parameters of the fabric of their clothes. For this purpose, we adopt a mesh-aligned 4D Gaussian technique for spatio-temporal mesh tracking as well as a physically based inverse renderer to estimate the intrinsic material properties. PhysAvatar integrates a physics simulator to estimate the physical parameters of the garments using gradient-based optimization in a principled manner. These novel capabilities enable PhysAvatar to create high-quality novel-view renderings of avatars dressed in loose-fitting clothes under motions and lighting conditions not seen in the training data. This marks a significant advancement towards modeling photorealistic digital humans using physically based inverse rendering with physics in the loop. Our project website is at: https://qingqing-zhao.github.io/PhysAvatar
Authors: Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu
Abstract: A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting previously acquired knowledge. In this work, we study the under-explored problem of Long-Tailed Online Continual Learning (LTOCL), which aims to learn new tasks from sequentially arriving class-imbalanced data streams. Each data is observed only once for training without knowing the task data distribution. We present DELTA, a decoupled learning approach designed to enhance learning representations and address the substantial imbalance in LTOCL. We enhance the learning process by adapting supervised contrastive learning to attract similar samples and repel dissimilar (out-of-class) samples. Further, by balancing gradients during training using an equalization loss, DELTA significantly enhances learning outcomes and successfully mitigates catastrophic forgetting. Through extensive evaluation, we demonstrate that DELTA improves the capacity for incremental learning, surpassing existing OCL methods. Our results suggest considerable promise for applying OCL in real-world applications.
Authors: Siyuan Tian, Hao Wang, Yiren Rong, Junhao Wang, Renjie Dai, Zhengxiao He
Abstract: Modern displays nowadays possess the capability to render video content with a high dynamic range (HDR) and an extensive color gamut (WCG).However, the majority of available resources are still in standard dynamic range(SDR). Therefore, we need to identify an effective methodology for this objective.The existing deep neural network (DNN) based SDR(Standard dynamic range) to HDR (High dynamic range) conversion methods outperform conventional methods, but they are either too large to implement or generate some terrible artifacts. We propose a neural network for SDRTV to HDRTV conversion, termed "FastHDRNet". This network includes two parts, Adaptive Universal Color Transformation and Local Enhancement.The architecture is designed as a lightweight network that utilizes global statistics and local information with super high efficiency. After the experiment, we find that our proposed method achieve state-of-the-art performance in both quantitative comparisons and visual quality with a lightweight structure and a enhanced infer speed.
Authors: Han Lei, Baoming Wang, Zuwei Shui, Peiyuan Yang, Penghao Liang
Abstract: In addition to environmental perception sensors such as cameras, radars, etc. in the automatic driving system, the external environment of the vehicle is perceived, in fact, there is also a perception sensor that has been silently dedicated in the system, that is, the positioning module. This paper explores the application of SLAM (Simultaneous Localization and Mapping) technology in the context of automatic lane change behavior prediction and environment perception for autonomous vehicles. It discusses the limitations of traditional positioning methods, introduces SLAM technology, and compares LIDAR SLAM with visual SLAM. Real-world examples from companies like Tesla, Waymo, and Mobileye showcase the integration of AI-driven technologies, sensor fusion, and SLAM in autonomous driving systems. The paper then delves into the specifics of SLAM algorithms, sensor technologies, and the importance of automatic lane changes in driving safety and efficiency. It highlights Tesla's recent update to its Autopilot system, which incorporates automatic lane change functionality using SLAM technology. The paper concludes by emphasizing the crucial role of SLAM in enabling accurate environment perception, positioning, and decision-making for autonomous vehicles, ultimately enhancing safety and driving experience.
Authors: Zhonghan Zhao, Ke Ma, Wenhao Chai, Xuan Wang, Kewei Chen, Dongxu Guo, Yanting Zhang, Hongwei Wang, Gaoang Wang
Abstract: With the power of large language models (LLMs), open-ended embodied agents can flexibly understand human instructions, generate interpretable guidance strategies, and output executable actions. Nowadays, Multi-modal Language Models~(MLMs) integrate multi-modal signals into LLMs, further bringing richer perception to entity agents and allowing embodied agents to perceive world-understanding tasks more delicately. However, existing works: 1) operate independently by agents, each containing multiple LLMs, from perception to action, resulting in gaps between complex tasks and execution; 2) train MLMs on static data, struggling with dynamics in open-ended scenarios; 3) input prior knowledge directly as prompts, suppressing application flexibility. We propose STEVE-2, a hierarchical knowledge distillation framework for open-ended embodied tasks, characterized by 1) a hierarchical system for multi-granular task division, 2) a mirrored distillation method for parallel simulation data, and 3) an extra expert model for bringing additional knowledge into parallel simulation. After distillation, embodied agents can complete complex, open-ended tasks without additional expert guidance, utilizing the performance and knowledge of a versatile MLM. Extensive evaluations on navigation and creation tasks highlight the superior performance of STEVE-2 in open-ended tasks, with $1.4 \times$ - $7.3 \times$ in performance.
Authors: Nagullas KS, Vivekanand. V, Narayana Darapaneni, Anwesh R P
Abstract: Introduction: Automated Lung X-Ray Abnormality Detection System is the application which distinguish the normal x-ray images from infected x-ray images and highlight area considered for prediction, with the recent pandemic a need to have a non-conventional method and faster detecting diseases, for which X ray serves the purpose. Obectives: As of current situation any viral disease that is infectious is potential pandemic, so there is need for cheap and early detection system. Methods: This research will help to eases the work of expert to do further analysis. Accuracy of three different preexisting models such as DenseNet, MobileNet and VGG16 were high but models over-fitted primarily due to black and white images. Results: This led to building up new method such as as V-BreathNet which gave more than 96% percent accuracy. Conclusion: Thus, it can be stated that not all state-of art CNN models can be used on B/W images. In conclusion not all state-of-art CNN models can be used on B/W images.
Authors: Gaurav Singh, Sanket Kalwar, Md Faizal Karim, Bipasha Sen, Nagamanikandan Govindan, Srinath Sridhar, K Madhava Krishna
Abstract: Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so.
Authors: Taminul Islam, Md. Alif Sheakh, Mst. Sazia Tahosin, Most. Hasna Hena, Shopnil Akash, Yousef A. Bin Jardan, Gezahign Fentahun Wondmie, Hiba-Allah Nafidi, Mohammed Bourhia
Abstract: Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F-1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model's predictions and understand the impact of each feature on the model's output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Authors: Yukun Yang, Naihao Wang, Haixin Yang, Ruirui Li
Abstract: Label noise is a common issue in real-world datasets that inevitably impacts the generalization of models. This study focuses on robust classification tasks where the label noise is instance-dependent. Estimating the transition matrix accurately in this task is challenging, and methods based on sample selection often exhibit confirmation bias to varying degrees. Sparse over-parameterized training (SOP) has been theoretically effective in estimating and recovering label noise, offering a novel solution for noise-label learning. However, this study empirically observes and verifies a technical flaw of SOP: the lack of coordination between model predictions and noise recovery leads to increased generalization error. To address this, we propose a method called Coordinated Sparse Recovery (CSR). CSR introduces a collaboration matrix and confidence weights to coordinate model predictions and noise recovery, reducing error leakage. Based on CSR, this study designs a joint sample selection strategy and constructs a comprehensive and powerful learning framework called CSR+. CSR+ significantly reduces confirmation bias, especially for datasets with more classes and a high proportion of instance-specific noise. Experimental results on simulated and real-world noisy datasets demonstrate that both CSR and CSR+ achieve outstanding performance compared to methods at the same level.
Authors: Shezheng Song, Shasha Li, Shan Zhao, Xiaopeng Li, Chengyu Wang, Jie Yu, Jun Ma, Tianwei Yan, Bin Ji, Xiaoguang Mao
Abstract: Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as input may contain redundant information. (2)the insufficient utilization of entity-related information, such as attributes in images. (3)semantic inconsistency between the entity in knowledge base and its representation. To this end, we propose DWE+ for multimodal entity linking. DWE+ could capture finer semantics and dynamically maintain semantic consistency with entities. This is achieved by three aspects: (a)we introduce a method for extracting fine-grained image features by partitioning the image into multiple local objects. Then, hierarchical contrastive learning is used to further align semantics between coarse-grained information(text and image) and fine-grained (mention and visual objects). (b)we explore ways to extract visual attributes from images to enhance fusion feature such as facial features and identity. (c)we leverage Wikipedia and ChatGPT to capture the entity representation, achieving semantic enrichment from both static and dynamic perspectives, which better reflects the real-world entity semantics. Experiments on Wikimel, Richpedia, and Wikidiverse datasets demonstrate the effectiveness of DWE+ in improving MEL performance. Specifically, we optimize these datasets and achieve state-of-the-art performance on the enhanced datasets. The code and enhanced datasets are released on https://github.com/season1blue/DWET
Authors: Xingtong Ge, Jixiang Luo, Xinjie Zhang, Tongda Xu, Guo Lu, Dailan He, Jing Geng, Yan Wang, Jun Zhang, Hongwei Qin
Abstract: Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder controller, enabling the adaptation of a single codec to different tasks through mechanisms like mode prediction. Drawing inspiration from this, we introduce an innovative encoder controller for deep video compression for machines. This controller features a mode prediction and a Group of Pictures (GoP) selection module. Our approach centralizes control at the encoding stage, allowing for adaptable encoder adjustments across different tasks, such as detection and tracking, while maintaining compatibility with a standard pre-trained DVC decoder. Empirical evidence demonstrates that our method is applicable across multiple tasks with various existing pre-trained DVCs. Moreover, extensive experiments demonstrate that our method outperforms previous DVC by about 25% bitrate for different tasks, with only one pre-trained decoder.
Authors: Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu
Abstract: Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the probably approximately correct (PAC) learning theory of OOD detection that fits the commonly used evaluation metrics in the literature. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we offer theoretical support for representative OOD detection works based on our OOD theory.
Authors: Yu-Hsi Chen
Abstract: In the realm of continual learning, the presence of noisy labels within data streams represents a notable obstacle to model reliability and fairness. We focus on the data stream scenario outlined in pertinent literature, characterized by fuzzy task boundaries and noisy labels. To address this challenge, we introduce a novel and intuitive sampling method called Noisy Test Debiasing (NTD) to mitigate noisy labels in evolving data streams and establish a fair and robust continual learning algorithm. NTD is straightforward to implement, making it feasible across various scenarios. Our experiments benchmark four datasets, including two synthetic noise datasets (CIFAR10 and CIFAR100) and real-world noise datasets (mini-WebVision and Food-101N). The results validate the efficacy of NTD for online continual learning in scenarios with noisy labels in data streams. Compared to the previous leading approach, NTD achieves a training speedup enhancement over two times while maintaining or surpassing accuracy levels. Moreover, NTD utilizes less than one-fifth of the GPU memory resources compared to previous leading methods.
Authors: Wei Fang, Yuxing Tang, Heng Guo, Mingze Yuan, Tony C. W. Mok, Ke Yan, Jiawen Yao, Xin Chen, Zaiyi Liu, Le Lu, Ling Zhang, Minfeng Xu
Abstract: In the realm of medical 3D data, such as CT and MRI images, prevalent anisotropic resolution is characterized by high intra-slice but diminished inter-slice resolution. The lowered resolution between adjacent slices poses challenges, hindering optimal viewing experiences and impeding the development of robust downstream analysis algorithms. Various volumetric super-resolution algorithms aim to surmount these challenges, enhancing inter-slice resolution and overall 3D medical imaging quality. However, existing approaches confront inherent challenges: 1) often tailored to specific upsampling factors, lacking flexibility for diverse clinical scenarios; 2) newly generated slices frequently suffer from over-smoothing, degrading fine details, and leading to inter-slice inconsistency. In response, this study presents CycleINR, a novel enhanced Implicit Neural Representation model for 3D medical data volumetric super-resolution. Leveraging the continuity of the learned implicit function, the CycleINR model can achieve results with arbitrary up-sampling rates, eliminating the need for separate training. Additionally, we enhance the grid sampling in CycleINR with a local attention mechanism and mitigate over-smoothing by integrating cycle-consistent loss. We introduce a new metric, Slice-wise Noise Level Inconsistency (SNLI), to quantitatively assess inter-slice noise level inconsistency. The effectiveness of our approach is demonstrated through image quality evaluations on an in-house dataset and a downstream task analysis on the Medical Segmentation Decathlon liver tumor dataset.
Authors: Yiyang Ma, Wenhan Yang, Jiaying Liu
Abstract: The images produced by diffusion models can attain excellent perceptual quality. However, it is challenging for diffusion models to guarantee distortion, hence the integration of diffusion models and image compression models still needs more comprehensive explorations. This paper presents a diffusion-based image compression method that employs a privileged end-to-end decoder model as correction, which achieves better perceptual quality while guaranteeing the distortion to an extent. We build a diffusion model and design a novel paradigm that combines the diffusion model and an end-to-end decoder, and the latter is responsible for transmitting the privileged information extracted at the encoder side. Specifically, we theoretically analyze the reconstruction process of the diffusion models at the encoder side with the original images being visible. Based on the analysis, we introduce an end-to-end convolutional decoder to provide a better approximation of the score function $\nabla_{\mathbf{x}_t}\log p(\mathbf{x}_t)$ at the encoder side and effectively transmit the combination. Experiments demonstrate the superiority of our method in both distortion and perception compared with previous perceptual compression methods.
Authors: Aur\'elie Beaufr\`ere, Nora Ouzir, Paul Emile Zafar, Astrid Laurent-Bellue, Miguel Albuquerque, Gwladys Lubuela, Jules Gr\'egory, Catherine Guettier, K\'evin Mondet, Jean-Christophe Pesquet, Val\'erie Paradis
Abstract: The diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method. Weak tumour/non-tumour annotations served as labels for training a Resnet18 neural network, and the network's last convolutional layer was used to extract new tumour tile features. Without knowledge of the precise labels of the malignancies, we then applied an unsupervised clustering algorithm. Our model identified specific features of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (iCCA). Despite no specific features of cHCC-CCA being recognized, the identification of HCC and iCCA tiles within a slide could facilitate the diagnosis of primary liver cancers, particularly cHCC-CCA. Method and results: 166 PLC biopsies were divided into training, internal and external validation sets: 90, 29 and 47 samples. Two liver pathologists reviewed each whole-slide hematein eosin saffron (HES)-stained image (WSI). After annotating the tumour/non-tumour areas, 256x256 pixel tiles were extracted from the WSIs and used to train a ResNet18. The network was used to extract new tile features. An unsupervised clustering algorithm was then applied to the new tile features. In a two-cluster model, Clusters 0 and 1 contained mainly HCC and iCCA histological features. The diagnostic agreement between the pathological diagnosis and the model predictions in the internal and external validation sets was 100% (11/11) and 96% (25/26) for HCC and 78% (7/9) and 87% (13/15) for iCCA, respectively. For cHCC-CCA, we observed a highly variable proportion of tiles from each cluster (Cluster 0: 5-97%; Cluster 1: 2-94%).
Authors: Yousef Sadegheih, Afshin Bozorgpour, Pratibha Kumari, Reza Azad, Dorit Merhof
Abstract: As a result of the rise of Transformer architectures in medical image analysis, specifically in the domain of medical image segmentation, a multitude of hybrid models have been created that merge the advantages of Convolutional Neural Networks (CNNs) and Transformers. These hybrid models have achieved notable success by significantly improving segmentation accuracy. Yet, this progress often comes at the cost of increased model complexity, both in terms of parameters and computational demand. Moreover, many of these models fail to consider the crucial interplay between spatial and channel features, which could further refine and improve segmentation outcomes. To address this, we introduce LHU-Net, a Light Hybrid U-Net architecture optimized for volumetric medical image segmentation. LHU-Net is meticulously designed to prioritize spatial feature analysis in its initial layers before shifting focus to channel-based features in its deeper layers, ensuring a comprehensive feature extraction process. Rigorous evaluation across five benchmark datasets - Synapse, LA, Pancreas, ACDC, and BRaTS 2018 - underscores LHU-Net's superior performance, showcasing its dual capacity for efficiency and accuracy. Notably, LHU-Net sets new performance benchmarks, such as attaining a Dice score of 92.66 on the ACDC dataset, while simultaneously reducing parameters by 85% and quartering the computational load compared to existing state-of-the-art models. Achieved without any reliance on pre-training, additional data, or model ensemble, LHU-Net's effectiveness is further evidenced by its state-of-the-art performance across all evaluated datasets, utilizing fewer than 11 million parameters. This achievement highlights that balancing computational efficiency with high accuracy in medical image segmentation is feasible. Our implementation of LHU-Net is freely accessible to the research community on GitHub.
Authors: HyoJe Jung, Yunha Kim, Heejung Choi, Hyeram Seo, Minkyoung Kim, JiYe Han, Gaeun Kee, Seohyun Park, Soyoung Ko, Byeolhee Kim, Suyeon Kim, Tae Joon Jun, Young-Hak Kim
Abstract: Medical documentation, including discharge notes, is crucial for ensuring patient care quality, continuity, and effective medical communication. However, the manual creation of these documents is not only time-consuming but also prone to inconsistencies and potential errors. The automation of this documentation process using artificial intelligence (AI) represents a promising area of innovation in healthcare. This study directly addresses the inefficiencies and inaccuracies in creating discharge notes manually, particularly for cardiac patients, by employing AI techniques, specifically large language model (LLM). Utilizing a substantial dataset from a cardiology center, encompassing wide-ranging medical records and physician assessments, our research evaluates the capability of LLM to enhance the documentation process. Among the various models assessed, Mistral-7B distinguished itself by accurately generating discharge notes that significantly improve both documentation efficiency and the continuity of care for patients. These notes underwent rigorous qualitative evaluation by medical expert, receiving high marks for their clinical relevance, completeness, readability, and contribution to informed decision-making and care planning. Coupled with quantitative analyses, these results confirm Mistral-7B's efficacy in distilling complex medical information into concise, coherent summaries. Overall, our findings illuminate the considerable promise of specialized LLM, such as Mistral-7B, in refining healthcare documentation workflows and advancing patient care. This study lays the groundwork for further integrating advanced AI technologies in healthcare, demonstrating their potential to revolutionize patient documentation and support better care outcomes.
Authors: Yihe Fan, Yuxin Cao, Ziyu Zhao, Ziyao Liu, Shaofeng Li
Abstract: Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities that increasingly influence various aspects of our daily lives, constantly defining the new boundary of Artificial General Intelligence (AGI). Image modalities, enriched with profound semantic information and a more continuous mathematical nature compared to other modalities, greatly enhance the functionalities of MLLMs when integrated. However, this integration serves as a double-edged sword, providing attackers with expansive vulnerabilities to exploit for highly covert and harmful attacks. The pursuit of reliable AI systems like powerful MLLMs has emerged as a pivotal area of contemporary research. In this paper, we endeavor to demostrate the multifaceted risks associated with the incorporation of image modalities into MLLMs. Initially, we delineate the foundational components and training processes of MLLMs. Subsequently, we construct a threat model, outlining the security vulnerabilities intrinsic to MLLMs. Moreover, we analyze and summarize existing scholarly discourses on MLLMs' attack and defense mechanisms, culminating in suggestions for the future research on MLLM security. Through this comprehensive analysis, we aim to deepen the academic understanding of MLLM security challenges and propel forward the development of trustworthy MLLM systems.
Authors: Shoffan Saifullah, Andri Pranolo, Rafa{\l} Dre\.zewski
Abstract: This study systematically investigates the impact of image enhancement techniques on Convolutional Neural Network (CNN)-based Brain Tumor Segmentation, focusing on Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and their hybrid variations. Employing the U-Net architecture on a dataset of 3064 Brain MRI images, the research delves into preprocessing steps, including resizing and enhancement, to optimize segmentation accuracy. A detailed analysis of the CNN-based U-Net architecture, training, and validation processes is provided. The comparative analysis, utilizing metrics such as Accuracy, Loss, MSE, IoU, and DSC, reveals that the hybrid approach CLAHE-HE consistently outperforms others. Results highlight its superior accuracy (0.9982, 0.9939, 0.9936 for training, testing, and validation, respectively) and robust segmentation overlap, with Jaccard values of 0.9862, 0.9847, and 0.9864, and Dice values of 0.993, 0.9923, and 0.9932 for the same phases, emphasizing its potential in neuro-oncological applications. The study concludes with a call for refinement in segmentation methodologies to further enhance diagnostic precision and treatment planning in neuro-oncology.
Authors: Marc S. Seibel, Hristina Uzunova, Timo Kepp, Heinz Handels
Abstract: For a unified analysis of medical images from different modalities, data harmonization using image-to-image (I2I) translation is desired. We study this problem employing an optical coherence tomography (OCT) data set of Spectralis-OCT and Home-OCT images. I2I translation is challenging because the images are unpaired, and a bijective mapping does not exist due to the information discrepancy between both domains. This problem has been addressed by the Contrastive Learning for Unpaired I2I Translation (CUT) approach, but it reduces semantic consistency. To restore the semantic consistency, we support the style decoder using an additional segmentation decoder. Our approach increases the similarity between the style-translated images and the target distribution. Importantly, we improve the segmentation of biomarkers in Home-OCT images in an unsupervised domain adaptation scenario. Our data harmonization approach provides potential for the monitoring of diseases, e.g., age related macular disease, using different OCT devices.
Authors: Hugo Caselles-Dupr\'e, Charles Mellerio, Paul H\'erent, Aliz\'ee Lopez-Persem, Benoit B\'eranger, Mathieu Soularue, Pierre Fautrel, Gauthier Vernier, Matthieu Cord
Abstract: The reconstruction of images observed by subjects from fMRI data collected during visual stimuli has made significant strides in the past decade, thanks to the availability of extensive fMRI datasets and advancements in generative models for image generation. However, the application of visual reconstruction has remained limited. Reconstructing visual imagination presents a greater challenge, with potentially revolutionary applications ranging from aiding individuals with disabilities to verifying witness accounts in court. The primary hurdles in this field are the absence of data collection protocols for visual imagery and the lack of datasets on the subject. Traditionally, fMRI-to-image relies on data collected from subjects exposed to visual stimuli, which poses issues for generating visual imagery based on the difference of brain activity between visual stimulation and visual imagery. For the first time, we have compiled a substantial dataset (around 6h of scans) on visual imagery along with a proposed data collection protocol. We then train a modified version of an fMRI-to-image model and demonstrate the feasibility of reconstructing images from two modes of imagination: from memory and from pure imagination. This marks an important step towards creating a technology that allow direct reconstruction of visual imagery.
Authors: Woo Kyoung Han, Sunghoon Im, Jaedeok Kim, Kyong Hwan Jin
Abstract: We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a high compression rate, inevitably resulting in quality degradation while encoding an image. We have designed a continuous cosine spectrum estimator to address the quality degradation issue that restores the distorted spectrum. By leveraging local DCT formulations, our network has the privilege to exploit dequantization and upsampling simultaneously. Our proposed model enables decoding compressed images directly across different quality factors using a single pre-trained model without relying on a conventional JPEG decoder. As a result, our proposed network achieves state-of-the-art performance in flexible color image JPEG artifact removal tasks. Our source code is available at https://github.com/WooKyoungHan/JDEC.
Authors: Artem Vysogorets, Kartik Ahuja, Julia Kempe
Abstract: In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning. Data pruning offers a solution by removing redundant or uninformative samples from the dataset, which yields faster convergence and improved neural scaling laws. However, little is known about its impact on classification bias of the trained models. We conduct the first systematic study of this effect and reveal that existing data pruning algorithms can produce highly biased classifiers. At the same time, we argue that random data pruning with appropriate class ratios has potential to improve the worst-class performance. We propose a "fairness-aware" approach to pruning and empirically demonstrate its performance on standard computer vision benchmarks. In sharp contrast to existing algorithms, our proposed method continues improving robustness at a tolerable drop of average performance as we prune more from the datasets. We present theoretical analysis of the classification risk in a mixture of Gaussians to further motivate our algorithm and support our findings.
Authors: Xiefan Guo, Hongyu Yang, Di Huang
Abstract: Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors. Due to the lack of proper interaction with image texture during structure reconstruction, however, current solutions are incompetent in handling the cases with large corruptions, and they generally suffer from distorted results. In this paper, we propose a novel two-stream network for image inpainting, which models the structure-constrained texture synthesis and texture-guided structure reconstruction in a coupled manner so that they better leverage each other for more plausible generation. Furthermore, to enhance the global consistency, a Bi-directional Gated Feature Fusion (Bi-GFF) module is designed to exchange and combine the structure and texture information and a Contextual Feature Aggregation (CFA) module is developed to refine the generated contents by region affinity learning and multi-scale feature aggregation. Qualitative and quantitative experiments on the CelebA, Paris StreetView and Places2 datasets demonstrate the superiority of the proposed method. Our code is available at https://github.com/Xiefan-Guo/CTSDG.
Authors: Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan
Abstract: Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases after the initial one. However, we find that improving CIL at its initial phase is also a promising direction. Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance. Motivated by this, we study the difference between a na\"ively-trained initial-phase model and the oracle model. Specifically, since one major difference between these two models is the number of training classes, we investigate how such difference affects the model representations. We find that, with fewer training classes, the data representations of each class lie in a long and narrow region; with more training classes, the representations of each class scatter more uniformly. Inspired by this observation, we propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly, thus mimicking the model jointly trained with all classes (i.e., the oracle model). Our CwD is simple to implement and easy to plug into existing methods. Extensive experiments on various benchmark datasets show that CwD consistently and significantly improves the performance of existing state-of-the-art methods by around 1\% to 3\%. Code will be released.
Authors: Sihao Lin, Hongwei Xie, Bing Wang, Kaicheng Yu, Xiaojun Chang, Xiaodan Liang, Gang Wang
Abstract: Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial matching fashion. However, people tend to overlook the fact that, due to the architecture differences, the semantic information on the same spatial location usually vary. This greatly undermines the underlying assumption of the one-to-one distillation approach. To this end, we propose a novel one-to-all spatial matching knowledge distillation approach. Specifically, we allow each pixel of the teacher feature to be distilled to all spatial locations of the student features given its similarity, which is generated from a target-aware transformer. Our approach surpasses the state-of-the-art methods by a significant margin on various computer vision benchmarks, such as ImageNet, Pascal VOC and COCOStuff10k. Code is available at https://github.com/sihaoevery/TaT.
Authors: Jiahang Zhang, Lilang Lin, Zejia Fan, Wenjing Wang, Jiaying Liu
Abstract: Deep learning has become a powerful tool for Mars exploration. Mars terrain semantic segmentation is an important Martian vision task, which is the base of rover autonomous planning and safe driving. However, there is a lack of sufficient detailed and high-confidence data annotations, which are exactly required by most deep learning methods to obtain a good model. To address this problem, we propose our solution from the perspective of joint data and method design. We first present a newdataset S5Mars for Semi-SuperviSed learning on Mars Semantic Segmentation, which contains 6K high-resolution images and is sparsely annotated based on confidence, ensuring the high quality of labels. Then to learn from this sparse data, we propose a semi-supervised learning (SSL) framework for Mars image semantic segmentation, to learn representations from limited labeled data. Different from the existing SSL methods which are mostly targeted at the Earth image data, our method takes into account Mars data characteristics. Specifically, we first investigate the impact of current widely used natural image augmentations on Mars images. Based on the analysis, we then proposed two novel and effective augmentations for SSL of Mars segmentation, AugIN and SAM-Mix, which serve as strong augmentations to boost the model performance. Meanwhile, to fully leverage the unlabeled data, we introduce a soft-to-hard consistency learning strategy, learning from different targets based on prediction confidence. Experimental results show that our method can outperform state-of-the-art SSL approaches remarkably. Our proposed dataset is available at https://jhang2020.github.io/S5Mars.github.io/.
Authors: Esteve Valls Mascaro, Hyemin Ahn, Dongheui Lee
Abstract: To anticipate how a human would act in the future, it is essential to understand the human intention since it guides the human towards a certain goal. In this paper, we propose a hierarchical architecture which assumes a sequence of human action (low-level) can be driven from the human intention (high-level). Based on this, we deal with Long-Term Action Anticipation task in egocentric videos. Our framework first extracts two level of human information over the N observed videos human actions through a Hierarchical Multi-task MLP Mixer (H3M). Then, we condition the uncertainty of the future through an Intention-Conditioned Variational Auto-Encoder (I-CVAE) that generates K stable predictions of the next Z=20 actions that the observed human might perform. By leveraging human intention as high-level information, we claim that our model is able to anticipate more time-consistent actions in the long-term, thus improving the results over baseline methods in EGO4D Challenge. This work ranked first in both CVPR@2022 and ECVV@2022 EGO4D LTA Challenge by providing more plausible anticipated sequences, improving the anticipation of nouns and overall actions. Webpage: https://evm7.github.io/icvae-page/
Authors: Guangkai Xu, Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Simon Chen, Jia-Wang Bian
Abstract: Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by various range sensors, including those in modern mobile phones, or by multi-view reconstruction algorithms. Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model. We propose an effective training scheme where we simulate various sparsity patterns in typical task domains. In addition, we design two new benchmarks to evaluate the generalizability and the robustness of depth completion methods. Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods, introducing a practical solution to high-quality depth capture on a mobile device. The code is available at: https://github.com/YvanYin/FillDepth.
Authors: Baoliang Chen, Hanwei Zhu, Lingyu Zhu, Shiqi Wang, Sam Kwong
Abstract: The statistical regularities of natural images, referred to as natural scene statistics, play an important role in no-reference image quality assessment. However, it has been widely acknowledged that screen content images (SCIs), which are typically computer generated, do not hold such statistics. Here we make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined. The underlying mechanism of the proposed approach is based upon the mild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion. We empirically show that the statistics deviation could be effectively leveraged in quality assessment, and the proposed method is superior when evaluated in different settings. Extensive experimental results demonstrate the Deep Feature Statistics based SCI Quality Assessment (DFSS-IQA) model delivers promising performance compared with existing NR-IQA models and shows a high generalization capability in the cross-dataset settings. The implementation of our method is publicly available at https://github.com/Baoliang93/DFSS-IQA.
Authors: Pu Yang, Bin Dong
Abstract: Magnetic Resonance Imaging (MRI) is a widely used medical imaging technique, but its long acquisition time can be a limiting factor in clinical settings. To address this issue, researchers have been exploring ways to reduce the acquisition time while maintaining the reconstruction quality. Previous works have focused on finding either sparse samplers with a fixed reconstructor or finding reconstructors with a fixed sampler. However, these approaches do not fully utilize the potential of joint learning of samplers and reconstructors. In this paper, we propose an alternating training framework for jointly learning a good pair of samplers and reconstructors via deep reinforcement learning (RL). In particular, we consider the process of MRI sampling as a sampling trajectory controlled by a sampler, and introduce a novel sparse-reward Partially Observed Markov Decision Process (POMDP) to formulate the MRI sampling trajectory. Compared to the dense-reward POMDP used in existing works, the proposed sparse-reward POMDP is more computationally efficient and has a provable advantage. Moreover, the proposed framework, called L2SR (Learning to Sample and Reconstruct), overcomes the training mismatch problem that arises in previous methods that use dense-reward POMDP. By alternately updating samplers and reconstructors, L2SR learns a pair of samplers and reconstructors that achieve state-of-the-art reconstruction performances on the fastMRI dataset. Codes are available at \url{https://github.com/yangpuPKU/L2SR-Learning-to-Sample-and-Reconstruct}.
URLs: https://github.com/yangpuPKU/L2SR-Learning-to-Sample-and-Reconstruct
Authors: Mingqi Jiang, Saeed Khorram, Li Fuxin
Abstract: In order to gain insights about the decision-making of different visual recognition backbones, we propose two methodologies, sub-explanation counting and cross-testing, that systematically applies deep explanation algorithms on a dataset-wide basis, and compares the statistics generated from the amount and nature of the explanations. These methodologies reveal the difference among networks in terms of two properties called compositionality and disjunctivism. Transformers and ConvNeXt are found to be more compositional, in the sense that they jointly consider multiple parts of the image in building their decisions, whereas traditional CNNs and distilled transformers are less compositional and more disjunctive, which means that they use multiple diverse but smaller set of parts to achieve a confident prediction. Through further experiments, we pinpointed the choice of normalization to be especially important in the compositionality of a model, in that batch normalization leads to less compositionality while group and layer normalization lead to more. Finally, we also analyze the features shared by different backbones and plot a landscape of different models based on their feature-use similarity.
Authors: Xiaolong Shen, Zhedong Zheng, Yi Yang
Abstract: The goal of sign language recognition (SLR) is to help those who are hard of hearing or deaf overcome the communication barrier. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. Skeleton-based methods do not consider facial expressions, while RGB-based approaches usually ignore the fine-grained hand structure. To overcome both limitations, we propose a new framework called Spatial-temporal Part-aware network~(StepNet), based on RGB parts. As its name suggests, it is made up of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Part-level Spatial Modeling, in particular, automatically captures the appearance-based properties, such as hands and faces, in the feature space without the use of any keypoint-level annotations. On the other hand, Part-level Temporal Modeling implicitly mines the long-short term context to capture the relevant attributes over time. Extensive experiments demonstrate that our StepNet, thanks to spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three commonly-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Additionally, the proposed method is compatible with the optical flow input and can produce superior performance if fused. For those who are hard of hearing, we hope that our work can act as a preliminary step.
Authors: Shuren Qi, Yushu Zhang, Chao Wang, Tao Xiang, Xiaochun Cao, Yong Xiang
Abstract: A long-standing topic in artificial intelligence is the effective recognition of patterns from noisy images. In this regard, the recent data-driven paradigm considers 1) improving the representation robustness by adding noisy samples in training phase (i.e., data augmentation) or 2) pre-processing the noisy image by learning to solve the inverse problem (i.e., image denoising). However, such methods generally exhibit inefficient process and unstable result, limiting their practical applications. In this paper, we explore a non-learning paradigm that aims to derive robust representation directly from noisy images, without the denoising as pre-processing. Here, the noise-robust representation is designed as Fractional-order Moments in Radon space (FMR), with also beneficial properties of orthogonality and rotation invariance. Unlike earlier integer-order methods, our work is a more generic design taking such classical methods as special cases, and the introduced fractional-order parameter offers time-frequency analysis capability that is not available in classical methods. Formally, both implicit and explicit paths for constructing the FMR are discussed in detail. Extensive simulation experiments and an image security application are provided to demonstrate the uniqueness and usefulness of our FMR, especially for noise robustness, rotation invariance, and time-frequency discriminability.
Authors: Daniel Gritzner, J\"orn Ostermann
Abstract: Aerial image segmentation is the basis for applications such as automatically creating maps or tracking deforestation. In true orthophotos, which are often used in these applications, many objects and regions can be approximated well by polygons. However, this fact is rarely exploited by state-of-the-art semantic segmentation models. Instead, most models allow unnecessary degrees of freedom in their predictions by allowing arbitrary region shapes. We therefore present a refinement of our deep learning model which predicts binary space partitioning trees, an efficient polygon representation. The refinements include a new feature decoder architecture and a new differentiable BSP tree renderer which both avoid vanishing gradients. Additionally, we designed a novel loss function specifically designed to improve the spatial partitioning defined by the predicted trees. Furthermore, our expanded model can predict multiple trees at once and thus can predict class-specific segmentations. As an additional contribution, we investigate the impact of a non-optimal training process in comparison to an optimized training process. While model architectures optimized for aerial images, such as PFNet or our own model, show an advantage under non-optimal conditions, this advantage disappears under optimal training conditions. Despite this observation, our model still makes better predictions for small rectangular objects, e.g., cars.
Authors: Esteve Valls Mascaro, Shuo Ma, Hyemin Ahn, Dongheui Lee
Abstract: Comprehending human motion is a fundamental challenge for developing Human-Robot Collaborative applications. Computer vision researchers have addressed this field by only focusing on reducing error in predictions, but not taking into account the requirements to facilitate its implementation in robots. In this paper, we propose a new model based on Transformer that simultaneously deals with the real time 3D human motion forecasting in the short and long term. Our 2-Channel Transformer (2CH-TR) is able to efficiently exploit the spatio-temporal information of a shortly observed sequence (400ms) and generates a competitive accuracy against the current state-of-the-art. 2CH-TR stands out for the efficient performance of the Transformer, being lighter and faster than its competitors. In addition, our model is tested in conditions where the human motion is severely occluded, demonstrating its robustness in reconstructing and predicting 3D human motion in a highly noisy environment. Our experiment results show that the proposed 2CH-TR outperforms the ST-Transformer, which is another state-of-the-art model based on the Transformer, in terms of reconstruction and prediction under the same conditions of input prefix. Our model reduces in 8.89% the mean squared error of ST-Transformer in short-term prediction, and 2.57% in long-term prediction in Human3.6M dataset with 400ms input prefix. Webpage: https://evm7.github.io/2CHTR-page/
Authors: Ying Zeng, Yushi Chen, Xue Yang, Qingyun Li, Junchi Yan
Abstract: Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model. We argue that AP$_{50}$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation. Therefore, we advocate using high-precision metric, e.g. AP$_{75}$, to measure the performance of models. In this paper, we propose an Aspect Ratio Sensitive Oriented Object Detector with Transformer, termed ARS-DETR, which exhibits a competitive performance in high-precision oriented object detection. Specifically, a new angle classification method, calling Aspect Ratio aware Circle Smooth Label (AR-CSL), is proposed to smooth the angle label in a more reasonable way and discard the hyperparameter that introduced by previous work (e.g. CSL). Then, a rotated deformable attention module is designed to rotate the sampling points with the corresponding angles and eliminate the misalignment between region features and sampling points. Moreover, a dynamic weight coefficient according to the aspect ratio is adopted to calculate the angle loss. Comprehensive experiments on several challenging datasets show that our method achieves competitive performance on the high-precision oriented object detection task.
Authors: Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, Limin Wang
Abstract: In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an ``early-fusion'' or ``late-fusion'' manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarity. To address the problem, we propose a novel end-to-end framework, which consists of 2D and 3D branches with multiple bidirectional fusion connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to extract the LiDAR features, as it preserves the geometric structure of point clouds. To fuse dense image features and sparse point features, we propose a learnable operator named bidirectional camera-LiDAR fusion module (Bi-CLFM). We instantiate two types of the bidirectional fusion pipeline, one based on the pyramidal coarse-to-fine architecture (dubbed CamLiPWC), and the other one based on the recurrent all-pairs field transforms (dubbed CamLiRAFT). On FlyingThings3D, both CamLiPWC and CamLiRAFT surpass all existing methods and achieve up to a 47.9\% reduction in 3D end-point-error from the best published result. Our best-performing model, CamLiRAFT, achieves an error of 4.26\% on the KITTI Scene Flow benchmark, ranking 1st among all submissions with much fewer parameters. Besides, our methods have strong generalization performance and the ability to handle non-rigid motion. Code is available at https://github.com/MCG-NJU/CamLiFlow.
Authors: Mehmet Ayg\"un, Oisin Mac Aodha
Abstract: We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or tailored 3D skeletons, SAOR learns to articulate shapes from single-view image collections with a skeleton-free part-based model without requiring any 3D object shape priors. To prevent ill-posed solutions, we propose a cross-instance consistency loss that exploits disentangled object shape deformation and articulation. This is helped by a new silhouette-based sampling mechanism to enhance viewpoint diversity during training. Our method only requires estimated object silhouettes and relative depth maps from off-the-shelf pre-trained networks during training. At inference time, given a single-view image, it efficiently outputs an explicit mesh representation. We obtain improved qualitative and quantitative results on challenging quadruped animals compared to relevant existing work.
Authors: H M Dipu Kabir
Abstract: Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class activation mappings (CAMs) of the trained models, we observed the tendency towards looking at a bigger picture with the proposed model training methodology. Applying the vision transformer with the proposed background class, we receive state-of-the-art (SOTA) performance on STL-10, Caltech-101, and CINIC-10 datasets. Example scripts are available in the 'CAM' folder of the following GitHub Repository: github.com/dipuk0506/UQ
Authors: Wenjing Wang, Huan Yang, Zixi Tuo, Huiguo He, Junchen Zhu, Jianlong Fu, Jiaying Liu
Abstract: With the explosive popularity of AI-generated content (AIGC), video generation has recently received a lot of attention. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship between space and time, and the lack of large-scale text-video paired data. Existing text-video datasets suffer from limitations in both content quality and scale, or they are not open-source, rendering them inaccessible for study and use. For model design, previous approaches extend pretrained text-to-image generation models by adding temporal 1D convolution/attention modules for video generation. However, these approaches overlook the importance of jointly modeling space and time, inevitably leading to temporal distortions and misalignment between texts and videos. In this paper, we propose a novel approach that strengthens the interaction between spatial and temporal perceptions. In particular, we utilize a swapped cross-attention mechanism in 3D windows that alternates the ``query'' role between spatial and temporal blocks, enabling mutual reinforcement for each other. Moreover, to fully unlock model capabilities for high-quality video generation and promote the development of the field, we curate a large-scale and open-source video dataset called HD-VG-130M. This dataset comprises 130 million text-video pairs from the open-domain, ensuring high-definition, widescreen and watermark-free characters. A smaller-scale yet more meticulously cleaned subset further enhances the data quality, aiding models in achieving superior performance. Experimental quantitative and qualitative results demonstrate the superiority of our approach in terms of per-frame quality, temporal correlation, and text-video alignment, with clear margins.
Authors: Mingkun Li, Peng Xu, Chun-Guang Li, Jun Guo
Abstract: In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change. Existing unsupervised person re-id methods are mainly designed for short-term scenarios and usually rely on RGB cues so that fail to perceive feature patterns that are independent of the clothes. To crack this bottleneck, we propose a silhouette-driven contrastive learning (SiCL) method, which is designed to learn cross-clothes invariance by integrating both the RGB cues and the silhouette information within a contrastive learning framework. To our knowledge, this is the first tailor-made framework for unsupervised long-term clothes change \reid{}, with superior performance on six benchmark datasets. We conduct extensive experiments to evaluate our proposed SiCL compared to the state-of-the-art unsupervised person reid methods across all the representative datasets. Experimental results demonstrate that our proposed SiCL significantly outperforms other unsupervised re-id methods.
Authors: Hongtao Wang, Jiangshe Zhang, Xiaoli Wei, Li Long, Chunxia Zhang
Abstract: In seismic exploration, first break (FB) picking is a crucial aspect in the determination of subsurface velocity models, significantly influencing the placement of wells. Many deep neural networks (DNNs)-based automatic picking methods have been proposed to accelerate this processing. Significantly, the segmentation-based DNN methods provide a segmentation map and then estimate FB from the map using a picking threshold. However, the uncertainty of the results picked by DNNs still needs to be analyzed. Thus, the automatic picking methods applied in field datasets can not ensure robustness, especially in the case of a low signal-to-noise ratio (SNR). In this paper, we introduce uncertainty quantification into the FB picking task and propose a novel uncertainty-based picking deep learning network called UPNet. UPNet not only estimates the uncertainty of network output but also can filter the pickings with low confidence. Many experiments evaluate that UPNet exhibits higher accuracy and robustness than the deterministic DNN-based model, achieving State-of-the-Art (SOTA) performance in field surveys. In addition, we verify that the measurement uncertainty is meaningful, which can provide a reference for human decision-making.
Authors: Tsu-Ching Hsiao, Hao-Wei Chen, Hsuan-Kung Yang, Chun-Yi Lee
Abstract: Addressing pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the $SE(3)$ group, marking the first application of diffusion models to $SE(3)$ within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method's efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on $SE(3)$. This formulation not only improves the convergence of denoising process but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.
Authors: Hongjie Wang, Bhishma Dedhia, Niraj K. Jha
Abstract: Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging solution to address this challenge due to its ease of deployment on various Transformer backbones. However, most token pruning methods require computationally expensive fine-tuning, which is undesirable in many edge deployment cases. In this work, we propose Zero-TPrune, the first zero-shot method that considers both the importance and similarity of tokens in performing token pruning. It leverages the attention graph of pre-trained Transformer models to produce an importance distribution for tokens via our proposed Weighted Page Rank (WPR) algorithm. This distribution further guides token partitioning for efficient similarity-based pruning. Due to the elimination of the fine-tuning overhead, Zero-TPrune can prune large models at negligible computational cost, switch between different pruning configurations at no computational cost, and perform hyperparameter tuning efficiently. We evaluate the performance of Zero-TPrune on vision tasks by applying it to various vision Transformer backbones and testing them on ImageNet. Without any fine-tuning, Zero-TPrune reduces the FLOPs cost of DeiT-S by 34.7% and improves its throughput by 45.3% with only 0.4% accuracy loss. Compared with state-of-the-art pruning methods that require fine-tuning, Zero-TPrune not only eliminates the need for fine-tuning after pruning but also does so with only 0.1% accuracy loss. Compared with state-of-the-art fine-tuning-free pruning methods, Zero-TPrune reduces accuracy loss by up to 49% with similar FLOPs budgets. Project webpage: https://jha-lab.github.io/zerotprune.
Authors: Yunhe Gao, Zhuowei Li, Di Liu, Mu Zhou, Shaoting Zhang, Dimitris N. Metaxas
Abstract: A major focus of clinical imaging workflow is disease diagnosis and management, leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has led to the prevailing practice of developing task-specific segmentation models, without gaining insights from widespread imaging cohorts. Inspired by the training program of medical radiology residents, we propose a shift towards universal medical image segmentation, a paradigm aiming to build medical image understanding foundation models by leveraging the diversity and commonality across clinical targets, body regions, and imaging modalities. Towards this goal, we develop Hermes, a novel context-prior learning approach to address the challenges of data heterogeneity and annotation differences in medical image segmentation. In a large collection of eleven diverse datasets (2,438 3D images) across five modalities (CT, PET, T1, T2 and cine MRI) and multiple body regions, we demonstrate the merit of the universal paradigm over the traditional paradigm on addressing multiple tasks within a single model. By exploiting the synergy across tasks, Hermes achieves state-of-the-art performance on all testing datasets and shows superior model scalability. Results on two additional datasets reveals Hermes' strong performance for transfer learning, incremental learning, and generalization to downstream tasks. Hermes's learned priors demonstrate an appealing trait to reflect the intricate relations among tasks and modalities, which aligns with the established anatomical and imaging principles in radiology. The code is available: https://github.com/yhygao/universal-medical-image-segmentation.
URLs: https://github.com/yhygao/universal-medical-image-segmentation.
Authors: Seoyeon Kim, Minguk Kang, Dongwon Kim, Jaesik Park, Suha Kwak
Abstract: Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques for joint reasoning across modalities. However, the inherent cross-modal nature of RIS raises questions about the effectiveness of unimodal backbones. We propose RISCLIP, a novel framework that effectively leverages the cross-modal nature of CLIP for RIS. Observing CLIP's inherent alignment between image and text features, we capitalize on this starting point and introduce simple but strong modules that enhance unimodal feature extraction and leverage rich alignment knowledge in CLIP's image-text shared-embedding space. RISCLIP exhibits outstanding results on all three major RIS benchmarks and also outperforms previous CLIP-based methods, demonstrating the efficacy of our strategy in extending CLIP's image-text alignment to RIS.
Authors: Yiman Zhu, Lu Wang, Jingyi Yuan, Yu Guo
Abstract: On-orbit service is important for maintaining the sustainability of space environment. Space-based visible camera is an economical and lightweight sensor for situation awareness during on-orbit service. However, it can be easily affected by the low illumination environment. Recently, deep learning has achieved remarkable success in image enhancement of natural images, but seldom applied in space due to the data bottleneck. In this article, we first propose a dataset of the Beidou Navigation Satellite for on-orbit low-light image enhancement (LLIE). In the automatic data collection scheme, we focus on reducing domain gap and improving the diversity of the dataset. we collect hardware in-the-loop images based on a robotic simulation testbed imitating space lighting conditions. To evenly sample poses of different orientation and distance without collision, a collision-free working space and pose stratified sampling is proposed. Afterwards, a novel diffusion model is proposed. To enhance the image contrast without over-exposure and blurring details, we design a fused attention to highlight the structure and dark region. Finally, we compare our method with previous methods using our dataset, which indicates that our method has a better capacity in on-orbit LLIE.
Authors: Lukas Haas, Michal Skreta, Silas Alberti, Chelsea Finn
Abstract: Planet-scale image geolocalization remains a challenging problem due to the diversity of images originating from anywhere in the world. Although approaches based on vision transformers have made significant progress in geolocalization accuracy, success in prior literature is constrained to narrow distributions of images of landmarks, and performance has not generalized to unseen places. We present a new geolocalization system that combines semantic geocell creation, multi-task contrastive pretraining, and a novel loss function. Additionally, our work is the first to perform retrieval over location clusters for guess refinements. We train two models for evaluations on street-level data and general-purpose image geolocalization; the first model, PIGEON, is trained on data from the game of Geoguessr and is capable of placing over 40% of its guesses within 25 kilometers of the target location globally. We also develop a bot and deploy PIGEON in a blind experiment against humans, ranking in the top 0.01% of players. We further challenge one of the world's foremost professional Geoguessr players to a series of six matches with millions of viewers, winning all six games. Our second model, PIGEOTTO, differs in that it is trained on a dataset of images from Flickr and Wikipedia, achieving state-of-the-art results on a wide range of image geolocalization benchmarks, outperforming the previous SOTA by up to 7.7 percentage points on the city accuracy level and up to 38.8 percentage points on the country level. Our findings suggest that PIGEOTTO is the first image geolocalization model that effectively generalizes to unseen places and that our approach can pave the way for highly accurate, planet-scale image geolocalization systems. Our code is available on GitHub.
Authors: Robin Louiset, Edouard Duchesnay, Antoine Grigis, Benoit Dufumier, Pietro Gori
Abstract: Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (TG) (i.e., patients) from the ones that only exist in the target dataset. To do so, these methods separate the latent space into a set of salient features (i.e., proper to the target dataset) and a set of common features (i.e., exist in both datasets). Currently, all models fail to prevent the sharing of information between latent spaces effectively and to capture all salient factors of variation. To this end, we introduce two crucial regularization losses: a disentangling term between common and salient representations and a classification term between background and target samples in the salient space. We show a better performance than previous CA-VAEs methods on three medical applications and a natural images dataset (CelebA). Code and datasets are available on GitHub https://github.com/neurospin-projects/2023_rlouiset_sepvae.
URLs: https://github.com/neurospin-projects/2023_rlouiset_sepvae.
Authors: Anagh Malik, Parsa Mirdehghan, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell
Abstract: Neural radiance fields (NeRFs) have become a ubiquitous tool for modeling scene appearance and geometry from multiview imagery. Recent work has also begun to explore how to use additional supervision from lidar or depth sensor measurements in the NeRF framework. However, previous lidar-supervised NeRFs focus on rendering conventional camera imagery and use lidar-derived point cloud data as auxiliary supervision; thus, they fail to incorporate the underlying image formation model of the lidar. Here, we propose a novel method for rendering transient NeRFs that take as input the raw, time-resolved photon count histograms measured by a single-photon lidar system, and we seek to render such histograms from novel views. Different from conventional NeRFs, the approach relies on a time-resolved version of the volume rendering equation to render the lidar measurements and capture transient light transport phenomena at picosecond timescales. We evaluate our method on a first-of-its-kind dataset of simulated and captured transient multiview scans from a prototype single-photon lidar. Overall, our work brings NeRFs to a new dimension of imaging at transient timescales, newly enabling rendering of transient imagery from novel views. Additionally, we show that our approach recovers improved geometry and conventional appearance compared to point cloud-based supervision when training on few input viewpoints. Transient NeRFs may be especially useful for applications which seek to simulate raw lidar measurements for downstream tasks in autonomous driving, robotics, and remote sensing.
Authors: Yongxin Shao, Aihong Tan, Zhetao Sun, Enhui Zheng, Tianhong Yan, Peng Liao
Abstract: LiDAR-based 3D object detection and classification is crucial for autonomous driving. However, real-time inference from extremely sparse 3D data is a formidable challenge. To address this problem, a typical class of approaches transforms the point cloud cast into a regular data representation (voxels or projection maps). Then, it performs feature extraction with convolutional neural networks. However, such methods often result in a certain degree of information loss due to down-sampling or over-compression of feature information. This paper proposes a multi-modal point cloud feature fusion method for projection features and variable receptive field voxel features (PV-SSD) based on projection and variable voxelization to solve the information loss problem. We design a two-branch feature extraction structure with a 2D convolutional neural network to extract the point cloud's projection features in bird's-eye view to focus on the correlation between local features. A voxel feature extraction branch is used to extract local fine-grained features. Meanwhile, we propose a voxel feature extraction method with variable sensory fields to reduce the information loss of voxel branches due to downsampling. It avoids missing critical point information by selecting more useful feature points based on feature point weights for the detection task. In addition, we propose a multi-modal feature fusion module for point clouds. To validate the effectiveness of our method, we tested it on the KITTI dataset and ONCE dataset.
Authors: Esteve Valls Mascaro, Hyemin Ahn, Dongheui Lee
Abstract: The synthesis of human motion has traditionally been addressed through task-dependent models that focus on specific challenges, such as predicting future motions or filling in intermediate poses conditioned on known key-poses. In this paper, we present a novel task-independent model called UNIMASK-M, which can effectively address these challenges using a unified architecture. Our model obtains comparable or better performance than the state-of-the-art in each field. Inspired by Vision Transformers (ViTs), our UNIMASK-M model decomposes a human pose into body parts to leverage the spatio-temporal relationships existing in human motion. Moreover, we reformulate various pose-conditioned motion synthesis tasks as a reconstruction problem with different masking patterns given as input. By explicitly informing our model about the masked joints, our UNIMASK-M becomes more robust to occlusions. Experimental results show that our model successfully forecasts human motion on the Human3.6M dataset. Moreover, it achieves state-of-the-art results in motion inbetweening on the LaFAN1 dataset, particularly in long transition periods. More information can be found on the project website https://evm7.github.io/UNIMASKM-page/
Authors: Guilherme Schardong, Tiago Novello, Hallison Paz, Iurii Medvedev, Vin\'icius da Silva, Luiz Velho, Nuno Gon\c{c}alves
Abstract: Face morphing is a problem in computer graphics with numerous artistic and forensic applications. It is challenging due to variations in pose, lighting, gender, and ethnicity. This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coord-based neural networks to represent such warpings and blendings of face images. During training, we exploit the smoothness and flexibility of such networks by combining energy functionals employed in classical approaches without discretizations. Additionally, our method is time-dependent, allowing a continuous warping/blending of the images. During morphing inference, we need both direct and inverse transformations of the time-dependent warping. The first (second) is responsible for warping the target (source) image into the source (target) image. Our neural warping stores those maps in a single network dismissing the need for inverting them. The results of our experiments indicate that our method is competitive with both classical and generative models under the lens of image quality and face-morphing detectors. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.
Authors: Shaojie Zhang, Jianqin Yin, Yonghao Dang, Jiajun Fu
Abstract: Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, previous GCN-based methods rely on elaborate human priors excessively and construct complex feature aggregation mechanisms, which limits the generalizability and effectiveness of networks. To solve these problems, we propose a novel Spatial Topology Gating Unit (STGU), an MLP-based variant without extra priors, to capture the co-occurrence topology features that encode the spatial dependency across all joints. In STGU, to learn the point-wise topology features, a new gate-based feature interaction mechanism is introduced to activate the features point-to-point by the attention map generated from the input sample. Based on the STGU, we propose the first MLP-based model, SiT-MLP, for skeleton-based action recognition in this work. Compared with previous methods on three large-scale datasets, SiT-MLP achieves competitive performance. In addition, SiT-MLP reduces the parameters significantly with favorable results. The code will be available at https://github.com/BUPTSJZhang/SiT?MLP.
Authors: Zhuqiang Lu, Kun Hu, Chaoyue Wang, Lei Bai, Zhiyong Wang
Abstract: A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene. Recently, there has been an increasing interest in synthesising 360-degree images from conventional narrow field of view (NFoV) images captured by digital cameras and smartphones, for providing immersive experiences in various scenarios such as virtual reality. Yet, existing methods typically fall short in synthesizing intricate visual details or ensure the generated images align consistently with user-provided prompts. In this study, autoregressive omni-aware generative network (AOG-Net) is proposed for 360-degree image generation by out-painting an incomplete 360-degree image progressively with NFoV and text guidances joinly or individually. This autoregressive scheme not only allows for deriving finer-grained and text-consistent patterns by dynamically generating and adjusting the process but also offers users greater flexibility to edit their conditions throughout the generation process. A global-local conditioning mechanism is devised to comprehensively formulate the outpainting guidance in each autoregressive step. Text guidances, omni-visual cues, NFoV inputs and omni-geometry are encoded and further formulated with cross-attention based transformers into a global stream and a local stream into a conditioned generative backbone model. As AOG-Net is compatible to leverage large-scale models for the conditional encoder and the generative prior, it enables the generation to use extensive open-vocabulary text guidances. Comprehensive experiments on two commonly used 360-degree image datasets for both indoor and outdoor settings demonstrate the state-of-the-art performance of our proposed method. Our code will be made publicly available.
Authors: Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif
Abstract: Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modality. In this paper, we propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) that incorporates the proposed fusion strategy to perform multimodal material and semantic segmentation tasks. MMSFormer outperforms current state-of-the-art models on three different datasets. As we begin with only one input modality, performance improves progressively as additional modalities are incorporated, showcasing the effectiveness of the fusion block in combining useful information from diverse input modalities. Ablation studies show that different modules in the fusion block are crucial for overall model performance. Furthermore, our ablation studies also highlight the capacity of different input modalities to improve performance in the identification of different types of materials. The code and pretrained models will be made available at https://github.com/csiplab/MMSFormer.
Authors: Ruoyu Feng, Wenming Weng, Yanhui Wang, Yuhui Yuan, Jianmin Bao, Chong Luo, Zhibo Chen, Baining Guo
Abstract: In this paper, we present CCEdit, a versatile generative video editing framework based on diffusion models. Our approach employs a novel trident network structure that separates structure and appearance control, ensuring precise and creative editing capabilities. Utilizing the foundational ControlNet architecture, we maintain the structural integrity of the video during editing. The incorporation of an additional appearance branch enables users to exert fine-grained control over the edited key frame. These two side branches seamlessly integrate into the main branch, which is constructed upon existing text-to-image (T2I) generation models, through learnable temporal layers. The versatility of our framework is demonstrated through a diverse range of choices in both structure representations and personalized T2I models, as well as the option to provide the edited key frame. To facilitate comprehensive evaluation, we introduce the BalanceCC benchmark dataset, comprising 100 videos and 4 target prompts for each video. Our extensive user studies compare CCEdit with eight state-of-the-art video editing methods. The outcomes demonstrate CCEdit's substantial superiority over all other methods.
Authors: Esteve Valls Mascaro, Daniel Sliwowski, Dongheui Lee
Abstract: Robots are becoming increasingly integrated into our lives, assisting us in various tasks. To ensure effective collaboration between humans and robots, it is essential that they understand our intentions and anticipate our actions. In this paper, we propose a Human-Object Interaction (HOI) anticipation framework for collaborative robots. We propose an efficient and robust transformer-based model to detect and anticipate HOIs from videos. This enhanced anticipation empowers robots to proactively assist humans, resulting in more efficient and intuitive collaborations. Our model outperforms state-of-the-art results in HOI detection and anticipation in VidHOI dataset with an increase of 1.76% and 1.04% in mAP respectively while being 15.4 times faster. We showcase the effectiveness of our approach through experimental results in a real robot, demonstrating that the robot's ability to anticipate HOIs is key for better Human-Robot Interaction. More information can be found on our project webpage: https://evm7.github.io/HOI4ABOT_page/
Authors: Hu Xu, Saining Xie, Xiaoqing Ellen Tan, Po-Yao Huang, Russell Howes, Vasu Sharma, Shang-Wen Li, Gargi Ghosh, Luke Zettlemoyer, Christoph Feichtenhofer
Abstract: Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of CLIP is its data and not the model architecture or pre-training objective. However, CLIP only provides very limited information about its data and how it has been collected, leading to works that aim to reproduce CLIP's data by filtering with its model parameters. In this work, we intend to reveal CLIP's data curation approach and in our pursuit of making it open to the community introduce Metadata-Curated Language-Image Pre-training (MetaCLIP). MetaCLIP takes a raw data pool and metadata (derived from CLIP's concepts) and yields a balanced subset over the metadata distribution. Our experimental study rigorously isolates the model and training settings, concentrating solely on data. MetaCLIP applied to CommonCrawl with 400M image-text data pairs outperforms CLIP's data on multiple standard benchmarks. In zero-shot ImageNet classification, MetaCLIP achieves 70.8% accuracy, surpassing CLIP's 68.3% on ViT-B models. Scaling to 1B data, while maintaining the same training budget, attains 72.4%. Our observations hold across various model sizes, exemplified by ViT-H achieving 80.5%, without any bells-and-whistles. Curation code and training data distribution on metadata is made available at https://github.com/facebookresearch/MetaCLIP.
Authors: Zijie Chen, Lichao Zhang, Fangsheng Weng, Lili Pan, Zhenzhong Lan
Abstract: Despite significant progress in the field, it is still challenging to create personalized visual representations that align closely with the desires and preferences of individual users. This process requires users to articulate their ideas in words that are both comprehensible to the models and accurately capture their vision, posing difficulties for many users. In this paper, we tackle this challenge by leveraging historical user interactions with the system to enhance user prompts. We propose a novel approach that involves rewriting user prompts based on a newly collected large-scale text-to-image dataset with over 300k prompts from 3115 users. Our rewriting model enhances the expressiveness and alignment of user prompts with their intended visual outputs. Experimental results demonstrate the superiority of our methods over baseline approaches, as evidenced in our new offline evaluation method and online tests. Our code and dataset are available at https://github.com/zzjchen/Tailored-Visions.
Authors: Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, Wanli Ouyang
Abstract: In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pre-training methods have shown widespread success, most methods follow the ideas originally designed for 2D images. In this paper, we present UniPAD, a novel self-supervised learning paradigm applying 3D volumetric differentiable rendering. UniPAD implicitly encodes 3D space, facilitating the reconstruction of continuous 3D shape structures and the intricate appearance characteristics of their 2D projections. The flexibility of our method enables seamless integration into both 2D and 3D frameworks, enabling a more holistic comprehension of the scenes. We manifest the feasibility and effectiveness of UniPAD by conducting extensive experiments on various downstream 3D tasks. Our method significantly improves lidar-, camera-, and lidar-camera-based baseline by 9.1, 7.7, and 6.9 NDS, respectively. Notably, our pre-training pipeline achieves 73.2 NDS for 3D object detection and 79.4 mIoU for 3D semantic segmentation on the nuScenes validation set, achieving state-of-the-art results in comparison with previous methods. The code will be available at https://github.com/Nightmare-n/UniPAD.
Authors: Yi Ke Yun, Weisi Lin
Abstract: Although recent efforts in image quality assessment (IQA) have achieved promising performance, there still exists a considerable gap compared to the human visual system (HVS). One significant disparity lies in humans' seamless transition between full reference (FR) and no reference (NR) tasks, whereas existing models are constrained to either FR or NR tasks. This disparity implies the necessity of designing two distinct systems, thereby greatly diminishing the model's versatility. Therefore, our focus lies in unifying FR and NR IQA under a single framework. Specifically, we first employ an encoder to extract multi-level features from input images. Then a Hierarchical Attention (HA) module is proposed as a universal adapter for both FR and NR inputs to model the spatial distortion at each encoder stage. Furthermore, considering that different distortions contaminate encoder stages and damage image semantic meaning differently, a Semantic Distortion Aware (SDA) module is proposed to examine feature correlations between shallow and deep layers of the encoder. By adopting HA and SDA, the proposed network can effectively perform both FR and NR IQA. When our proposed model is independently trained on NR or FR IQA tasks, it outperforms existing models and achieves state-of-the-art performance. Moreover, when trained jointly on NR and FR IQA tasks, it further enhances the performance of NR IQA while achieving on-par performance in the state-of-the-art FR IQA. You only train once to perform both IQA tasks. Code will be released at: https://github.com/BarCodeReader/YOTO.
Authors: Weiwen Chen, Yingtie Lei, Shenghong Luo, Ziyang Zhou, Mingxian Li, Chi-Man Pun
Abstract: Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality.
Authors: Yihong Luo, Siya Qiu, Xingjian Tao, Yujun Cai, Jing Tang
Abstract: In this paper, we propose a novel generative model that utilizes a conditional Energy-Based Model (EBM) for enhancing Variational Autoencoder (VAE), termed Energy-Calibrated VAE (EC-VAE). Specifically, VAEs often suffer from blurry generated samples due to the lack of a tailored training on the samples generated in the generative direction. On the other hand, EBMs can generate high-quality samples but require expensive Markov Chain Monte Carlo (MCMC) sampling. To address these issues, we introduce a conditional EBM for calibrating the generative direction of VAE during training, without requiring it for the generation at test time. In particular, we train EC-VAE upon both the input data and the calibrated samples with adaptive weight to enhance efficacy while avoiding MCMC sampling at test time. Furthermore, we extend the calibration idea of EC-VAE to variational learning and normalizing flows, and apply EC-VAE to an additional application of zero-shot image restoration via neural transport prior and range-null theory. We evaluate the proposed method with two applications, including image generation and zero-shot image restoration, and the experimental results show that our method achieves competitive performance over single-step non-adversarial generation. Our code is available at https://github.com/DJ-LYH/EC-VAE.
Authors: Virmarie Maquiling, Sean Anthony Byrne, Diederick C. Niehorster, Marcus Nystr\"om, Enkelejda Kasneci
Abstract: The advent of foundation models signals a new era in artificial intelligence. The Segment Anything Model (SAM) is the first foundation model for image segmentation. In this study, we evaluate SAM's ability to segment features from eye images recorded in virtual reality setups. The increasing requirement for annotated eye-image datasets presents a significant opportunity for SAM to redefine the landscape of data annotation in gaze estimation. Our investigation centers on SAM's zero-shot learning abilities and the effectiveness of prompts like bounding boxes or point clicks. Our results are consistent with studies in other domains, demonstrating that SAM's segmentation effectiveness can be on-par with specialized models depending on the feature, with prompts improving its performance, evidenced by an IoU of 93.34% for pupil segmentation in one dataset. Foundation models like SAM could revolutionize gaze estimation by enabling quick and easy image segmentation, reducing reliance on specialized models and extensive manual annotation.
Authors: Ehsan Asali, Prashant Doshi, Jin Sun
Abstract: The learn-from-observation (LfO) paradigm is a human-inspired mode for a robot to learn to perform a task simply by watching it being performed. LfO can facilitate robot integration on factory floors by minimizing disruption and reducing tedious programming. A key component of the LfO pipeline is a transformation of the depth camera frames to the corresponding task state and action pairs, which are then relayed to learning techniques such as imitation or inverse reinforcement learning for understanding the task parameters. While several existing computer vision models analyze videos for activity recognition, SA-Net specifically targets robotic LfO from RGB-D data. However, SA-Net and many other models analyze frame data captured from a single viewpoint. Their analysis is therefore highly sensitive to occlusions of the observed task, which are frequent in deployments. An obvious way of reducing occlusions is to simultaneously observe the task from multiple viewpoints and synchronously fuse the multiple streams in the model. Toward this, we present multi-view SA-Net, which generalizes the SA-Net model to allow the perception of multiple viewpoints of the task activity, integrate them, and better recognize the state and action in each frame. Performance evaluations on two distinct domains establish that MVSA-Net recognizes the state-action pairs under occlusion more accurately compared to single-view MVSA-Net and other baselines. Our ablation studies further evaluate its performance under different ambient conditions and establish the contribution of the architecture components. As such, MVSA-Net offers a significantly more robust and deployable state-action trajectory generation compared to previous methods.
Authors: Yiyu Chen, Zheyi Fan, Zhaoru Chen, Yixuan Zhu
Abstract: Person re-identification (re-ID) is a challenging task that aims to learn discriminative features for person retrieval. In person re-ID, Jaccard distance is a widely used distance metric, especially in re-ranking and clustering scenarios. However, we discover that camera variation has a significant negative impact on the reliability of Jaccard distance. In particular, Jaccard distance calculates the distance based on the overlap of relevant neighbors. Due to camera variation, intra-camera samples dominate the relevant neighbors, which reduces the reliability of the neighbors by introducing intra-camera negative samples and excluding inter-camera positive samples. To overcome this problem, we propose a novel camera-aware Jaccard (CA-Jaccard) distance that leverages camera information to enhance the reliability of Jaccard distance. Specifically, we design camera-aware k-reciprocal nearest neighbors (CKRNNs) to find k-reciprocal nearest neighbors on the intra-camera and inter-camera ranking lists, which improves the reliability of relevant neighbors and guarantees the contribution of inter-camera samples in the overlap. Moreover, we propose a camera-aware local query expansion (CLQE) to mine reliable samples in relevant neighbors by exploiting camera variation as a strong constraint and assign these samples higher weights in overlap, further improving the reliability. Our CA-Jaccard distance is simple yet effective and can serve as a general distance metric for person re-ID methods with high reliability and low computational cost. Extensive experiments demonstrate the effectiveness of our method.
Authors: Chi Yan, Delin Qu, Dan Xu, Bin Zhao, Zhigang Wang, Dong Wang, Xuelong Li
Abstract: In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. Project page: https://gs-slam.github.io/.
Authors: Zixuan Xie, Rengan Xie, Rong Li, Kai Huang, Pengju Qiao, Jingsen Zhu, Xu Yin, Qi Ye, Wei Hua, Yuchi Huo, Hujun Bao
Abstract: In this work, we use multi-view aerial images to reconstruct the geometry, lighting, and material of facades using neural signed distance fields (SDFs). Without the requirement of complex equipment, our method only takes simple RGB images captured by a drone as inputs to enable physically based and photorealistic novel-view rendering, relighting, and editing. However, a real-world facade usually has complex appearances ranging from diffuse rocks with subtle details to large-area glass windows with specular reflections, making it hard to attend to everything. As a result, previous methods can preserve the geometry details but fail to reconstruct smooth glass windows or verse vise. In order to address this challenge, we introduce three spatial- and semantic-adaptive optimization strategies, including a semantic regularization approach based on zero-shot segmentation techniques to improve material consistency, a frequency-aware geometry regularization to balance surface smoothness and details in different surfaces, and a visibility probe-based scheme to enable efficient modeling of the local lighting in large-scale outdoor environments. In addition, we capture a real-world facade aerial 3D scanning image set and corresponding point clouds for training and benchmarking. The experiment demonstrates the superior quality of our method on facade holistic inverse rendering, novel view synthesis, and scene editing compared to state-of-the-art baselines.
Authors: Hao Li, Dingwen Zhang, Yalun Dai, Nian Liu, Lechao Cheng, Jingfeng Li, Jingdong Wang, Junwei Han
Abstract: Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, we conduct experimental comparisons under two perception tasks (\textit{i.e.} semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94\%, 11.76\%, and 8.47\% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively.
Authors: Yongliang Lin, Yongzhi Su, Praveen Nathan, Sandeep Inuganti, Yan Di, Martin Sundermeyer, Fabian Manhardt, Didier Stricker, Jason Rambach, Yu Zhang
Abstract: In this work, we present a novel dense-correspondence method for 6DoF object pose estimation from a single RGB-D image. While many existing data-driven methods achieve impressive performance, they tend to be time-consuming due to their reliance on rendering-based refinement approaches. To circumvent this limitation, we present HiPose, which establishes 3D-3D correspondences in a coarse-to-fine manner with a hierarchical binary surface encoding. Unlike previous dense-correspondence methods, we estimate the correspondence surface by employing point-to-surface matching and iteratively constricting the surface until it becomes a correspondence point while gradually removing outliers. Extensive experiments on public benchmarks LM-O, YCB-V, and T-Less demonstrate that our method surpasses all refinement-free methods and is even on par with expensive refinement-based approaches. Crucially, our approach is computationally efficient and enables real-time critical applications with high accuracy requirements.
Authors: Kecen Li, Chen Gong, Zhixiang Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang
Abstract: Differential Privacy (DP) image data synthesis, which leverages the DP technique to generate synthetic data to replace the sensitive data, allowing organizations to share and utilize synthetic images without privacy concerns. Previous methods incorporate the advanced techniques of generative models and pre-training on a public dataset to produce exceptional DP image data, but suffer from problems of unstable training and massive computational resource demands. This paper proposes a novel DP image synthesis method, termed PRIVIMAGE, which meticulously selects pre-training data, promoting the efficient creation of DP datasets with high fidelity and utility. PRIVIMAGE first establishes a semantic query function using a public dataset. Then, this function assists in querying the semantic distribution of the sensitive dataset, facilitating the selection of data from the public dataset with analogous semantics for pre-training. Finally, we pre-train an image generative model using the selected data and then fine-tune this model on the sensitive dataset using Differentially Private Stochastic Gradient Descent (DP-SGD). PRIVIMAGE allows us to train a lightly parameterized generative model, reducing the noise in the gradient during DP-SGD training and enhancing training stability. Extensive experiments demonstrate that PRIVIMAGE uses only 1% of the public dataset for pre-training and 7.6% of the parameters in the generative model compared to the state-of-the-art method, whereas achieves superior synthetic performance and conserves more computational resources. On average, PRIVIMAGE achieves 30.1% lower FID and 12.6% higher Classification Accuracy than the state-of-the-art method. The replication package and datasets can be accessed online.
Authors: Jiaxuan Li, Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama
Abstract: Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data; yet novel objects occur frequently, necessitating the requirement of sustaining up-to-date object knowledge for open-world comprehension. Instead of relying on large amounts of data and/or scaling up network parameters, we introduce a highly effective retrieval-augmented image captioning method that prompts LLMs with object names retrieved from External Visual--name memory (EVCap). We build ever-changing object knowledge memory using objects' visuals and names, enabling us to (i) update the memory at a minimal cost and (ii) effortlessly augment LLMs with retrieved object names by utilizing a lightweight and fast-to-train model. Our model, which was trained only on the COCO dataset, can adapt to out-of-domain without requiring additional fine-tuning or re-training. Our experiments conducted on benchmarks and synthetic commonsense-violating data show that EVCap, with only 3.97M trainable parameters, exhibits superior performance compared to other methods based on frozen pre-trained LLMs. Its performance is also competitive to specialist SOTAs that require extensive training.
Authors: Ayush K. Rai, Tarun Krishna, Feiyan Hu, Alexandru Drimbarean, Kevin McGuinness, Alan F. Smeaton, Noel E. O'Connor
Abstract: Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances. Recent works have investigated the creation of pseudo-anomalies (PAs) using only the normal data and making strong assumptions about real-world anomalies with regards to abnormality of objects and speed of motion to inject prior information about anomalies in an autoencoder (AE) based reconstruction model during training. This work proposes a novel method for generating generic spatio-temporal PAs by inpainting a masked out region of an image using a pre-trained Latent Diffusion Model and further perturbing the optical flow using mixup to emulate spatio-temporal distortions in the data. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting by learning three types of anomaly indicators, namely reconstruction quality, temporal irregularity and semantic inconsistency. Extensive experiments on four VAD benchmark datasets namely Ped2, Avenue, ShanghaiTech and UBnormal demonstrate that our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting. Our analysis also examines the transferability and generalisation of PAs across these datasets, offering valuable insights by identifying real-world anomalies through PAs.
Authors: Huajian Huang, Longwei Li, Hui Cheng, Sai-Kit Yeung
Abstract: The integration of neural rendering and the SLAM system recently showed promising results in joint localization and photorealistic view reconstruction. However, existing methods, fully relying on implicit representations, are so resource-hungry that they cannot run on portable devices, which deviates from the original intention of SLAM. In this paper, we present Photo-SLAM, a novel SLAM framework with a hyper primitives map. Specifically, we simultaneously exploit explicit geometric features for localization and learn implicit photometric features to represent the texture information of the observed environment. In addition to actively densifying hyper primitives based on geometric features, we further introduce a Gaussian-Pyramid-based training method to progressively learn multi-level features, enhancing photorealistic mapping performance. The extensive experiments with monocular, stereo, and RGB-D datasets prove that our proposed system Photo-SLAM significantly outperforms current state-of-the-art SLAM systems for online photorealistic mapping, e.g., PSNR is 30% higher and rendering speed is hundreds of times faster in the Replica dataset. Moreover, the Photo-SLAM can run at real-time speed using an embedded platform such as Jetson AGX Orin, showing the potential of robotics applications.
Authors: Huajian Huang, Changkun Liu, Yipeng Zhu, Hui Cheng, Tristan Braud, Sai-Kit Yeung
Abstract: Portable 360$^\circ$ cameras are becoming a cheap and efficient tool to establish large visual databases. By capturing omnidirectional views of a scene, these cameras could expedite building environment models that are essential for visual localization. However, such an advantage is often overlooked due to the lack of valuable datasets. This paper introduces a new benchmark dataset, 360Loc, composed of 360$^\circ$ images with ground truth poses for visual localization. We present a practical implementation of 360$^\circ$ mapping combining 360$^\circ$ images with lidar data to generate the ground truth 6DoF poses. 360Loc is the first dataset and benchmark that explores the challenge of cross-device visual positioning, involving 360$^\circ$ reference frames, and query frames from pinhole, ultra-wide FoV fisheye, and 360$^\circ$ cameras. We propose a virtual camera approach to generate lower-FoV query frames from 360$^\circ$ images, which ensures a fair comparison of performance among different query types in visual localization tasks. We also extend this virtual camera approach to feature matching-based and pose regression-based methods to alleviate the performance loss caused by the cross-device domain gap, and evaluate its effectiveness against state-of-the-art baselines. We demonstrate that omnidirectional visual localization is more robust in challenging large-scale scenes with symmetries and repetitive structures. These results provide new insights into 360-camera mapping and omnidirectional visual localization with cross-device queries.
Authors: Lorenzo Bianchi, Fabio Carrara, Nicola Messina, Claudio Gennaro, Fabrizio Falchi
Abstract: Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference. In this paper, we aim to probe the state-of-the-art methods for open-vocabulary object detection to determine to what extent they understand fine-grained properties of objects and their parts. To this end, we introduce an evaluation protocol based on dynamic vocabulary generation to test whether models detect, discern, and assign the correct fine-grained description to objects in the presence of hard-negative classes. We contribute with a benchmark suite of increasing difficulty and probing different properties like color, pattern, and material. We further enhance our investigation by evaluating several state-of-the-art open-vocabulary object detectors using the proposed protocol and find that most existing solutions, which shine in standard open-vocabulary benchmarks, struggle to accurately capture and distinguish finer object details. We conclude the paper by highlighting the limitations of current methodologies and exploring promising research directions to overcome the discovered drawbacks. Data and code are available at https://lorebianchi98.github.io/FG-OVD/.
Authors: Jiapeng Tang, Angela Dai, Yinyu Nie, Lev Markhasin, Justus Thies, Matthias Niessner
Abstract: We introduce Diffusion Parametric Head Models (DPHMs), a generative model that enables robust volumetric head reconstruction and tracking from monocular depth sequences. While recent volumetric head models, such as NPHMs, can now excel in representing high-fidelity head geometries, tracking and reconstructing heads from real-world single-view depth sequences remains very challenging, as the fitting to partial and noisy observations is underconstrained. To tackle these challenges, we propose a latent diffusion-based prior to regularize volumetric head reconstruction and tracking. This prior-based regularizer effectively constrains the identity and expression codes to lie on the underlying latent manifold which represents plausible head shapes. To evaluate the effectiveness of the diffusion-based prior, we collect a dataset of monocular Kinect sequences consisting of various complex facial expression motions and rapid transitions. We compare our method to state-of-the-art tracking methods and demonstrate improved head identity reconstruction as well as robust expression tracking.
Authors: Yichen Liu, Benran Hu, Chi-Keung Tang, Yu-Wing Tai
Abstract: Recently, the Segment Anything Model (SAM) has showcased remarkable capabilities of zero-shot segmentation, while NeRF (Neural Radiance Fields) has gained popularity as a method for various 3D problems beyond novel view synthesis. Though there exist initial attempts to incorporate these two methods into 3D segmentation, they face the challenge of accurately and consistently segmenting objects in complex scenarios. In this paper, we introduce the Segment Anything for NeRF in High Quality (SANeRF-HQ) to achieve high-quality 3D segmentation of any target object in a given scene. SANeRF-HQ utilizes SAM for open-world object segmentation guided by user-supplied prompts, while leveraging NeRF to aggregate information from different viewpoints. To overcome the aforementioned challenges, we employ density field and RGB similarity to enhance the accuracy of segmentation boundary during the aggregation. Emphasizing on segmentation accuracy, we evaluate our method on multiple NeRF datasets where high-quality ground-truths are available or manually annotated. SANeRF-HQ shows a significant quality improvement over state-of-the-art methods in NeRF object segmentation, provides higher flexibility for object localization, and enables more consistent object segmentation across multiple views. Results and code are available at the project site: https://lyclyc52.github.io/SANeRF-HQ/.
Authors: Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi
Abstract: 3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artifacts reducing feature quality. Recently, 3D Gaussian Splatting has shown state-of-the-art performance on real-time radiance field rendering. In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation. This translation is not straightforward: naively incorporating feature fields in the 3DGS framework encounters significant challenges, notably the disparities in spatial resolution and channel consistency between RGB images and feature maps. We propose architectural and training changes to efficiently avert this problem. Our proposed method is general, and our experiments showcase novel view semantic segmentation, language-guided editing and segment anything through learning feature fields from state-of-the-art 2D foundation models such as SAM and CLIP-LSeg. Across experiments, our distillation method is able to provide comparable or better results, while being significantly faster to both train and render. Additionally, to the best of our knowledge, we are the first method to enable point and bounding-box prompting for radiance field manipulation, by leveraging the SAM model. Project website at: https://feature-3dgs.github.io/
Authors: Qi Yang, Xing Nie, Tong Li, Pengfei Gao, Ying Guo, Cheng Zhen, Pengfei Yan, Shiming Xiang
Abstract: Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglement, we employ a Siam-Encoder Module (SEM) that leverages prior knowledge to generate more precise visual features from the foundational model. For modality entanglement, we design a Bilateral-Fusion Module (BFM), enabling COMBO to align corresponding visual and auditory signals bi-directionally. As for temporal entanglement, we introduce an innovative adaptive inter-frame consistency loss according to the inherent rules of temporal. Comprehensive experiments and ablation studies on AVSBench-object (84.7 mIoU on S4, 59.2 mIou on MS3) and AVSBench-semantic (42.1 mIoU on AVSS) datasets demonstrate that COMBO surpasses previous state-of-the-art methods. Code and more results will be publicly available at https://yannqi.github.io/AVS-COMBO/.
Authors: Zechuan Zhang, Zongxin Yang, Yi Yang
Abstract: Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline.SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios. Project page https://river-zhang.github.io/SIFU-projectpage/ .
Authors: Mengwei Ren, Wei Xiong, Jae Shin Yoon, Zhixin Shu, Jianming Zhang, HyunJoon Jung, Guido Gerig, He Zhang
Abstract: Portrait harmonization aims to composite a subject into a new background, adjusting its lighting and color to ensure harmony with the background scene. Existing harmonization techniques often only focus on adjusting the global color and brightness of the foreground and ignore crucial illumination cues from the background such as apparent lighting direction, leading to unrealistic compositions. We introduce Relightful Harmonization, a lighting-aware diffusion model designed to seamlessly harmonize sophisticated lighting effect for the foreground portrait using any background image. Our approach unfolds in three stages. First, we introduce a lighting representation module that allows our diffusion model to encode lighting information from target image background. Second, we introduce an alignment network that aligns lighting features learned from image background with lighting features learned from panorama environment maps, which is a complete representation for scene illumination. Last, to further boost the photorealism of the proposed method, we introduce a novel data simulation pipeline that generates synthetic training pairs from a diverse range of natural images, which are used to refine the model. Our method outperforms existing benchmarks in visual fidelity and lighting coherence, showing superior generalization in real-world testing scenarios, highlighting its versatility and practicality.
Authors: Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll
Abstract: Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real data to learn strong interaction and 3D shape priors is very expensive due to the combinatorial nature of human-object interactions. In this paper, we propose ProciGen (Procedural interaction Generation), a method to procedurally generate datasets with both, plausible interaction and diverse object variation. We generate 1M+ human-object interaction pairs in 3D and leverage this large-scale data to train our HDM (Hierarchical Diffusion Model), a novel method to reconstruct interacting human and unseen objects, without any templates. Our HDM is an image-conditioned diffusion model that learns both realistic interaction and highly accurate human and object shapes. Experiments show that our HDM trained with ProciGen significantly outperforms prior methods that requires template meshes and that our dataset allows training methods with strong generalization ability to unseen object instances. Our code and data are released.
Authors: Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang, Seungryong Kim, Chong Luo
Abstract: This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision. Our innovative framework, unlike any before, seamlessly integrates 2D correspondence matching, camera pose estimation, and NeRF rendering, fostering a synergistic enhancement of these tasks. We achieve this through designing an architecture that utilizes a shared representation, which serves as a foundation for enhanced 3D geometry understanding. Capitalizing on the inherent interplay between the tasks, our unified framework is trained end-to-end with the proposed training strategy to improve overall model accuracy. Through extensive evaluations across diverse indoor and outdoor scenes from two real-world datasets, we demonstrate that our approach achieves substantial improvement over previous methodologies, especially in scenarios characterized by extreme viewpoint changes and the absence of accurate camera poses.
Authors: Peng Lu, Tao Jiang, Yining Li, Xiangtai Li, Kai Chen, Wenming Yang
Abstract: Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases, existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance. This paper introduces RTMO, a one-stage pose estimation framework that seamlessly integrates coordinate classification by representing keypoints using dual 1-D heatmaps within the YOLO architecture, achieving accuracy comparable to top-down methods while maintaining high speed. We propose a dynamic coordinate classifier and a tailored loss function for heatmap learning, specifically designed to address the incompatibilities between coordinate classification and dense prediction models. RTMO outperforms state-of-the-art one-stage pose estimators, achieving 1.1% higher AP on COCO while operating about 9 times faster with the same backbone. Our largest model, RTMO-l, attains 74.8% AP on COCO val2017 and 141 FPS on a single V100 GPU, demonstrating its efficiency and accuracy. The code and models are available at https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo.
URLs: https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo.
Authors: Muxin Zhang, Qiao Feng, Zhuo Su, Chao Wen, Zhou Xue, Kun Li
Abstract: 3D human generation is increasingly significant in various applications. However, the direct use of 2D generative methods in 3D generation often results in losing local details, while methods that reconstruct geometry from generated images struggle with global view consistency. In this work, we introduce Joint2Human, a novel method that leverages 2D diffusion models to generate detailed 3D human geometry directly, ensuring both global structure and local details. To achieve this, we employ the Fourier occupancy field (FOF) representation, enabling the direct generation of 3D shapes as preliminary results with 2D generative models. With the proposed high-frequency enhancer and the multi-view recarving strategy, our method can seamlessly integrate the details from different views into a uniform global shape. To better utilize the 3D human prior and enhance control over the generated geometry, we introduce a compact spherical embedding of 3D joints. This allows for an effective guidance of pose during the generation process. Additionally, our method can generate 3D humans guided by textual inputs. Our experimental results demonstrate the capability of our method to ensure global structure, local details, high resolution, and low computational cost simultaneously. More results and the code can be found on our project page at http://cic.tju.edu.cn/faculty/likun/projects/Joint2Human.
URLs: http://cic.tju.edu.cn/faculty/likun/projects/Joint2Human.
Authors: Phuc D. A. Nguyen, Tuan Duc Ngo, Evangelos Kalogerakis, Chuang Gan, Anh Tran, Cuong Pham, Khoi Nguyen
Abstract: We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments exhibit diverse shapes, scales, and colors, making precise instance-level identification a challenging task. Recent advancements in Open-Vocabulary scene understanding have made significant strides in this area by employing class-agnostic 3D instance proposal networks for object localization and learning queryable features for each 3D mask. While these methods produce high-quality instance proposals, they struggle with identifying small-scale and geometrically ambiguous objects. The key idea of our method is a new module that aggregates 2D instance masks across frames and maps them to geometrically coherent point cloud regions as high-quality object proposals addressing the above limitations. These are then combined with 3D class-agnostic instance proposals to include a wide range of objects in the real world. To validate our approach, we conducted experiments on three prominent datasets, including ScanNet200, S3DIS, and Replica, demonstrating significant performance gains in segmenting objects with diverse categories over the state-of-the-art approaches.
Authors: Tai Le-Gia, Jaehyun Ahn
Abstract: Contrastive representation learning has emerged as an outstanding approach for anomaly detection. In this work, we explore the $\ell_2$-norm of contrastive features and its applications in out-of-distribution detection. We propose a simple method based on contrastive learning, which incorporates out-of-distribution data by discriminating against normal samples in the contrastive layer space. Our approach can be applied flexibly as an outlier exposure (OE) approach, where the out-of-distribution data is a huge collective of random images, or as a fully self-supervised learning approach, where the out-of-distribution data is self-generated by applying distribution-shifting transformations. The ability to incorporate additional out-of-distribution samples enables a feasible solution for datasets where AD methods based on contrastive learning generally underperform, such as aerial images or microscopy images. Furthermore, the high-quality features learned through contrastive learning consistently enhance performance in OE scenarios, even when the available out-of-distribution dataset is not diverse enough. Our extensive experiments demonstrate the superiority of our proposed method under various scenarios, including unimodal and multimodal settings, with various image datasets.
Authors: Zhifan Zhu, Dima Damen
Abstract: We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the reconstruction of frames during which the hand is stably holding the object. We first develop the stable grasp definition based on the intuition that the in-contact area between the hand and object should remain stable. By analysing the 3D ARCTIC dataset, we identify stable grasp durations and showcase that objects in stable grasps move within a single degree of freedom (1-DoF). We thereby propose a method to jointly optimise all frames within a stable grasp, minimising object motions to a latent 1-DoF. Finally, we extend the knowledge to in-the-wild videos by labelling 2.4K clips of stable grasps. Our proposed EPIC-Grasps dataset includes 390 object instances of 9 categories, featuring stable grasps from videos of daily interactions in 141 environments. Without 3D ground truth, we use stable contact areas and 2D projection masks to assess the HO-SGR task in the wild. We evaluate relevant methods and our approach preserves significantly higher stable contact area, on both EPIC-Grasps and stable grasp sub-sequences from the ARCTIC dataset.
Authors: Haisong Liu, Yang Chen, Haiguang Wang, Zetong Yang, Tianyu Li, Jia Zeng, Li Chen, Hongyang Li, Limin Wang
Abstract: Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering high computational costs. To bridge the gap, we introduce a novel fully sparse occupancy network, termed SparseOcc. SparseOcc initially reconstructs a sparse 3D representation from visual inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries. A mask-guided sparse sampling is designed to enable sparse queries to interact with 2D features in a fully sparse manner, thereby circumventing costly dense features or global attention. Additionally, we design a thoughtful ray-based evaluation metric, namely RayIoU, to solve the inconsistency penalty along depths raised in traditional voxel-level mIoU criteria. SparseOcc demonstrates its effectiveness by achieving a RayIoU of 34.0, while maintaining a real-time inference speed of 17.3 FPS, with 7 history frames inputs. By incorporating more preceding frames to 15, SparseOcc continuously improves its performance to 35.1 RayIoU without whistles and bells. Code is available at https://github.com/MCG-NJU/SparseOcc.
Authors: Yuming Huang, Yingpin Chen, Changhui Wu, Hanrong Xie, Binhui Song, Hui Wang
Abstract: The Swin Transformer image super-resolution reconstruction network only relies on the long-range relationship of window attention and shifted window attention to explore features. This mechanism has two limitations. On the one hand, it only focuses on global features while ignoring local features. On the other hand, it is only concerned with spatial feature interactions while ignoring channel features and channel interactions, thus limiting its non-linear mapping ability. To address the above limitations, this paper proposes enhanced Swin Transformer modules via alternating aggregation of local-global features. In the local feature aggregation stage, we introduce a shift convolution to realize the interaction between local spatial information and channel information. Then, a block sparse global perception module is introduced in the global feature aggregation stage. In this module, we reorganize the spatial information first, then send the recombination information into a dense layer to implement the global perception. After that, a multi-scale self-attention module and a low-parameter residual channel attention module are introduced to realize information aggregation at different scales. Finally, the proposed network is validated on five publicly available datasets. The experimental results show that the proposed network outperforms the other state-of-the-art super-resolution networks.
Authors: Renshuai Liu, Bowen Ma, Wei Zhang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Xuan Cheng
Abstract: In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting diverse expressions. This paper introduces our efforts towards personalized face generation. To this end, we propose a novel multi-modal face generation framework, capable of simultaneous identity-expression control and more fine-grained expression synthesis. Our expression control is so sophisticated that it can be specialized by the fine-grained emotional vocabulary. We devise a novel diffusion model that can undertake the task of simultaneously face swapping and reenactment. Due to the entanglement of identity and expression, it's nontrivial to separately and precisely control them in one framework, thus has not been explored yet. To overcome this, we propose several innovative designs in the conditional diffusion model, including balancing identity and expression encoder, improved midpoint sampling, and explicitly background conditioning. Extensive experiments have demonstrated the controllability and scalability of the proposed framework, in comparison with state-of-the-art text-to-image, face swapping, and face reenactment methods.
Authors: Huy Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes
Abstract: Aerial-ground person re-identification (Re-ID) presents unique challenges in computer vision, stemming from the distinct differences in viewpoints, poses, and resolutions between high-altitude aerial and ground-based cameras. Existing research predominantly focuses on ground-to-ground matching, with aerial matching less explored due to a dearth of comprehensive datasets. To address this, we introduce AG-ReID.v2, a dataset specifically designed for person Re-ID in mixed aerial and ground scenarios. This dataset comprises 100,502 images of 1,615 unique individuals, each annotated with matching IDs and 15 soft attribute labels. Data were collected from diverse perspectives using a UAV, stationary CCTV, and smart glasses-integrated camera, providing a rich variety of intra-identity variations. Additionally, we have developed an explainable attention network tailored for this dataset. This network features a three-stream architecture that efficiently processes pairwise image distances, emphasizes key top-down features, and adapts to variations in appearance due to altitude differences. Comparative evaluations demonstrate the superiority of our approach over existing baselines. We plan to release the dataset and algorithm source code publicly, aiming to advance research in this specialized field of computer vision. For access, please visit https://github.com/huynguyen792/AG-ReID.v2.
Authors: Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao
Abstract: This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second, an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively, including six public datasets and randomly captured photos. It demonstrates impressive generalization ability. Further, through fine-tuning it with metric depth information from NYUv2 and KITTI, new SOTAs are set. Our better depth model also results in a better depth-conditioned ControlNet. Our models are released at https://github.com/LiheYoung/Depth-Anything.
Authors: Yesheng Zhang, Xu Zhao
Abstract: Feature matching is a crucial task in the field of computer vision, which involves finding correspondences between images. Previous studies achieve remarkable performance using learning-based feature comparison. However, the pervasive presence of matching redundancy between images gives rise to unnecessary and error-prone computations in these methods, imposing limitations on their accuracy. To address this issue, we propose MESA, a novel approach to establish precise area (or region) matches for efficient matching redundancy reduction. MESA first leverages the advanced image understanding capability of SAM, a state-of-the-art foundation model for image segmentation, to obtain image areas with implicit semantic. Then, a multi-relational graph is proposed to model the spatial structure of these areas and construct their scale hierarchy. Based on graphical models derived from the graph, the area matching is reformulated as an energy minimization task and effectively resolved. Extensive experiments demonstrate that MESA yields substantial precision improvement for multiple point matchers in indoor and outdoor downstream tasks, e.g. +13.61% for DKM in indoor pose estimation.
Authors: Hyunyoung Jung, Seonghyeon Nam, Nikolaos Sarafianos, Sungjoo Yoo, Alexander Sorkine-Hornung, Rakesh Ranjan
Abstract: Shape and geometric patterns are essential in defining stylistic identity. However, current 3D style transfer methods predominantly focus on transferring colors and textures, often overlooking geometric aspects. In this paper, we introduce Geometry Transfer, a novel method that leverages geometric deformation for 3D style transfer. This technique employs depth maps to extract a style guide, subsequently applied to stylize the geometry of radiance fields. Moreover, we propose new techniques that utilize geometric cues from the 3D scene, thereby enhancing aesthetic expressiveness and more accurately reflecting intended styles. Our extensive experiments show that Geometry Transfer enables a broader and more expressive range of stylizations, thereby significantly expanding the scope of 3D style transfer.
Authors: Zequan Chen, Jianping Li, Qusheng Li, Bisheng Yang, Zhen Dong
Abstract: Automated Aerial Triangulation (AAT), aiming to restore image pose and reconstruct sparse points simultaneously, plays a pivotal role in earth observation. With its rich research heritage spanning several decades in photogrammetry, AAT has evolved into a fundamental process widely applied in large-scale Unmanned Aerial Vehicle (UAV) based mapping. Despite its advancements, classic AAT methods still face challenges like low efficiency and limited robustness. This paper introduces DeepAAT, a deep learning network designed specifically for AAT of UAV imagery. DeepAAT considers both spatial and spectral characteristics of imagery, enhancing its capability to resolve erroneous matching pairs and accurately predict image poses. DeepAAT marks a significant leap in AAT's efficiency, ensuring thorough scene coverage and precision. Its processing speed outpaces incremental AAT methods by hundreds of times and global AAT methods by tens of times while maintaining a comparable level of reconstruction accuracy. Additionally, DeepAAT's scene clustering and merging strategy facilitate rapid localization and pose determination for large-scale UAV images, even under constrained computing resources. The experimental results demonstrate DeepAAT's substantial improvements over conventional AAT methods, highlighting its potential in the efficiency and accuracy of UAV-based 3D reconstruction tasks. To benefit the photogrammetry society, the code of DeepAAT will be released at: https://github.com/WHU-USI3DV/DeepAAT.
Authors: Wenhui Chang, Hongming Chen, Xin He, Xiang Chen, Liangduo Shen
Abstract: Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality. Despite recent progress in image deraining methods and datasets, there is a lack of focus on raindrop removal from UAV aerial imagery due to the unique challenges posed by varying angles and rapid movement during drone flight. To fill the gap in this research, we first construct a new benchmark dataset for removing raindrops from UAV images, called UAV-Rain1k. In this letter, we provide a dataset generation pipeline, which includes modeling raindrop shapes using Blender, collecting background images from various UAV angles, random sampling of rain masks and etc. Based on the proposed benchmark, we further present a comprehensive evaluation of existing representative image deraining algorithms, and reveal future research opportunities worth exploring. The proposed dataset is publicly available at https://github.com/cschenxiang/UAV-Rain1k.
Authors: Chengjian Feng, Yujie Zhong, Zequn Jie, Weidi Xie, Lin Ma
Abstract: In this paper, we present a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic dataset generated from diffusion models. Specifically, we integrate an instance-level grounding head into a pre-trained, generative diffusion model, to augment it with the ability of localising instances in the generated images. The grounding head is trained to align the text embedding of category names with the regional visual feature of the diffusion model, using supervision from an off-the-shelf object detector, and a novel self-training scheme on (novel) categories not covered by the detector. We conduct thorough experiments to show that, this enhanced version of diffusion model, termed as InstaGen, can serve as a data synthesizer, to enhance object detectors by training on its generated samples, demonstrating superior performance over existing state-of-the-art methods in open-vocabulary (+4.5 AP) and data-sparse (+1.2 to 5.2 AP) scenarios. Project page with code: https://fcjian.github.io/InstaGen.
Authors: Shivanand Venkanna Sheshappanavar, Tejas Anvekar, Shivanand Kundargi, Yufan Wang, Chandra Kambhamettu
Abstract: Fine-grained grocery object recognition is an important computer vision problem with broad applications in automatic checkout, in-store robotic navigation, and assistive technologies for the visually impaired. Existing datasets on groceries are mainly 2D images. Models trained on these datasets are limited to learning features from the regular 2D grids. While portable 3D sensors such as Kinect were commonly available for mobile phones, sensors such as LiDAR and TrueDepth, have recently been integrated into mobile phones. Despite the availability of mobile 3D sensors, there are currently no dedicated real-world large-scale benchmark 3D datasets for grocery. In addition, existing 3D datasets lack fine-grained grocery categories and have limited training samples. Furthermore, collecting data by going around the object versus the traditional photo capture makes data collection cumbersome. Thus, we introduce a large-scale grocery dataset called 3DGrocery100. It constitutes 100 classes, with a total of 87,898 3D point clouds created from 10,755 RGB-D single-view images. We benchmark our dataset on six recent state-of-the-art 3D point cloud classification models. Additionally, we also benchmark the dataset on few-shot and continual learning point cloud classification tasks. Project Page: https://bigdatavision.org/3DGrocery100/.
Authors: Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Enkaer Xieerke, Jen-Shiun Chiang
Abstract: Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first and prepare for it based on the analysis of the radiologist. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection as computer-assisted diagnosis (CAD). In 2023, Ultralytics presented the latest version of the YOLO models, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the hottest methods to improve the model performance. This research work proposes YOLOv8-AM, which incorporates the attention mechanism into the original YOLOv8 architecture. Specifically, we respectively employ four attention modules, Convolutional Block Attention Module (CBAM), Global Attention Mechanism (GAM), Efficient Channel Attention (ECA), and Shuffle Attention (SA), to design the improved models and train them on GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP 50) of the YOLOv8-AM model based on ResBlock + CBAM (ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. Conversely, YOLOv8-AM model incorporating GAM obtains the mAP 50 value of 64.2%, which is not a satisfactory enhancement. Therefore, we combine ResBlock and GAM, introducing ResGAM to design another new YOLOv8-AM model, whose mAP 50 value is increased to 65.0%. The implementation code for this study is available on GitHub at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
URLs: https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
Authors: Wenzhao Zheng, Ruiqi Song, Xianda Guo, Chenming Zhang, Long Chen
Abstract: Directly producing planning results from raw sensors has been a long-desired solution for autonomous driving and has attracted increasing attention recently. Most existing end-to-end autonomous driving methods factorize this problem into perception, motion prediction, and planning. However, we argue that the conventional progressive pipeline still cannot comprehensively model the entire traffic evolution process, e.g., the future interaction between the ego car and other traffic participants and the structural trajectory prior. In this paper, we explore a new paradigm for end-to-end autonomous driving, where the key is to predict how the ego car and the surroundings evolve given past scenes. We propose GenAD, a generative framework that casts autonomous driving into a generative modeling problem. We propose an instance-centric scene tokenizer that first transforms the surrounding scenes into map-aware instance tokens. We then employ a variational autoencoder to learn the future trajectory distribution in a structural latent space for trajectory prior modeling. We further adopt a temporal model to capture the agent and ego movements in the latent space to generate more effective future trajectories. GenAD finally simultaneously performs motion prediction and planning by sampling distributions in the learned structural latent space conditioned on the instance tokens and using the learned temporal model to generate futures. Extensive experiments on the widely used nuScenes benchmark show that the proposed GenAD achieves state-of-the-art performance on vision-centric end-to-end autonomous driving with high efficiency. Code: https://github.com/wzzheng/GenAD.
Authors: Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, Jiang Bian
Abstract: Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video editing from image editing, is underexplored. In this work, we present UniEdit, a tuning-free framework that supports both video motion and appearance editing by harnessing the power of a pre-trained text-to-video generator within an inversion-then-generation framework. To realize motion editing while preserving source video content, based on the insights that temporal and spatial self-attention layers encode inter-frame and intra-frame dependency respectively, we introduce auxiliary motion-reference and reconstruction branches to produce text-guided motion and source features respectively. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers. Extensive experiments demonstrate that UniEdit covers video motion editing and various appearance editing scenarios, and surpasses the state-of-the-art methods. Our code will be publicly available.
Authors: Lingji Chen
Abstract: Conventional tracking paradigm takes in instantaneous measurements such as range and bearing, and produces object tracks across time. In applications such as autonomous driving, lidar measurements in the form of point clouds are usually passed through a "virtual sensor" realized by a deep learning model, to produce "measurements" such as bounding boxes, which are in turn ingested by a tracking module to produce object tracks. Very often multiple lidar sweeps are accumulated in a buffer to merge and become the input to the virtual sensor. We argue in this paper that such an input already contains temporal information, and therefore the virtual sensor output should also contain temporal information, not just instantaneous values for the time corresponding to the end of the buffer. In particular, we present the deep learning model called MULti-Sweep PAired Detector (MULSPAD) that produces, for each detected object, a pair of bounding boxes at both the end time and the beginning time of the input buffer. This is achieved with fairly straightforward changes in commonly used lidar detection models, and with only marginal extra processing, but the resulting symmetry is satisfying. Such paired detections make it possible not only to construct rudimentary trackers fairly easily, but also to construct more sophisticated trackers that can exploit the extra information conveyed by the pair and be robust to choices of motion models and object birth/death models. We have conducted preliminary training and experimentation using Waymo Open Dataset, which shows the efficacy of our proposed method.
Authors: Wenhao Tang, Fengtao Zhou, Sheng Huang, Xiang Zhu, Yi Zhang, Bo Liu
Abstract: Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks, limiting its adaptability and performance. To address this issue, we propose a Re-embedded Regional Transformer (R$^2$T) for re-embedding the instance features online, which captures fine-grained local features and establishes connections across different regions. Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R$^2$T is tailored to re-embed instance features online. It serves as a portable module that can seamlessly integrate into mainstream MIL models. Extensive experimental results on common computational pathology tasks validate that: 1) feature re-embedding improves the performance of MIL models based on ResNet-50 features to the level of foundation model features, and further enhances the performance of foundation model features; 2) the R$^2$T can introduce more significant performance improvements to various MIL models; 3) R$^2$T-MIL, as an R$^2$T-enhanced AB-MIL, outperforms other latest methods by a large margin.The code is available at: https://github.com/DearCaat/RRT-MIL.
Authors: Cidan Shi, Lihuang Fang, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
Abstract: In real-world environments, outdoor imaging systems are often affected by disturbances such as rain degradation. Especially, in nighttime driving scenes, insufficient and uneven lighting shrouds the scenes in darkness, resulting degradation of both the image quality and visibility. Particularly, in the field of autonomous driving, the visual perception ability of RGB sensors experiences a sharp decline in such harsh scenarios. Additionally, driving assistance systems suffer from reduced capabilities in capturing and discerning the surrounding environment, posing a threat to driving safety. Single-view information captured by single-modal sensors cannot comprehensively depict the entire scene. To address these challenges, we developed an image de-raining framework tailored for rainy nighttime driving scenes. It aims to remove rain artifacts, enrich scene representation, and restore useful information. Specifically, we introduce cooperative learning between visible and infrared images captured by different sensors. By cross-view fusion of these multi-source data, the scene within the images gains richer texture details and enhanced contrast. We constructed an information cleaning module called CleanNet as the first stage of our framework. Moreover, we designed an information fusion module called FusionNet as the second stage to fuse the clean visible images with infrared images. Using this stage-by-stage learning strategy, we obtain de-rained fusion images with higher quality and better visual perception. Extensive experiments demonstrate the effectiveness of our proposed Cross-View Cooperative Learning (CVCL) in adverse driving scenarios in low-light rainy environments. The proposed approach addresses the gap in the utilization of existing rain removal algorithms in specific low-light conditions.
Authors: Ziying Pan, Kun Wang, Gang Li, Feihong He, Xiwang Li, Yongxuan Lai
Abstract: The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and reduces storage overhead by only fine-tuning tiered class embedder, bias terms, and normalization layers' parameters. To further improve the image generation quality of fine-grained categories, we propose a novel sampling method for fine-grained image generation, which utilizes superclass-conditioned guidance, specifically tailored for fine-grained categories, to replace the conventional classifier-free guidance sampling. Compared to full fine-tuning, FineDiffusion achieves a remarkable 1.56x training speed-up and requires storing merely 1.77% of the total model parameters, while achieving state-of-the-art FID of 9.776 on image generation of 10,000 classes. Extensive qualitative and quantitative experiments demonstrate the superiority of our method compared to other parameter-efficient fine-tuning methods. The code and more generated results are available at our project website: https://finediffusion.github.io/.
Authors: Yuhao Liu, Zhanghan Ke, Fang Liu, Nanxuan Zhao, Rynson W. H. Lau
Abstract: Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle with handling diverse low-level tasks that require details preservation. To overcome this limitation, we present a new Diff-Plugin framework to enable a single pre-trained diffusion model to generate high-fidelity results across a variety of low-level tasks. Specifically, we first propose a lightweight Task-Plugin module with a dual branch design to provide task-specific priors, guiding the diffusion process in preserving image content. We then propose a Plugin-Selector that can automatically select different Task-Plugins based on the text instruction, allowing users to edit images by indicating multiple low-level tasks with natural language. We conduct extensive experiments on 8 low-level vision tasks. The results demonstrate the superiority of Diff-Plugin over existing methods, particularly in real-world scenarios. Our ablations further validate that Diff-Plugin is stable, schedulable, and supports robust training across different dataset sizes.
Authors: Mahmoud Afifi, Zhenhua Hu, Liang Liang
Abstract: High dynamic range (HDR) imaging involves capturing a series of frames of the same scene, each with different exposure settings, to broaden the dynamic range of light. This can be achieved through burst capturing or using staggered HDR sensors that capture long and short exposures simultaneously in the camera image signal processor (ISP). Within camera ISP pipeline, illuminant estimation is a crucial step aiming to estimate the color of the global illuminant in the scene. This estimation is used in camera ISP white-balance module to remove undesirable color cast in the final image. Despite the multiple frames captured in the HDR pipeline, conventional illuminant estimation methods often rely only on a single frame of the scene. In this paper, we explore leveraging information from frames captured with different exposure times. Specifically, we introduce a simple feature extracted from dual-exposure images to guide illuminant estimators, referred to as the dual-exposure feature (DEF). To validate the efficiency of DEF, we employed two illuminant estimators using the proposed DEF: 1) a multilayer perceptron network (MLP), referred to as exposure-based MLP (EMLP), and 2) a modified version of the convolutional color constancy (CCC) to integrate our DEF, that we call ECCC. Both EMLP and ECCC achieve promising results, in some cases surpassing prior methods that require hundreds of thousands or millions of parameters, with only a few hundred parameters for EMLP and a few thousand parameters for ECCC.
Authors: Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Nguyen
Abstract: CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. Therefore, they perform poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scientific names of birds). For fine-grained classification, we propose PEEB - an explainable and editable classifier to (1) express the class name into a set of text descriptors that describe the visual parts of that class; and (2) match the embeddings of the detected parts to their textual descriptors in each class to compute a logit score for classification. In a zero-shot setting where the class names are unknown, PEEB outperforms CLIP by a huge margin (~10x in top-1 accuracy). Compared to part-based classifiers, PEEB is not only the state-of-the-art (SOTA) on the supervised-learning setting (88.80% and 92.20% accuracy on CUB-200 and Dogs-120, respectively) but also the first to enable users to edit the text descriptors to form a new classifier without any re-training. Compared to concept bottleneck models, PEEB is also the SOTA in both zero-shot and supervised-learning settings.
Authors: Jiahui Zhang, Fangneng Zhan, Muyu Xu, Shijian Lu, Eric Xing
Abstract: 3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
Authors: Licheng Zhong, Hong-Xing Yu, Jiajun Wu, Yunzhu Li
Abstract: Reconstructing and simulating elastic objects from visual observations is crucial for applications in computer vision and robotics. Existing methods, such as 3D Gaussians, model 3D appearance and geometry, but lack the ability to estimate physical properties for objects and simulate them. The core challenge lies in integrating an expressive yet efficient physical dynamics model. We propose Spring-Gaus, a 3D physical object representation for reconstructing and simulating elastic objects from videos of the object from multiple viewpoints. In particular, we develop and integrate a 3D Spring-Mass model into 3D Gaussian kernels, enabling the reconstruction of the visual appearance, shape, and physical dynamics of the object. Our approach enables future prediction and simulation under various initial states and environmental properties. We evaluate Spring-Gaus on both synthetic and real-world datasets, demonstrating accurate reconstruction and simulation of elastic objects. Project page: https://zlicheng.com/spring_gaus.
Authors: Xiaoben Li, Mancheng Meng, Ziyan Wu, Terrence Chen, Fan Yang, Dinggang Shen
Abstract: Human mesh recovery from arbitrary multi-view images involves two characteristics: the arbitrary camera poses and arbitrary number of camera views. Because of the variability, designing a unified framework to tackle this task is challenging. The challenges can be summarized as the dilemma of being able to simultaneously estimate arbitrary camera poses and recover human mesh from arbitrary multi-view images while maintaining flexibility. To solve this dilemma, we propose a divide and conquer framework for Unified Human Mesh Recovery (U-HMR) from arbitrary multi-view images. In particular, U-HMR consists of a decoupled structure and two main components: camera and body decoupling (CBD), camera pose estimation (CPE), and arbitrary view fusion (AVF). As camera poses and human body mesh are independent of each other, CBD splits the estimation of them into two sub-tasks for two individual sub-networks (ie, CPE and AVF) to handle respectively, thus the two sub-tasks are disentangled. In CPE, since each camera pose is unrelated to the others, we adopt a shared MLP to process all views in a parallel way. In AVF, in order to fuse multi-view information and make the fusion operation independent of the number of views, we introduce a transformer decoder with a SMPL parameters query token to extract cross-view features for mesh recovery. To demonstrate the efficacy and flexibility of the proposed framework and effect of each component, we conduct extensive experiments on three public datasets: Human3.6M, MPI-INF-3DHP, and TotalCapture.
Authors: Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Jian Wu, Philip Torr
Abstract: We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. Specifically, the prompts in the toolkit are designed to guide the MLLM to focus on regional information (e.g., zooming in), read coordinates according to measure standards (e.g., overlaying rulers and compasses), and infer from the contextual information (e.g., overlaying scene graphs). Building upon these tools, the new detection chain-of-thought can automatically decompose the task into simple subtasks, diagnose the predictions, and plan for progressive box refinements. The effectiveness of our framework is demonstrated across a spectrum of detection tasks, especially hard cases. Compared to existing state-of-the-art methods, GPT-4V with our DetToolChain improves state-of-the-art object detectors by +21.5% AP50 on MS COCO Novel class set for open-vocabulary detection, +24.23% Acc on RefCOCO val set for zero-shot referring expression comprehension, +14.5% AP on D-cube describe object detection FULL setting.
Authors: Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem
Abstract: We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that increasing pretraining data diversity enhances SSL performance, albeit only when the distribution distance to the downstream data is minimal. Notably, even with an exceptionally large pretraining data diversity achieved through methods like web crawling or diffusion-generated data, among other ways, the distribution shift remains a challenge. Our experiments are comprehensive with seven SSL methods using large-scale datasets such as ImageNet and YFCC100M amounting to over 200 GPU days. Code and trained models will be available at https://github.com/hammoudhasan/DiversitySSL .
Authors: Siyuan Liang, Wei Wang, Ruoyu Chen, Aishan Liu, Boxi Wu, Ee-Chien Chang, Xiaochun Cao, Dacheng Tao
Abstract: With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, where crucial factors (e.g., data distribution, objective) that influence model learning are often changing. The dynamic and intricate nature of the open environment poses novel and formidable challenges to object detectors. Unfortunately, current research on object detectors in open environments lacks a comprehensive analysis of their distinctive characteristics, challenges, and corresponding solutions, which hinders their secure deployment in critical real-world scenarios. This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments. We initially identified limitations of key structural components within the existing detection pipeline and propose the open environment object detector challenge framework that includes four quadrants (i.e., out-of-domain, out-of-category, robust learning, and incremental learning) based on the dimensions of the data / target changes. For each quadrant of challenges in the proposed framework, we present a detailed description and systematic analysis of the overarching goals and core difficulties, systematically review the corresponding solutions, and benchmark their performance over multiple widely adopted datasets. In addition, we engage in a discussion of open problems and potential avenues for future research. This paper aims to provide a fresh, comprehensive, and systematic understanding of the challenges and solutions associated with open-environment object detectors, thus catalyzing the development of more solid applications in real-world scenarios. A project related to this survey can be found at https://github.com/LiangSiyuan21/OEOD_Survey.
Authors: Tianwei Zhang, Dong Wei, Mengmeng Zhu, Shi Gu, Yefeng Zheng
Abstract: Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.
Authors: Yang Luo, Xiqing Guo, Hao Li
Abstract: Due to the complementary nature of visible light and thermal infrared modalities, object tracking based on the fusion of visible light images and thermal images (referred to as RGB-T tracking) has received increasing attention from researchers in recent years. How to achieve more comprehensive fusion of information from the two modalities at a lower cost has been an issue that researchers have been exploring. Inspired by visual prompt learning, we designed a novel two-stream RGB-T tracking architecture based on cross-modal mutual prompt learning, and used this model as a teacher to guide a one-stream student model for rapid learning through knowledge distillation techniques. Extensive experiments have shown that, compared to similar RGB-T trackers, our designed teacher model achieved the highest precision rate, while the student model, with comparable precision rate to the teacher model, realized an inference speed more than three times faster than the teacher model.(Codes will be available if accepted.)
Authors: Yunpeng Zhang, Deheng Qian, Ding Li, Yifeng Pan, Yong Chen, Zhenbao Liang, Zhiyao Zhang, Shurui Zhang, Hongxu Li, Maolei Fu, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du
Abstract: Modeling complicated interactions among the ego-vehicle, road agents, and map elements has been a crucial part for safety-critical autonomous driving. Previous works on end-to-end autonomous driving rely on the attention mechanism for handling heterogeneous interactions, which fails to capture the geometric priors and is also computationally intensive. In this paper, we propose the Interaction Scene Graph (ISG) as a unified method to model the interactions among the ego-vehicle, road agents, and map elements. With the representation of the ISG, the driving agents aggregate essential information from the most influential elements, including the road agents with potential collisions and the map elements to follow. Since a mass of unnecessary interactions are omitted, the more efficient scene-graph-based framework is able to focus on indispensable connections and leads to better performance. We evaluate the proposed method for end-to-end autonomous driving on the nuScenes dataset. Compared with strong baselines, our method significantly outperforms in the full-stack driving tasks, including perception, prediction, and planning. Code will be released at https://github.com/zhangyp15/GraphAD.
Authors: Kyotaro Tokoro, Kazutoshi Akita, Norimichi Ukita
Abstract: While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In addition, it is difficult to perfectly align the burst LR images, making the SR image more blurry. Since such blurry images are perceptually degraded, we aim to reconstruct the sharp high-fidelity boundaries. Such high-fidelity images can be reconstructed by diffusion models. However, prior SR methods using the diffusion model are not properly optimized for the burst SR task. Specifically, the reverse process starting from a random sample is not optimized for image enhancement and restoration methods, including burst SR. In our proposed method, on the other hand, burst LR features are used to reconstruct the initial burst SR image that is fed into an intermediate step in the diffusion model. This reverse process from the intermediate step 1) skips diffusion steps for reconstructing the global structure of the image and 2) focuses on steps for refining detailed textures. Our experimental results demonstrate that our method can improve the scores of the perceptual quality metrics. Code: https://github.com/placerkyo/BSRD
Authors: Yan Luo, Min Shi, Muhammad Osama Khan, Muhammad Muneeb Afzal, Hao Huang, Shuaihang Yuan, Yu Tian, Luo Song, Ava Kouhana, Tobias Elze, Yi Fang, Mengyu Wang
Abstract: Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions. Although fairness has been investigated in the vision-only domain, the fairness of medical vision-language (VL) models remains unexplored due to the scarcity of medical VL datasets for studying fairness. To bridge this research gap, we introduce the first fair vision-language medical dataset Harvard-FairVLMed that provides detailed demographic attributes, ground-truth labels, and clinical notes to facilitate an in-depth examination of fairness within VL foundation models. Using Harvard-FairVLMed, we conduct a comprehensive fairness analysis of two widely-used VL models (CLIP and BLIP2), pre-trained on both natural and medical domains, across four different protected attributes. Our results highlight significant biases in all VL models, with Asian, Male, Non-Hispanic, and Spanish being the preferred subgroups across the protected attributes of race, gender, ethnicity, and language, respectively. In order to alleviate these biases, we propose FairCLIP, an optimal-transport-based approach that achieves a favorable trade-off between performance and fairness by reducing the Sinkhorn distance between the overall sample distribution and the distributions corresponding to each demographic group. As the first VL dataset of its kind, Harvard-FairVLMed holds the potential to catalyze advancements in the development of machine learning models that are both ethically aware and clinically effective. Our dataset and code are available at https://ophai.hms.harvard.edu/datasets/harvard-fairvlmed10k.
URLs: https://ophai.hms.harvard.edu/datasets/harvard-fairvlmed10k.
Authors: Robik Shrestha, Yang Zou, Qiuyu Chen, Zhiheng Li, Yusheng Xie, Siqi Deng
Abstract: Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness, FairRAG applies simple-yet-effective debiasing strategies, providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outperforms existing methods in terms of demographic diversity, image-text alignment, and image fidelity while incurring minimal computational overhead during inference.
Authors: Zelin Zhao, Fenglei Fan, Wenlong Liao, Junchi Yan
Abstract: Many contemporary studies utilize grid-based models for neural field representation, but a systematic analysis of grid-based models is still missing, hindering the improvement of those models. Therefore, this paper introduces a theoretical framework for grid-based models. This framework points out that these models' approximation and generalization behaviors are determined by grid tangent kernels (GTK), which are intrinsic properties of grid-based models. The proposed framework facilitates a consistent and systematic analysis of diverse grid-based models. Furthermore, the introduced framework motivates the development of a novel grid-based model named the Multiplicative Fourier Adaptive Grid (MulFAGrid). The numerical analysis demonstrates that MulFAGrid exhibits a lower generalization bound than its predecessors, indicating its robust generalization performance. Empirical studies reveal that MulFAGrid achieves state-of-the-art performance in various tasks, including 2D image fitting, 3D signed distance field (SDF) reconstruction, and novel view synthesis, demonstrating superior representation ability. The project website is available at https://sites.google.com/view/cvpr24-2034-submission/home.
URLs: https://sites.google.com/view/cvpr24-2034-submission/home.
Authors: Tongkun Su, Jun Li, Xi Zhang, Haibo Jin, Hao Chen, Qiong Wang, Faqin Lv, Baoliang Zhao, Yin Hu
Abstract: Multimodal pre-training demonstrates its potential in the medical domain, which learns medical visual representations from paired medical reports. However, many pre-training tasks require extra annotations from clinicians, and most of them fail to explicitly guide the model to learn the desired features of different pathologies. To the best of our knowledge, we are the first to utilize Visual Question Answering (VQA) for multimodal pre-training to guide the framework focusing on targeted pathological features. In this work, we leverage descriptions in medical reports to design multi-granular question-answer pairs associated with different diseases, which assist the framework in pre-training without requiring extra annotations from experts. We also propose a novel pre-training framework with a quasi-textual feature transformer, a module designed to transform visual features into a quasi-textual space closer to the textual domain via a contrastive learning strategy. This narrows the vision-language gap and facilitates modality alignment. Our framework is applied to four downstream tasks: report generation, classification, segmentation, and detection across five datasets. Extensive experiments demonstrate the superiority of our framework compared to other state-of-the-art methods. Our code will be released upon acceptance.
Authors: Pancheng Zhao, Peng Xu, Pengda Qin, Deng-Ping Fan, Zhicheng Zhang, Guoli Jia, Bowen Zhou, Jufeng Yang
Abstract: Camouflaged vision perception is an important vision task with numerous practical applications. Due to the expensive collection and labeling costs, this community struggles with a major bottleneck that the species category of its datasets is limited to a small number of object species. However, the existing camouflaged generation methods require specifying the background manually, thus failing to extend the camouflaged sample diversity in a low-cost manner. In this paper, we propose a Latent Background Knowledge Retrieval-Augmented Diffusion (LAKE-RED) for camouflaged image generation. To our knowledge, our contributions mainly include: (1) For the first time, we propose a camouflaged generation paradigm that does not need to receive any background inputs. (2) Our LAKE-RED is the first knowledge retrieval-augmented method with interpretability for camouflaged generation, in which we propose an idea that knowledge retrieval and reasoning enhancement are separated explicitly, to alleviate the task-specific challenges. Moreover, our method is not restricted to specific foreground targets or backgrounds, offering a potential for extending camouflaged vision perception to more diverse domains. (3) Experimental results demonstrate that our method outperforms the existing approaches, generating more realistic camouflage images.
Authors: Chenyi Zhang, Yihan Hu, Henghui Ding, Humphrey Shi, Yao Zhao, Yunchao Wei
Abstract: Despite significant advancements in image matting, existing models heavily depend on manually-drawn trimaps for accurate results in natural image scenarios. However, the process of obtaining trimaps is time-consuming, lacking user-friendliness and device compatibility. This reliance greatly limits the practical application of all trimap-based matting methods. To address this issue, we introduce Click2Trimap, an interactive model capable of predicting high-quality trimaps and alpha mattes with minimal user click inputs. Through analyzing real users' behavioral logic and characteristics of trimaps, we successfully propose a powerful iterative three-class training strategy and a dedicated simulation function, making Click2Trimap exhibit versatility across various scenarios. Quantitative and qualitative assessments on synthetic and real-world matting datasets demonstrate Click2Trimap's superior performance compared to all existing trimap-free matting methods. Especially, in the user study, Click2Trimap achieves high-quality trimap and matting predictions in just an average of 5 seconds per image, demonstrating its substantial practical value in real-world applications.
Authors: Wenxiao Cai, Xinyue Lei, Xinyu He, Junming Leo Chen, Yangang Wang
Abstract: We present Knowledge NeRF to synthesize novel views for dynamic scenes. Reconstructing dynamic 3D scenes from few sparse views and rendering them from arbitrary perspectives is a challenging problem with applications in various domains. Previous dynamic NeRF methods learn the deformation of articulated objects from monocular videos. However, qualities of their reconstructed scenes are limited. To clearly reconstruct dynamic scenes, we propose a new framework by considering two frames at a time.We pretrain a NeRF model for an articulated object.When articulated objects moves, Knowledge NeRF learns to generate novel views at the new state by incorporating past knowledge in the pretrained NeRF model with minimal observations in the present state. We propose a projection module to adapt NeRF for dynamic scenes, learning the correspondence between pretrained knowledge base and current states. Experimental results demonstrate the effectiveness of our method in reconstructing dynamic 3D scenes with 5 input images in one state. Knowledge NeRF is a new pipeline and promising solution for novel view synthesis in dynamic articulated objects. The data and implementation are publicly available at https://github.com/RussRobin/Knowledge_NeRF.
Authors: Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou
Abstract: In recent years, Vision Transformer-based applications to low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of images utilizing information from non-local areas. In the domain of super-resolution, Swin-transformer-based approaches have become mainstream due to their capacity to capture global spatial information and their shifting-window attention mechanism that facilitates the interchange of information between different windows. Many researchers have enhanced image quality and network efficiency by expanding the receptive field or designing complex networks, yielding commendable results. However, we observed that spatial information tends to diminish during the forward propagation process due to increased depth, leading to a loss of spatial information and, consequently, limiting the model's potential. To address this, we propose the Dense-residual-connected Transformer (DRCT), aimed at mitigating the loss of spatial information through dense-residual connections between layers, thereby unleashing the model's potential and enhancing performance. Experiment results indicate that our approach is not only straightforward but also achieves remarkable efficiency, surpassing state-of-the-art methods and performing commendably at NTIRE2024.
Authors: Rongjie Li, Songyang Zhang, Dahua Lin, Kai Chen, Xuming He
Abstract: Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks. Despite recent advancements, existing methods struggle to generate scene graphs with novel visual relation concepts. To address this challenge, we introduce a new open-vocabulary SGG framework based on sequence generation. Our framework leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm. Specifically, we generate scene graph sequences via image-to-text generation with VLM and then construct scene graphs from these sequences. By doing so, we harness the strong capabilities of VLM for open-vocabulary SGG and seamlessly integrate explicit relational modeling for enhancing the VL tasks. Experimental results demonstrate that our design not only achieves superior performance with an open vocabulary but also enhances downstream vision-language task performance through explicit relation modeling knowledge.
Authors: Heemin Yang, Jaesung Rim, Seungyong Lee, Seung-Hwan Baek, Sunghyun Cho
Abstract: In this paper, we present GyroDeblurNet, a novel single image deblurring method that utilizes a gyro sensor to effectively resolve the ill-posedness of image deblurring. The gyro sensor provides valuable information about camera motion during exposure time that can significantly improve deblurring quality. However, effectively exploiting real-world gyro data is challenging due to significant errors from various sources including sensor noise, the disparity between the positions of a camera module and a gyro sensor, the absence of translational motion information, and moving objects whose motions cannot be captured by a gyro sensor. To handle gyro error, GyroDeblurNet is equipped with two novel neural network blocks: a gyro refinement block and a gyro deblurring block. The gyro refinement block refines the error-ridden gyro data using the blur information from the input image. On the other hand, the gyro deblurring block removes blur from the input image using the refined gyro data and further compensates for gyro error by leveraging the blur information from the input image. For training a neural network with erroneous gyro data, we propose a training strategy based on the curriculum learning. We also introduce a novel gyro data embedding scheme to represent real-world intricate camera shakes. Finally, we present a synthetic dataset and a real dataset for the training and evaluation of gyro-based single image deblurring. Our experiments demonstrate that our approach achieves state-of-the-art deblurring quality by effectively utilizing erroneous gyro data.
Authors: Sheikh Musa Kaleem, Tufail Rouf, Gousia Habib, Tausifa jan Saleem, Brejesh Lall
Abstract: Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from significant drawbacks when deployed in resource-constrained environments due to their large model size and high complexity. Knowledge Distillation is one of the prominent solutions to overcome this challenge. This review paper examines the current state of research on knowledge distillation, a technique for compressing complex models into smaller and simpler ones. The paper provides an overview of the major principles and techniques associated with knowledge distillation and reviews the applications of knowledge distillation in the domain of computer vision. The review focuses on the benefits of knowledge distillation, as well as the problems that must be overcome to improve its effectiveness.
Authors: Hao Chen, Yuqi Hou, Chenyuan Qu, Irene Testini, Xiaohan Hong, Jianbo Jiao
Abstract: Human perception of the world is shaped by a multitude of viewpoints and modalities. While many existing datasets focus on scene understanding from a certain perspective (e.g. egocentric or third-person views), our dataset offers a panoptic perspective (i.e. multiple viewpoints with multiple data modalities). Specifically, we encapsulate third-person panoramic and front views, as well as egocentric monocular/binocular views with rich modalities including video, multi-channel audio, directional binaural delay, location data and textual scene descriptions within each scene captured, presenting comprehensive observation of the world. Figure 1 offers a glimpse of all 28 scene categories of our 360+x dataset. To the best of our knowledge, this is the first database that covers multiple viewpoints with multiple data modalities to mimic how daily information is accessed in the real world. Through our benchmark analysis, we presented 5 different scene understanding tasks on the proposed 360+x dataset to evaluate the impact and benefit of each data modality and perspective in panoptic scene understanding. We hope this unique dataset could broaden the scope of comprehensive scene understanding and encourage the community to approach these problems from more diverse perspectives.
Authors: Yang Liu, He Guan, Chuanchen Luo, Lue Fan, Junran Peng, Zhaoxiang Zhang
Abstract: The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time across various scales remains challenging. This paper introduces CityGaussian (CityGS), which employs a novel divide-and-conquer training approach and Level-of-Detail (LoD) strategy for efficient large-scale 3DGS training and rendering. Specifically, the global scene prior and adaptive training data selection enables efficient training and seamless fusion. Based on fused Gaussian primitives, we generate different detail levels through compression, and realize fast rendering across various scales through the proposed block-wise detail levels selection and aggregation strategy. Extensive experimental results on large-scale scenes demonstrate that our approach attains state-of-theart rendering quality, enabling consistent real-time rendering of largescale scenes across vastly different scales. Our project page is available at https://dekuliutesla.github.io/citygs/.
Authors: Ming Xu, Stephen Gould
Abstract: We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem, we are able to decode a temporally consistent segmentation from a noisy affinity/matching cost matrix between video frames and action classes. Unlike previous approaches, our method does not require knowing the action order for a video to attain temporal consistency. Furthermore, our resulting (fused) Gromov-Wasserstein problem can be efficiently solved on GPUs using a few iterations of projected mirror descent. We demonstrate the effectiveness of our method in an unsupervised learning setting, where our method is used to generate pseudo-labels for self-training. We evaluate our segmentation approach and unsupervised learning pipeline on the Breakfast, 50-Salads, YouTube Instructions and Desktop Assembly datasets, yielding state-of-the-art results for the unsupervised video action segmentation task.
Authors: Quanwei Liu, Yanni Dong, Tao Huang, Lefei Zhang, Bo Du
Abstract: Hyperspectral image (HSI) classification techniques have been intensively studied and a variety of models have been developed. However, these HSI classification models are confined to pocket models and unrealistic ways of datasets partitioning. The former limits the generalization performance of the model and the latter is partitioned leads to inflated model evaluation metrics, which results in plummeting model performance in the real world. Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap of HSI classification models between pocket models and standard vision backbones. We present a new HSI processing pipeline in conjunction with a range of data transformation and augmentation techniques that provide diverse data representations and realistic data partitioning. The proposed framework based on this pipeline is compatible with all kinds of backbones and can fully exploit labeled and unlabeled samples with expected training time. Furthermore, we design a new loss function, which can adaptively fuse the supervised loss and unsupervised loss, enhancing the learning performance. This proposed new classification paradigm shows great potentials in exploring for HSI classification technology. The code can be accessed at https://github.com/quanweiliu/KnowCL.
Authors: Wangguandong Zheng, Haifeng Xia, Rui Chen, Ming Shao, Siyu Xia, Zhengming Ding
Abstract: Recently, image-to-3D approaches have achieved significant results with a natural image as input. However, it is not always possible to access these enriched color input samples in practical applications, where only sketches are available. Existing sketch-to-3D researches suffer from limitations in broad applications due to the challenges of lacking color information and multi-view content. To overcome them, this paper proposes a novel generation paradigm Sketch3D to generate realistic 3D assets with shape aligned with the input sketch and color matching the textual description. Concretely, Sketch3D first instantiates the given sketch in the reference image through the shape-preserving generation process. Second, the reference image is leveraged to deduce a coarse 3D Gaussian prior, and multi-view style-consistent guidance images are generated based on the renderings of the 3D Gaussians. Finally, three strategies are designed to optimize 3D Gaussians, i.e., structural optimization via a distribution transfer mechanism, color optimization with a straightforward MSE loss and sketch similarity optimization with a CLIP-based geometric similarity loss. Extensive visual comparisons and quantitative analysis illustrate the advantage of our Sketch3D in generating realistic 3D assets while preserving consistency with the input.
Authors: Haoyang Ge, Qiao Feng, Hailong Jia, Xiongzheng Li, Xiangjun Yin, You Zhou, Jingyu Yang, Kun Li
Abstract: Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However, this task presents significant challenges due to the inherent ambiguity of the captured measurements and lacks effective methods for directly estimating human pose and shape from lensless data. In this paper, we propose the first end-to-end framework to recover 3D human poses and shapes from lensless measurements to our knowledge. We specifically design a multi-scale lensless feature decoder to decode the lensless measurements through the optically encoded mask for efficient feature extraction. We also propose a double-head auxiliary supervision mechanism to improve the estimation accuracy of human limb ends. Besides, we establish a lensless imaging system and verify the effectiveness of our method on various datasets acquired by our lensless imaging system.
Authors: Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdenour Hadid, Abdelmalik Taleb-Ahmed
Abstract: Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images. While this technological progress has captured significant interest, it has also raised concerns about the potential difficulty in distinguishing real images from their synthetic counterparts. This paper takes inspiration from the potent convergence capabilities between vision and language, coupled with the zero-shot nature of vision-language models (VLMs). We introduce an innovative method called Bi-LORA that leverages VLMs, combined with low-rank adaptation (LORA) tuning techniques, to enhance the precision of synthetic image detection for unseen model-generated images. The pivotal conceptual shift in our methodology revolves around reframing binary classification as an image captioning task, leveraging the distinctive capabilities of cutting-edge VLM, notably bootstrapping language image pre-training (BLIP2). Rigorous and comprehensive experiments are conducted to validate the effectiveness of our proposed approach, particularly in detecting unseen diffusion-generated images from unknown diffusion-based generative models during training, showcasing robustness to noise, and demonstrating generalization capabilities to GANs. The obtained results showcase an impressive average accuracy of 93.41% in synthetic image detection on unseen generation models. The code and models associated with this research can be publicly accessed at https://github.com/Mamadou-Keita/VLM-DETECT.
Authors: Ryan Donghan Kwon, Gangjoo Robin Nam, Jisoo Tak, Junseob Shin, Hyerin Cha, Yeom Hyeok, Seung Won Lee
Abstract: This study presents an advanced Convolutional Neural Network (CNN) architecture for ship classification from optical satellite imagery, significantly enhancing performance through the integration of the Convolutional Block Attention Module (CBAM) and additional architectural innovations. Building upon the foundational ResNet50 model, we first incorporated a standard CBAM to direct the model's focus towards more informative features, achieving an accuracy of 87% compared to the baseline ResNet50's 85%. Further augmentations involved multi-scale feature integration, depthwise separable convolutions, and dilated convolutions, culminating in the Enhanced ResNet Model with Improved CBAM. This model demonstrated a remarkable accuracy of 95%, with precision, recall, and f1-scores all witnessing substantial improvements across various ship classes. The bulk carrier and oil tanker classes, in particular, showcased nearly perfect precision and recall rates, underscoring the model's enhanced capability in accurately identifying and classifying ships. Attention heatmap analyses further validated the improved model's efficacy, revealing a more focused attention on relevant ship features, regardless of background complexities. These findings underscore the potential of integrating attention mechanisms and architectural innovations in CNNs for high-resolution satellite imagery classification. The study navigates through the challenges of class imbalance and computational costs, proposing future directions towards scalability and adaptability in new or rare ship type recognition. This research lays a groundwork for the application of advanced deep learning techniques in the domain of remote sensing, offering insights into scalable and efficient satellite image classification.
Authors: Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
Abstract: Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate weight checkpoints are not fully utilized and only the last converged checkpoint is used. In this work, we find that high-quality model weights often lie in a basin which cannot be reached by SGD but can be obtained by proper checkpoint averaging. Based on these observations, we propose LCSC, a simple but effective and efficient method to enhance the performance of DM and CM, by combining checkpoints along the training trajectory with coefficients deduced from evolutionary search. We demonstrate the value of LCSC through two use cases: $\textbf{(a) Reducing training cost.}$ With LCSC, we only need to train DM/CM with fewer number of iterations and/or lower batch sizes to obtain comparable sample quality with the fully trained model. For example, LCSC achieves considerable training speedups for CM (23$\times$ on CIFAR-10 and 15$\times$ on ImageNet-64). $\textbf{(b) Enhancing pre-trained models.}$ Assuming full training is already done, LCSC can further improve the generation quality or speed of the final converged models. For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10. Our code is available at https://github.com/imagination-research/LCSC.
Authors: Nafaa Nacereddine, Aicha Baya Goumeidane, Djemel Ziou
Abstract: An accurate detection of the centerlines of linear objects is a challenging topic in many sensitive real-world applications such X-ray imaging, remote sensing and lane marking detection in road traffic. Model-based approaches using Hough and Radon transforms are often used but, are not recommended for thick line detection, whereas approaches based on image derivatives need further step-by-step processing, making their efficiency dependent on each step outcomes. In this paper, we aim to detect linear structures found in images by considering the 3D representation of the image gray levels as a finite mixture model of statistical distribution. The latter, which we named linear anchored Gaussian distribution could be parametrized by a scale value ${\sigma}$ describing the linear structure thickness and a line equation, parametrized, in turn, by a radius ${\rho}$ and an orientation angle ${\theta}$, describing the linear structure centerline location. Expectation-Maximization (EM) algorithm is used for the mixture model parameter estimation, where a new paradigm, using the background subtraction for the likelihood function computation, is proposed. For the EM algorithm, two ${\theta}$ parameter initialization schemes are used: the first one is based on a random choice of the first component of ${\theta}$ vector, whereas the second is based on the image Hessian with a simultaneous computation of the mixture model components number. Experiments on real world images and synthetic images corrupted by blur and additive noise show the good performance of the proposed methods, where the algorithm using background subtraction and Hessian-based ${\theta}$ initialization provides an outstanding accuracy of the linear structure detection despite irregular image background and presence of blur and noise.
Authors: Longwei Li, Huajian Huang, Sai-Kit Yeung, Hui Cheng
Abstract: Photorealistic reconstruction relying on 3D Gaussian Splatting has shown promising potential in robotics. However, the current 3D Gaussian Splatting system only supports radiance field reconstruction using undistorted perspective images. In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction. Specifically, we conduct a theoretical analysis of spherical camera model derivatives in 3D Gaussian Splatting. According to the derivatives, we then implement a new GPU-accelerated omnidirectional rasterizer that directly splats 3D Gaussians onto the equirectangular screen space for omnidirectional image rendering. As a result, we realize differentiable optimization of the radiance field without the requirement of cube-map rectification or tangent-plane approximation. Extensive experiments conducted in egocentric and roaming scenarios demonstrate that our method achieves state-of-the-art reconstruction quality and high rendering speed using omnidirectional images. To benefit the research community, the code will be made publicly available once the paper is published.
Authors: Jiahang Li, Peng Yun, Qijun Chen, Rui Fan
Abstract: Data-fusion networks have shown significant promise for RGB-thermal scene parsing. However, the majority of existing studies have relied on symmetric duplex encoders for heterogeneous feature extraction and fusion, paying inadequate attention to the inherent differences between RGB and thermal modalities. Recent progress in vision foundation models (VFMs) trained through self-supervision on vast amounts of unlabeled data has proven their ability to extract informative, general-purpose features. However, this potential has yet to be fully leveraged in the domain. In this study, we take one step toward this new research area by exploring a feasible strategy to fully exploit VFM features for RGB-thermal scene parsing. Specifically, we delve deeper into the unique characteristics of RGB and thermal modalities, thereby designing a hybrid, asymmetric encoder that incorporates both a VFM and a convolutional neural network. This design allows for more effective extraction of complementary heterogeneous features, which are subsequently fused in a dual-path, progressive manner. Moreover, we introduce an auxiliary task to further enrich the local semantics of the fused features, thereby improving the overall performance of RGB-thermal scene parsing. Our proposed HAPNet, equipped with all these components, demonstrates superior performance compared to all other state-of-the-art RGB-thermal scene parsing networks, achieving top ranks across three widely used public RGB-thermal scene parsing datasets. We believe this new paradigm has opened up new opportunities for future developments in data-fusion scene parsing approaches.
Authors: Zhongkai Wu, Ziyu Wan, Jing Zhang, Jing Liao, Dong Xu
Abstract: NeRF (Neural Radiance Fields) has demonstrated tremendous potential in novel view synthesis and 3D reconstruction, but its performance is sensitive to input image quality, which struggles to achieve high-fidelity rendering when provided with low-quality sparse input viewpoints. Previous methods for NeRF restoration are tailored for specific degradation type, ignoring the generality of restoration. To overcome this limitation, we propose a generic radiance fields restoration pipeline, named RaFE, which applies to various types of degradations, such as low resolution, blurriness, noise, compression artifacts, or their combinations. Our approach leverages the success of off-the-shelf 2D restoration methods to recover the multi-view images individually. Instead of reconstructing a blurred NeRF by averaging inconsistencies, we introduce a novel approach using Generative Adversarial Networks (GANs) for NeRF generation to better accommodate the geometric and appearance inconsistencies present in the multi-view images. Specifically, we adopt a two-level tri-plane architecture, where the coarse level remains fixed to represent the low-quality NeRF, and a fine-level residual tri-plane to be added to the coarse level is modeled as a distribution with GAN to capture potential variations in restoration. We validate RaFE on both synthetic and real cases for various restoration tasks, demonstrating superior performance in both quantitative and qualitative evaluations, surpassing other 3D restoration methods specific to single task. Please see our project website https://zkaiwu.github.io/RaFE-Project/.
Authors: Prasun C. Tripathi, Mohammod N. I. Suvon, Lawrence Schobs, Shuo Zhou, Samer Alabed, Andrew J. Swift, Haiping Lu
Abstract: Heart failure is a serious and life-threatening condition that can lead to elevated pressure in the left ventricle. Pulmonary Arterial Wedge Pressure (PAWP) is an important surrogate marker indicating high pressure in the left ventricle. PAWP is determined by Right Heart Catheterization (RHC) but it is an invasive procedure. A non-invasive method is useful in quickly identifying high-risk patients from a large population. In this work, we develop a tensor learning-based pipeline for identifying PAWP from multimodal cardiac Magnetic Resonance Imaging (MRI). This pipeline extracts spatial and temporal features from high-dimensional scans. For quality control, we incorporate an epistemic uncertainty-based binning strategy to identify poor-quality training samples. To improve the performance, we learn complementary information by integrating features from multimodal data: cardiac MRI with short-axis and four-chamber views, and Electronic Health Records. The experimental analysis on a large cohort of $1346$ subjects who underwent the RHC procedure for PAWP estimation indicates that the proposed pipeline has a diagnostic value and can produce promising performance with significant improvement over the baseline in clinical practice (i.e., $\Delta$AUC $=0.10$, $\Delta$Accuracy $=0.06$, and $\Delta$MCC $=0.39$). The decision curve analysis further confirms the clinical utility of our method.
Authors: Anqi Wang, Jiahua Dong, Lik-Hang Lee, Jiachuan Shen, Pan Hui
Abstract: 3D shape generation techniques leveraging deep learning have garnered significant interest from both the computer vision and architectural design communities, promising to enrich the content of the future metaverse. However, research on virtual architectural design remains limited, particularly regarding human-AI collaboration and deep learning-assisted design. We first illuminate the principles, generation techniques, and current literature of virtual architecture, focusing on challenges such as datasets, multimodality, design intuition, and generative frameworks. In our survey, we reviewed 187 related articles (80.7\% of articles published between 2018 and 2022) covering architectural research, virtual environments, and technical approaches. This survey investigates the latest approaches to 3D object generation with deep generative models (DGMs) and summarizes four characteristics of deep-learning generation approaches for virtual architecture. According to our analysis of the survey, we expound on four research agendas, including agency, communication, user consideration, and integrating tools, and highlight three important enablers of ubiquitous interaction with immersive systems in deep learning-assisted architectural generation. Our work contributes to fostering understanding between designers and deep learning techniques, broadening access to human-AI collaboration. We advocate for interdisciplinary efforts to address this timely research topic, facilitating content designing and generation in the metaverse.
Authors: Bo Li, Yasin Esfandiari, Mikkel N. Schmidt, Tommy S. Alstr{\o}m, Sebastian U. Stich
Abstract: In federated learning, data heterogeneity is a critical challenge. A straightforward solution is to shuffle the clients' data to homogenize the distribution. However, this may violate data access rights, and how and when shuffling can accelerate the convergence of a federated optimization algorithm is not theoretically well understood. In this paper, we establish a precise and quantifiable correspondence between data heterogeneity and parameters in the convergence rate when a fraction of data is shuffled across clients. We prove that shuffling can quadratically reduce the gradient dissimilarity with respect to the shuffling percentage, accelerating convergence. Inspired by the theory, we propose a practical approach that addresses the data access rights issue by shuffling locally generated synthetic data. The experimental results show that shuffling synthetic data improves the performance of multiple existing federated learning algorithms by a large margin.
Authors: Skylar Wolfgang Wurster, Tianyu Xiong, Han-Wei Shen, Hanqi Guo, Tom Peterka
Abstract: Scene representation networks (SRNs) have been recently proposed for compression and visualization of scientific data. However, state-of-the-art SRNs do not adapt the allocation of available network parameters to the complex features found in scientific data, leading to a loss in reconstruction quality. We address this shortcoming with an adaptively placed multi-grid SRN (APMGSRN) and propose a domain decomposition training and inference technique for accelerated parallel training on multi-GPU systems. We also release an open-source neural volume rendering application that allows plug-and-play rendering with any PyTorch-based SRN. Our proposed APMGSRN architecture uses multiple spatially adaptive feature grids that learn where to be placed within the domain to dynamically allocate more neural network resources where error is high in the volume, improving state-of-the-art reconstruction accuracy of SRNs for scientific data without requiring expensive octree refining, pruning, and traversal like previous adaptive models. In our domain decomposition approach for representing large-scale data, we train an set of APMGSRNs in parallel on separate bricks of the volume to reduce training time while avoiding overhead necessary for an out-of-core solution for volumes too large to fit in GPU memory. After training, the lightweight SRNs are used for realtime neural volume rendering in our open-source renderer, where arbitrary view angles and transfer functions can be explored. A copy of this paper, all code, all models used in our experiments, and all supplemental materials and videos are available at https://github.com/skywolf829/APMGSRN.
Authors: Frederic Wang, Han Qi, Alfredo De Goyeneche, Reinhard Heckel, Michael Lustig, Efrat Shimron
Abstract: Although deep learning (DL) methods are powerful for solving inverse problems, their reliance on high-quality training data is a major hurdle. This is significant in high-dimensional (dynamic/volumetric) magnetic resonance imaging (MRI), where acquisition of high-resolution fully sampled k-space data is impractical. We introduce a novel mathematical framework, dubbed k-band, that enables training DL models using only partial, limited-resolution k-space data. Specifically, we introduce training with stochastic gradient descent (SGD) over k-space subsets. In each training iteration, rather than using the fully sampled k-space for computing gradients, we use only a small k-space portion. This concept is compatible with different sampling strategies; here we demonstrate the method for k-space "bands", which have limited resolution in one dimension and can hence be acquired rapidly. We prove analytically that our method stochastically approximates the gradients computed in a fully-supervised setup, when two simple conditions are met: (i) the limited-resolution axis is chosen randomly-uniformly for every new scan, hence k-space is fully covered across the entire training set, and (ii) the loss function is weighed with a mask, derived here analytically, which facilitates accurate reconstruction of high-resolution details. Numerical experiments with raw MRI data indicate that k-band outperforms two other methods trained on limited-resolution data and performs comparably to state-of-the-art (SoTA) methods trained on high-resolution data. k-band hence obtains SoTA performance, with the advantage of training using only limited-resolution data. This work hence introduces a practical, easy-to-implement, self-supervised training framework, which involves fast acquisition and self-supervised reconstruction and offers theoretical guarantees.
Authors: Xiaodan Xing, Chunling Tang, Yunzhe Guo, Nicholas Kurniawan, Guang Yang
Abstract: Organoids are self-organized 3D cell clusters that closely mimic the architecture and function of in vivo tissues and organs. Quantification of organoid morphology helps in studying organ development, drug discovery, and toxicity assessment. Recent microscopy techniques provide a potent tool to acquire organoid morphology features, but manual image analysis remains a labor and time-intensive process. Thus, this paper proposes a comprehensive pipeline for microscopy analysis that leverages the SegmentAnything to precisely demarcate individual organoids. Additionally, we introduce a set of morphological properties, including perimeter, area, radius, non-smoothness, and non-circularity, allowing researchers to analyze the organoid structures quantitatively and automatically. To validate the effectiveness of our approach, we conducted tests on bright-field images of human induced pluripotent stem cells (iPSCs) derived neural-epithelial (NE) organoids. The results obtained from our automatic pipeline closely align with manual organoid detection and measurement, showcasing the capability of our proposed method in accelerating organoids morphology analysis.
Authors: Christopher Hahne, Georges Chabouh, Arthur Chavignon, Olivier Couture, Raphael Sznitman
Abstract: In Ultrasound Localization Microscopy (ULM), achieving high-resolution images relies on the precise localization of contrast agent particles across a series of beamformed frames. However, our study uncovers an enormous potential: The process of delay-and-sum beamforming leads to an irreversible reduction of Radio-Frequency (RF) channel data, while its implications for localization remain largely unexplored. The rich contextual information embedded within RF wavefronts, including their hyperbolic shape and phase, offers great promise for guiding Deep Neural Networks (DNNs) in challenging localization scenarios. To fully exploit this data, we propose to directly localize scatterers in RF channel data. Our approach involves a custom super-resolution DNN using learned feature channel shuffling, non-maximum suppression, and a semi-global convolutional block for reliable and accurate wavefront localization. Additionally, we introduce a geometric point transformation that facilitates seamless mapping to the B-mode coordinate space. To understand the impact of beamforming on ULM, we validate the effectiveness of our method by conducting an extensive comparison with State-Of-The-Art (SOTA) techniques. We present the inaugural in vivo results from a wavefront-localizing DNN, highlighting its real-world practicality. Our findings show that RF-ULM bridges the domain shift between synthetic and real datasets, offering a considerable advantage in terms of precision and complexity. To enable the broader research community to benefit from our findings, our code and the associated SOTA methods are made available at https://github.com/hahnec/rf-ulm.
Authors: Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Abstract: Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities. Federated learning, a method for collaboratively training a machine learning model across remote clients, achieves this by combining client models via the orchestration of a central server. However, current approaches face two critical limitations: i) they struggle to converge when client domains are sufficiently different, and ii) current aggregation techniques produce an identical global model for each client. In this work, we address these issues by reformulating the typical federated learning setup: rather than learning a single global model, we learn N models each optimized for a common objective. To achieve this, we apply a weighted distance minimization to model parameters shared in a peer-to-peer topology. The resulting framework, Iterative Parameter Alignment, applies naturally to the cross-silo setting, and has the following properties: (i) a unique solution for each participant, with the option to globally converge each model in the federation, and (ii) an optional early-stopping mechanism to elicit fairness among peers in collaborative learning settings. These characteristics jointly provide a flexible new framework for iteratively learning from peer models trained on disparate datasets. We find that the technique achieves competitive results on a variety of data partitions compared to state-of-the-art approaches. Further, we show that the method is robust to divergent domains (i.e. disjoint classes across peers) where existing approaches struggle.
Authors: Chancharik Mitra, Abrar Anwar, Rodolfo Corona, Dan Klein, Trevor Darrell, Jesse Thomason
Abstract: When connecting objects and their language referents in an embodied 3D environment, it is important to note that: (1) an object can be better characterized by leveraging comparative information between itself and other objects, and (2) an object's appearance can vary with camera position. As such, we present the Multi-view Approach to Grounding in Context (MAGiC), which selects an object referent based on language that distinguishes between two similar objects. By pragmatically reasoning over both objects and across multiple views of those objects, MAGiC improves over the state-of-the-art model on the SNARE object reference task with a relative error reduction of 12.9\% (representing an absolute improvement of 2.7\%). Ablation studies show that reasoning jointly over object referent candidates and multiple views of each object both contribute to improved accuracy. Code: https://github.com/rcorona/magic_snare/
Authors: Catherine Bouchard, Andr\'eanne Desch\^enes, Vincent Boulanger, Jean-Michel Bellavance, Flavie Lavoie-Cardinal, Christian Gagn\'e
Abstract: The development of robust signal unmixing algorithms is essential for leveraging multimodal datasets acquired through a wide array of scientific imaging technologies, including hyperspectral or time-resolved acquisitions. In experimental physics, enhancing the spatio-temporal resolution or expanding the number of detection channels often leads to diminished sampling rate and signal-to-noise ratio, significantly affecting the efficacy of signal unmixing algorithms. We propose applying band-pass filters to the latent space of a multi-dimensional convolutional neural network to disentangle overlapping signal components, enabling the isolation and quantification of their individual contributions. Using multi-dimensional convolution kernels to process all dimensions simultaneously enhances the network's ability to extract information from adjacent pixels, time- or spectral-bins. This approach enables more effective separation of components in cases where individual pixels do not provide clear, well-resolved information. We showcase the method's practical use in experimental physics through two test cases that highlight the versatility of our approach: fluorescence lifetime microscopy and mode decomposition in optical fibers. The latent unmixing method extracts valuable information from complex signals that cannot be resolved by standard methods. Application of latent unmixing to real FLIM experiments will increase the number of distinguishable fluorescent markers. It will also open new possibilities in optics and photonics for multichannel separations at increased sampling rate.
Authors: Tom Tirer, Raja Giryes, Se Young Chun, Yonina C. Eldar
Abstract: Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data is scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited. Using this information is the key to deep internal-learning strategies, which may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey paper aims at covering deep internal-learning techniques that have been proposed in the past few years for these two important directions. While our main focus will be on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities.
Authors: Xingguang Zhang, Nicholas Chimitt, Yiheng Chi, Zhiyuan Mao, Stanley H. Chan
Abstract: Recovering images distorted by atmospheric turbulence is a challenging inverse problem due to the stochastic nature of turbulence. Although numerous turbulence mitigation (TM) algorithms have been proposed, their efficiency and generalization to real-world dynamic scenarios remain severely limited. Building upon the intuitions of classical TM algorithms, we present the Deep Atmospheric TUrbulence Mitigation network (DATUM). DATUM aims to overcome major challenges when transitioning from classical to deep learning approaches. By carefully integrating the merits of classical multi-frame TM methods into a deep network structure, we demonstrate that DATUM can efficiently perform long-range temporal aggregation using a recurrent fashion, while deformable attention and temporal-channel attention seamlessly facilitate pixel registration and lucky imaging. With additional supervision, tilt and blur degradation can be jointly mitigated. These inductive biases empower DATUM to significantly outperform existing methods while delivering a tenfold increase in processing speed. A large-scale training dataset, ATSyn, is presented as a co-invention to enable generalization in real turbulence. Our code and datasets are available at https://xg416.github.io/DATUM.
Authors: Junming Chen, Yunfei Liu, Jianan Wang, Ailing Zeng, Yu Li, Qifeng Chen
Abstract: We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length. While previous works focused on co-speech gesture or expression generation individually, the joint generation of synchronized expressions and gestures remains barely explored. To address this, our diffusion-based co-speech motion generation transformer enables uni-directional information flow from expression to gesture, facilitating improved matching of joint expression-gesture distributions. Furthermore, we introduce an outpainting-based sampling strategy for arbitrary long sequence generation in diffusion models, offering flexibility and computational efficiency. Our method provides a practical solution that produces high-quality synchronized expression and gesture generation driven by speech. Evaluated on two public datasets, our approach achieves state-of-the-art performance both quantitatively and qualitatively. Additionally, a user study confirms the superiority of DiffSHEG over prior approaches. By enabling the real-time generation of expressive and synchronized motions, DiffSHEG showcases its potential for various applications in the development of digital humans and embodied agents.
Authors: Esteve Valls Mascaro, Yashuai Yan, Dongheui Lee
Abstract: Integrating robots into populated environments is a complex challenge that requires an understanding of human social dynamics. In this work, we propose to model social motion forecasting in a shared human-robot representation space, which facilitates us to synthesize robot motions that interact with humans in social scenarios despite not observing any robot in the motion training. We develop a transformer-based architecture called ECHO, which operates in the aforementioned shared space to predict the future motions of the agents encountered in social scenarios. Contrary to prior works, we reformulate the social motion problem as the refinement of the predicted individual motions based on the surrounding agents, which facilitates the training while allowing for single-motion forecasting when only one human is in the scene. We evaluate our model in multi-person and human-robot motion forecasting tasks and obtain state-of-the-art performance by a large margin while being efficient and performing in real-time. Additionally, our qualitative results showcase the effectiveness of our approach in generating human-robot interaction behaviors that can be controlled via text commands. Webpage: https://evm7.github.io/ECHO/
Authors: Pranav Kulkarni, Andrew Chan, Nithya Navarathna, Skylar Chan, Paul H. Yi, Vishwa S. Parekh
Abstract: The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an underexplored field of research in medical imaging. In this work, we demonstrate that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in DL models. Our results across multiple performance metrics and demographic groups like sex, age, and their intersectional subgroups show that adversarial bias attacks demonstrate high-selectivity for bias in the targeted group by degrading group model performance without impacting overall model performance. Furthermore, our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets.
Authors: Yehui Tang, Yunhe Wang, Jianyuan Guo, Zhijun Tu, Kai Han, Hailin Hu, Dacheng Tao
Abstract: Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision models (LVM). Model compression methods reduce the memory and computational cost of Transformer, which is a necessary step to implement large language/vision models on practical devices. Given the unique architecture of Transformer, featuring alternative attention and feedforward neural network (FFN) modules, specific compression techniques are usually required. The efficiency of these compression methods is also paramount, as retraining large models on the entire training dataset is usually impractical. This survey provides a comprehensive review of recent compression methods, with a specific focus on their application to Transformer-based models. The compression methods are primarily categorized into pruning, quantization, knowledge distillation, and efficient architecture design (Mamba, RetNet, RWKV, etc.). In each category, we discuss compression methods for both language and vision tasks, highlighting common underlying principles. Finally, we delve into the relation between various compression methods, and discuss further directions in this domain.
Authors: Chester Luo, Kevin Lai
Abstract: In recent years, there has been a significant increase in the utilization of deep learning methods, particularly convolutional neural networks (CNNs), which have emerged as the dominant approach in various domains that involve structured grid data, such as picture analysis and processing. Nevertheless, the exponential growth in the utilization of LiDAR and 3D sensors across many domains has resulted in an increased need for the analysis of 3D point clouds. The utilization of 3D point clouds is crucial in various applications, including object recognition and segmentation, as they offer a spatial depiction of things within a three-dimensional environment. In contrast to photos, point clouds exhibit sparsity and lack a regular grid, hence posing distinct processing and computational issues.
Authors: Yanjie Ze, Gu Zhang, Kangning Zhang, Chenyuan Hu, Muhan Wang, Huazhe Xu
Abstract: Imitation learning provides an efficient way to teach robots dexterous skills; however, learning complex skills robustly and generalizablely usually consumes large amounts of human demonstrations. To tackle this challenging problem, we present 3D Diffusion Policy (DP3), a novel visual imitation learning approach that incorporates the power of 3D visual representations into diffusion policies, a class of conditional action generative models. The core design of DP3 is the utilization of a compact 3D visual representation, extracted from sparse point clouds with an efficient point encoder. In our experiments involving 72 simulation tasks, DP3 successfully handles most tasks with just 10 demonstrations and surpasses baselines with a 24.2% relative improvement. In 4 real robot tasks, DP3 demonstrates precise control with a high success rate of 85%, given only 40 demonstrations of each task, and shows excellent generalization abilities in diverse aspects, including space, viewpoint, appearance, and instance. Interestingly, in real robot experiments, DP3 rarely violates safety requirements, in contrast to baseline methods which frequently do, necessitating human intervention. Our extensive evaluation highlights the critical importance of 3D representations in real-world robot learning. Videos, code, and data are available on https://3d-diffusion-policy.github.io .
Authors: Andre Ye
Abstract: Vision is an important metaphor in ethical and political questions of knowledge. The feminist philosopher Donna Haraway points out the ``perverse'' nature of an intrusive, alienating, all-seeing vision (to which we might cry out ``stop looking at me!''), but also encourages us to embrace the embodied nature of sight and its promises for genuinely situated knowledge. Current technologies of machine vision -- surveillance cameras, drones (for war or recreation), iPhone cameras -- are usually construed as instances of the former rather than the latter, and for good reasons. However, although in no way attempting to diminish the real suffering these technologies have brought about in the world, I make the case for understanding technologies of computer vision as material instances of embodied seeing and situated knowing. Furthermore, borrowing from Iris Murdoch's concept of moral vision, I suggest that these technologies direct our labor towards self-reflection in ethically significant ways. My approach draws upon paradigms in computer vision research, phenomenology, and feminist epistemology. Ultimately, this essay is an argument for directing more philosophical attention from merely criticizing technologies of vision as ethically deficient towards embracing them as complex, methodologically and epistemologically important objects.
Authors: Abhinav Sharma, Bojing Liu, Mattias Rantalainen
Abstract: Deep learning enables the modelling of high-resolution histopathology whole-slide images (WSI). Weakly supervised learning of tile-level data is typically applied for tasks where labels only exist on the patient or WSI level (e.g. patient outcomes or histological grading). In this context, there is a need for improved spatial interpretability of predictions from such models. We propose a novel method, Wsi rEgion sElection aPproach (WEEP), for model interpretation. It provides a principled yet straightforward way to establish the spatial area of WSI required for assigning a particular prediction label. We demonstrate WEEP on a binary classification task in the area of breast cancer computational pathology. WEEP is easy to implement, is directly connected to the model-based decision process, and offers information relevant to both research and diagnostic applications.
Authors: Yao Ni, Piotr Koniusz
Abstract: Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overfitting and unstable training. Batch Normalization (BN), despite being known for enhancing generalization and training stability, has rarely been used in the discriminator of Data-Efficient GANs. Our work addresses this gap by identifying a critical flaw in BN: the tendency for gradient explosion during the centering and scaling steps. To tackle this issue, we present CHAIN (lipsCHitz continuity constrAIned Normalization), which replaces the conventional centering step with zero-mean regularization and integrates a Lipschitz continuity constraint in the scaling step. CHAIN further enhances GAN training by adaptively interpolating the normalized and unnormalized features, effectively avoiding discriminator overfitting. Our theoretical analyses firmly establishes CHAIN's effectiveness in reducing gradients in latent features and weights, improving stability and generalization in GAN training. Empirical evidence supports our theory. CHAIN achieves state-of-the-art results in data-limited scenarios on CIFAR-10/100, ImageNet, five low-shot and seven high-resolution few-shot image datasets. Code: https://github.com/MaxwellYaoNi/CHAIN
Authors: Zhonghao Shi, Ellen Landrum, Amy O' Connell, Mina Kian, Leticia Pinto-Alva, Kaleen Shrestha, Xiaoyuan Zhu, Maja J Matari\'c
Abstract: Socially assistive robots (SARs) have shown great success in providing personalized cognitive-affective support for user populations with special needs such as older adults, children with autism spectrum disorder (ASD), and individuals with mental health challenges. The large body of work on SAR demonstrates its potential to provide at-home support that complements clinic-based interventions delivered by mental health professionals, making these interventions more effective and accessible. However, there are still several major technical challenges that hinder SAR-mediated interactions and interventions from reaching human-level social intelligence and efficacy. With the recent advances in large language models (LLMs), there is an increased potential for novel applications within the field of SAR that can significantly expand the current capabilities of SARs. However, incorporating LLMs introduces new risks and ethical concerns that have not yet been encountered, and must be carefully be addressed to safely deploy these more advanced systems. In this work, we aim to conduct a brief survey on the use of LLMs in SAR technologies, and discuss the potentials and risks of applying LLMs to the following three major technical challenges of SAR: 1) natural language dialog; 2) multimodal understanding; 3) LLMs as robot policies.