Authors: Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Fartash Faghri, Devang Naik, Oncel Tuzel, Mohammad Rastegari
Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this challenge by initializing the model with weights of a pretrained model of the same size and specification to increase the convergence and training speed. However, what if no pretrained model of the required size is available? In this paper, we introduce a simple yet effective technique to transfer the knowledge of a pretrained model to smaller variants. Our approach called weight subcloning expedites the training of scaled-down transformers by initializing their weights from larger pretrained models.
Weight subcloning involves an operation on the pretrained model to obtain the equivalent initialized scaled-down model. It consists of two key steps: first, we introduce neuron importance ranking to decrease the embedding dimension per layer in the pretrained model. Then, we remove blocks from the transformer model to match the number of layers in the scaled-down network. The result is a network ready to undergo training, which gains significant improvements in training speed compared to random initialization. For instance, we achieve 4x faster training for vision transformers in image classification and language models designed for next token prediction.
Authors: Boshi Tang, Jianan Wang, Zhiyong Wu, Lei Zhang
Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation. However, a comprehensive understanding of the SDS formulation is still lacking, hindering the development of 3D generation. In this work, we present an interpretation of SDS as a combination of three functional components: mode-disengaging, mode-seeking and variance-reducing terms, and analyze the properties of each. We show that problems such as over-smoothness and color-saturation result from the intrinsic deficiency of the supervision terms and reveal that the variance-reducing term introduced by SDS is sub-optimal. Additionally, we shed light on the adoption of large Classifier-Free Guidance (CFG) scale for 3D generation. Based on the analysis, we propose a simple yet effective approach named Stable Score Distillation (SSD) which strategically orchestrates each term for high-quality 3D generation. Extensive experiments validate the efficacy of our approach, demonstrating its ability to generate high-fidelity 3D content without succumbing to issues such as over-smoothness and over-saturation, even under low CFG conditions with the most challenging NeRF representation.
Authors: Umar Khalid, Hasan Iqbal, Nazmul Karim, Jing Hua, Chen Chen
While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry and texture information from multi-view inputs. In this paper, we introduce \textsc{LatentEditor}, an innovative framework designed to empower users with the ability to perform precise and locally controlled editing of neural fields using text prompts. Leveraging denoising diffusion models, we successfully embed real-world scenes into the latent space, resulting in a faster and more adaptable NeRF backbone for editing compared to traditional methods. To enhance editing precision, we introduce a delta score to calculate the 2D mask in the latent space that serves as a guide for local modifications while preserving irrelevant regions. Our novel pixel-level scoring approach harnesses the power of InstructPix2Pix (IP2P) to discern the disparity between IP2P conditional and unconditional noise predictions in the latent space. The edited latents conditioned on the 2D masks are then iteratively updated in the training set to achieve 3D local editing. Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models, bridging the gap between textual instructions and high-quality 3D scene editing in latent space. We show the superiority of our approach on four benchmark 3D datasets, LLFF, IN2N, NeRFStudio and NeRF-Art.
Authors: Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Aniruddha Kembhavi, Kiana Ehsani
Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient personalization of robotic agents to diverse human preferences in complex environments. We use multi-objective reinforcement learning to train a single policy adaptable to a broad spectrum of preferences. We introduce three distinct methods to infer human preferences by leveraging different types of interactions: (1) human demonstrations, (2) preference feedback on trajectory comparisons, and (3) language instructions. We evaluate the proposed method in personalized object-goal navigation and flee navigation tasks in ProcTHOR and RoboTHOR, demonstrating the ability to prompt agent behaviors to satisfy human preferences in various scenarios. Project page: https://promptable-behaviors.github.io
Authors: Payal Kamboj, Ayan Banerjee, Varina L. Boerwinkle, Sandeep K.S. Gupta
We evaluated whether integration of expert guidance on seizure onset zone (SOZ) identification from resting state functional MRI (rs-fMRI) connectomics combined with deep learning (DL) techniques enhances the SOZ delineation in patients with refractory epilepsy (RE), compared to utilizing DL alone. Rs-fMRI were collected from 52 children with RE who had subsequently undergone ic-EEG and then, if indicated, surgery for seizure control (n = 25). The resting state functional connectomics data were previously independently classified by two expert epileptologists, as indicative of measurement noise, typical resting state network connectivity, or SOZ. An expert knowledge integrated deep network was trained on functional connectomics data to identify SOZ. Expert knowledge integrated with DL showed a SOZ localization accuracy of 84.8& and F1 score, harmonic mean of positive predictive value and sensitivity, of 91.7%. Conversely, a DL only model yielded an accuracy of less than 50% (F1 score 63%). Activations that initiate in gray matter, extend through white matter and end in vascular regions are seen as the most discriminative expert identified SOZ characteristics. Integration of expert knowledge of functional connectomics can not only enhance the performance of DL in localizing SOZ in RE, but also lead toward potentially useful explanations of prevalent co-activation patterns in SOZ. RE with surgical outcomes and pre-operative rs-fMRI studies can yield expert knowledge most salient for SOZ identification.
Authors: Sahil Nokhwal, Nirman Kumar
Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss function. We propose the RTRA, a modification to the widely used Elastic Weight Consolidation (EWC) regularization scheme, using the Natural Gradient for loss function optimization. Our approach improves the training of regularization-based methods without sacrificing test-data performance. We compare the proposed RTRA approach against EWC using the iFood251 dataset. We show that RTRA has a clear edge over the state-of-the-art approaches.
Authors: Guangming Liu, Quanying Sun, Qi iu
In this paper, we propose a novel variational active contour model based on I-divergence-TV model to segment Synthetic aperture radar (SAR) images with multiplicative gamma noise, which hybrides edge-based model with region-based model. The proposed model can efficiently stop the contours at weak or blurred edges, and can automatically detect the exterior and interior boundaries of images. We incorporate the global convex segmentation method and split Bregman technique into the proposed model, and propose a fast fixed point algorithm to solve the global convex segmentation question[25]. Experimental results for synthetic images and real SAR images show that the proposed fast fixed point algorithm is robust and efficient compared with the state-of-the-art approach.
Authors: Md Mahedi Hasan, Shoaib Meraj Sami, Nasser Nasrabadi
State-of-the-art face recognition (FR) models often experience a significant performance drop when dealing with facial images in surveillance scenarios where images are in low quality and often corrupted with noise. Leveraging facial characteristics, such as freckles, scars, gender, and ethnicity, becomes highly beneficial in improving FR performance in such scenarios. In this paper, we introduce text-guided face recognition (TGFR) to analyze the impact of integrating facial attributes in the form of natural language descriptions. We hypothesize that adding semantic information into the loop can significantly improve the image understanding capability of an FR algorithm compared to other soft biometrics. However, learning a discriminative joint embedding within the multimodal space poses a considerable challenge due to the semantic gap in the unaligned image-text representations, along with the complexities arising from ambiguous and incoherent textual descriptions of the face. To address these challenges, we introduce a face-caption alignment module (FCAM), which incorporates cross-modal contrastive losses across multiple granularities to maximize the mutual information between local and global features of the face-caption pair. Within FCAM, we refine both facial and textual features for learning aligned and discriminative features. We also design a face-caption fusion module (FCFM) that applies fine-grained interactions and coarse-grained associations among cross-modal features. Through extensive experiments conducted on three face-caption datasets, proposed TGFR demonstrates remarkable improvements, particularly on low-quality images, over existing FR models and outperforms other related methods and benchmarks.
Authors: Christoforos Galazis, Samuel Shepperd, Emma Brouwer, Sandro Queirós, Ebraham Alskaf, Mustafa Anjari, Amedeo Chiribiri, Jack Lee, Anil A. Bharath, Marta Varela
The functional analysis of the left atrium (LA) is important for evaluating cardiac health and understanding diseases like atrial fibrillation. Cine MRI is ideally placed for the detailed 3D characterisation of LA motion and deformation, but it is lacking appropriate acquisition and analysis tools. In this paper, we present Analysis for Left Atrial Displacements and Deformations using unsupervIsed neural Networks, \textit{Aladdin}, to automatically and reliably characterise regional LA deformations from high-resolution 3D Cine MRI. The tool includes: an online few-shot segmentation network (Aladdin-S), an online unsupervised image registration network (Aladdin-R), and a strain calculations pipeline tailored to the LA. We create maps of LA Displacement Vector Field (DVF) magnitude and LA principal strain values from images of 10 healthy volunteers and 8 patients with cardiovascular disease (CVD). We additionally create an atlas of these biomarkers using the data from the healthy volunteers. Aladdin is able to accurately track the LA wall across the cardiac cycle and characterize its motion and deformation. The overall DVF magnitude and principal strain values are significantly higher in the healthy group vs CVD patients: $2.85 \pm 1.59~mm$ and $0.09 \pm 0.05$ vs $1.96 \pm 0.74~mm$ and $0.03 \pm 0.04$, respectively. The time course of these metrics is also different in the two groups, with a more marked active contraction phase observed in the healthy cohort. Finally, utilizing the LA atlas allows us to identify regional deviations from the population distribution that may indicate focal tissue abnormalities. The proposed tool for the quantification of novel regional LA deformation biomarkers should have important clinical applications. The source code, anonymized images, generated maps and atlas are publicly available: https://github.com/cgalaz01/aladdin_cmr_la.
Authors: Krishna Mullia, Fujun Luan, Xin Sun, Miloš Hašan
High-fidelity 3D assets with materials composed of fibers (including hair), complex layered material shaders, or fine scattering geometry are ubiquitous in high-end realistic rendering applications. Rendering such models is computationally expensive due to heavy shaders and long scattering paths. Moreover, implementing the shading and scattering models is non-trivial and has to be done not only in the 3D content authoring software (which is necessarily complex), but also in all downstream rendering solutions. For example, web and mobile viewers for complex 3D assets are desirable, but frequently cannot support the full shading complexity allowed by the authoring application. Our goal is to design a neural representation for 3D assets with complex shading that supports full relightability and full integration into existing renderers. We provide an end-to-end shading solution at the first intersection of a ray with the underlying geometry. All shading and scattering is precomputed and included in the neural asset; no multiple scattering paths need to be traced, and no complex shading models need to be implemented to render our assets, beyond a single neural architecture. We combine an MLP decoder with a feature grid. Shading consists of querying a feature vector, followed by an MLP evaluation producing the final reflectance value. Our method provides high-fidelity shading, close to the ground-truth Monte Carlo estimate even at close-up views. We believe our neural assets could be used in practical renderers, providing significant speed-ups and simplifying renderer implementations.
Authors: Tianyi Chen, Tianyu Ding, Zhihui Zhu, Zeyu Chen, HsiangTao Wu, Ilya Zharkov, Luming Liang
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm. This topic spans various techniques, from structured pruning to neural architecture search, encompassing both pruning and erasing operators perspectives. Despite advancements, existing methods suffers from complex, multi-stage processes that demand substantial engineering and domain knowledge, limiting their broader applications. We introduce the third-generation Only-Train-Once (OTOv3), which first automatically trains and compresses a general DNN through pruning and erasing operations, creating a compact and competitive sub-network without the need of fine-tuning. OTOv3 simplifies and automates the training and compression process, minimizes the engineering efforts required from users. It offers key technological advancements: (i) automatic search space construction for general DNNs based on dependency graph analysis; (ii) Dual Half-Space Projected Gradient (DHSPG) and its enhanced version with hierarchical search (H2SPG) to reliably solve (hierarchical) structured sparsity problems and ensure sub-network validity; and (iii) automated sub-network construction using solutions from DHSPG/H2SPG and dependency graphs. Our empirical results demonstrate the efficacy of OTOv3 across various benchmarks in structured pruning and neural architecture search. OTOv3 produces sub-networks that match or exceed the state-of-the-arts. The source code will be available at https://github.com/tianyic/only_train_once.
Authors: Tue Minh Cao, Nhat Hong Tran, Le Phi Nguyen, Hieu Huy Pham, Hung Thanh Nguyen
Our study focuses on the potential for modifications of Inception-like architecture within the electrocardiogram (ECG) domain. To this end, we introduce IncepSE, a novel network characterized by strategic architectural incorporation that leverages the strengths of both InceptionTime and channel attention mechanisms. Furthermore, we propose a training setup that employs stabilization techniques that are aimed at tackling the formidable challenges of severe imbalance dataset PTB-XL and gradient corruption. By this means, we manage to set a new height for deep learning model in a supervised learning manner across the majority of tasks. Our model consistently surpasses InceptionTime by substantial margins compared to other state-of-the-arts in this domain, noticeably 0.013 AUROC score improvement in the "all" task, while also mitigating the inherent dataset fluctuations during training.
Authors: Sung-Jin Kim, Heon-Gyu Kwak, Hyeon-Taek Han, Dae-Hyeok Lee, Ji-Hoon Jeong, Seong-Whan Lee
Brain-computer interface (BCI) has garnered the significant attention for their potential in various applications, with event-related potential (ERP) performing a considerable role in BCI systems. This paper introduces a novel Distributed Inference System tailored for detecting task-wise single-trial ERPs in a stream of satellite images. Unlike traditional methodologies that employ a single model for target detection, our system utilizes multiple models, each optimized for specific tasks, ensuring enhanced performance across varying image transition times and target onset times. Our experiments, conducted on four participants, employed two paradigms: the Normal paradigm and an AI paradigm with bounding boxes. Results indicate that our proposed system outperforms the conventional methods in both paradigms, achieving the highest $F_{\beta}$ scores. Furthermore, including bounding boxes in the AI paradigm significantly improved target recognition. This study underscores the potential of our Distributed Inference System in advancing the field of ERP detection in satellite image streams.
Authors: Kuan-Huang Yu
This paper presents Chinese Poker Self-Playing Robot, an integrated system enabling a TM5-900 robotic arm to independently play the four-person card game Chinese poker. The robot uses a custom sucker mechanism to pick up and play cards. An object detection model based on YOLOv5 is utilized to recognize the suit and number of 13 cards dealt to the robot. A greedy algorithm is developed to divide the 13 cards into optimal hands of 3, 5, and 5 cards to play. Experiments demonstrate that the robot can successfully obtain the cards, identify them using computer vision, strategically select hands to play using the algorithm, and physically play the selected cards in the game. The system showcases effective integration of mechanical design, computer vision, algorithm design, and robotic control to accomplish the complex task of independently playing cards.
Authors: Ho-Weng Lee, Shang-Hong Lai
In recent years, the focus on anomaly detection and localization in industrial inspection tasks has intensified. While existing studies have demonstrated impressive outcomes, they often rely heavily on extensive training datasets or robust features extracted from pre-trained models trained on diverse datasets like ImageNet. In this work, we propose a novel framework leveraging the visual-linguistic CLIP model to adeptly train a backbone model tailored to the manufacturing domain. Our approach concurrently considers visual and text-aligned embedding spaces for normal and abnormal conditions. The resulting pre-trained backbone markedly enhances performance in industrial downstream tasks, particularly in anomaly detection and localization. Notably, this improvement is substantiated through experiments conducted on multiple datasets such as MVTecAD, BTAD, and KSDD2. Furthermore, using our pre-trained backbone weights allows previous works to achieve superior performance in few-shot scenarios with less training data. The proposed anomaly backbone provides a foundation model for more precise anomaly detection and localization.
Authors: Qian Wang, Yaoyao Liu, Hefei Ling, Yingwei Li, Qihao Liu, Ping Li, Jiazhong Chen, Alan Yuille, Ning Yu
In response to the rapidly evolving nature of adversarial attacks on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that can generalize to all types of attacks, including unseen ones, is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks used by many attackers. The defense system needs to upgrade itself by utilizing few-shot defense feedback and efficient memory. Therefore, we propose the first continual adversarial defense (CAD) framework that adapts to any attacks in a dynamic scenario, where various attacks emerge stage by stage. In practice, CAD is modeled under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial images. We leverage cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Experiments conducted on CIFAR-10 and ImageNet-100 validate the effectiveness of our approach against multiple stages of 10 modern adversarial attacks and significant improvements over 10 baseline methods. In particular, CAD is capable of quickly adapting with minimal feedback and a low cost of defense failure, while maintaining good performance against old attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Authors: Zixian Su, Jingwei Guo, Kai Yao, Xi Yang, Qiufeng Wang, Kaizhu Huang
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. Drawing upon this insight, we introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches. Importantly, our TEMA adaptively extends the scope of typical methods beyond the current batch to incorporate a diverse set of class information, which in turn boosts an accurate target estimation. Built upon this foundation, we further design a novel layer-wise rectification strategy to consistently promote test-time performance. Our proposed method enjoys a unique advantage as it requires neither training nor tuning parameters, offering a truly hassle-free solution. It significantly enhances model robustness against shifted domains and maintains resilience in diverse real-world scenarios with various batch sizes, achieving state-of-the-art performance on several major benchmarks. Code is available at \url{https://github.com/kiwi12138/RealisticTTA}.
Authors: Zhengdong Li
In recent years, deep generative models, such as Generative Adversarial Network (GAN), has grabbed significant attention in the field of computer vision. This project focuses on the application of GAN in image deblurring with the aim of generating clearer images from blurry inputs caused by factors such as motion blur. However, traditional image restoration techniques have limitations in handling complex blurring patterns. Hence, a GAN-based framework is proposed as a solution to generate high-quality deblurred images. The project defines a GAN model in Tensorflow and trains it with GoPRO dataset. The Generator will intake blur images directly to create fake images to convince the Discriminator which will receive clear images at the same time and distinguish between the real image and the fake image. After obtaining the trained parameters, the model was used to deblur motion-blur images taken in daily life as well as testing set for validation. The result shows that the pretrained network of GAN can obtain sharper pixels in image, achieving an average of 29.3 Peak Signal-to-Noise Ratio (PSNR) and 0.72 Structural Similarity Assessment (SSIM). This help to effectively address the challenges posed by image blurring, leading to the generation of visually pleasing and sharp images. By exploiting the adversarial learning framework, the proposed approach enhances the potential for real-world applications in image restoration.
Authors: Longzhong Lin, Xuewu Lin, Tianwei Lin, Lichao Huang, Rong Xiong, Yue Wang
Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors. Many successful works have utilized mixture models which require identification of positive mixture components, and correspondingly fall into two main lines: prediction-based and anchor-based matching. The prediction clustering phenomenon in prediction-based matching makes it difficult to pick representative trajectories for downstream tasks, while the anchor-based matching suffers from a limited regression capability. In this paper, we introduce a novel paradigm, named Evolving and Distinct Anchors (EDA), to define the positive and negative components for multimodal motion prediction based on mixture models. We enable anchors to evolve and redistribute themselves under specific scenes for an enlarged regression capacity. Furthermore, we select distinct anchors before matching them with the ground truth, which results in impressive scoring performance. Our approach enhances all metrics compared to the baseline MTR, particularly with a notable relative reduction of 13.5% in Miss Rate, resulting in state-of-the-art performance on the Waymo Open Motion Dataset. Code is available at https://github.com/Longzhong-Lin/EDA.
Authors: Huy Le, Tung Kieu, Anh Nguyen, Ngan Le
Text-video retrieval, a prominent sub-field within the broader domain of multimedia content management, has witnessed remarkable growth and innovation over the past decade. However, existing methods assume the video scenes are consistent and the description annotators are unbiased. These limitations fail to align with fluid real-world scenarios, and descriptions can be influenced by annotator biases, diverse writing styles, and varying textual perspectives. To overcome the aforementioned problems, we introduce WAVER, a cross-domain knowledge distillation mechanism designed to tackle the challenge of handling writing-style agnostics. WAVER capitalizes on the open-vocabulary properties inherent in pre-trained vision-language models and employs an implicit knowledge distillation approach to transfer text-based knowledge from a teacher model to a vision-based student. Empirical studies conducted across four standard benchmark datasets, encompassing various settings, provide compelling evidence that \WAVER can achieve state-of-the-art performance in text-video retrieval tasks while handling writing-style variations.
Authors: Hengrong Lan, Zhiqiang Li, Qiong He, Jianwen Luo
Image reconstruction from radio-frequency data is pivotal in ultrafast plane wave ultrasound imaging. Unlike the conventional delay-and-sum (DAS) technique, which relies on somewhat imprecise assumptions, deep learning-based methods perform image reconstruction by training on paired data, leading to a notable enhancement in image quality. Nevertheless, these strategies often exhibit limited generalization capabilities. Recently, denoising diffusion models have become the preferred paradigm for image reconstruction tasks. However, their reliance on an iterative sampling procedure results in prolonged generation time. In this paper, we propose a novel sampling framework that concurrently enforces data consistency of ultrasound signals and data-driven priors. By leveraging the advanced diffusion model, the generation of high-quality images is substantially expedited. Experimental evaluations on an in-vivo dataset indicate that our approach with a single plane wave surpasses DAS with spatial coherent compounding of 75 plane waves.
Authors: Zhiqiang Li, Hengrong Lan, Lijie Huang, Qiong He, Jianwen Luo
Reconstruction of ultrasound (US) images from radio-frequency data can be conceptualized as a linear inverse problem. Traditional deep learning approaches, which aim to improve the quality of US images by directly learning priors, often encounter challenges in generalization. Recently, diffusion-based generative models have received significant attention within the research community due to their robust performance in image reconstruction tasks. However, a limitation of these models is their inherent low speed in generating image samples from pure Gaussian noise progressively. In this study, we exploit the inherent similarity between the US images reconstructed from a single plane wave (PW) and PW compounding PWC). We hypothesize that a single PW can take a shortcut to reach the diffusion trajectory of PWC, removing the need to begin with Gaussian noise. By employing an advanced diffusion model, we demonstrate its effectiveness in US image reconstruction, achieving a substantial reduction in sampling steps. In-vivo experimental results indicate that our approach can reduce sampling steps by 60%, while preserving comparable performance metrics with the conventional diffusion model.
Authors: Chen Ma, Ningfei Wang, Qi Alfred Chen, Chao Shen
In Autonomous Driving (AD), real-time perception is a critical component responsible for detecting surrounding objects to ensure safe driving. While researchers have extensively explored the integrity of AD perception due to its safety and security implications, the aspect of availability (real-time performance) or latency has received limited attention. Existing works on latency-based attack have focused mainly on object detection, i.e., a component in camera-based AD perception, overlooking the entire camera-based AD perception, which hinders them to achieve effective system-level effects, such as vehicle crashes. In this paper, we propose SlowTrack, a novel framework for generating adversarial attacks to increase the execution time of camera-based AD perception. We propose a novel two-stage attack strategy along with the three new loss function designs. Our evaluation is conducted on four popular camera-based AD perception pipelines, and the results demonstrate that SlowTrack significantly outperforms existing latency-based attacks while maintaining comparable imperceptibility levels. Furthermore, we perform the evaluation on Baidu Apollo, an industry-grade full-stack AD system, and LGSVL, a production-grade AD simulator, with two scenarios to compare the system-level effects of SlowTrack and existing attacks. Our evaluation results show that the system-level effects can be significantly improved, i.e., the vehicle crash rate of SlowTrack is around 95% on average while existing works only have around 30%.
Authors: Arjun Balasingam, Joseph Chandler, Chenning Li, Zhoutong Zhang, Hari Balakrishnan
This paper presents DriveTrack, a new benchmark and data generation framework for long-range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that the accuracy of state-of-the-art trackers depends strongly on visual attributes around the selected keypoints, such as texture and lighting. The problem is that these artifacts are especially pronounced in real-world videos, but these trackers are unable to train on such scenes due to a dearth of annotations. DriveTrack bridges this gap by building a framework to automatically annotate point tracks on autonomous driving datasets. We release a dataset consisting of 1 billion point tracks across 24 hours of video, which is seven orders of magnitude greater than prior real-world benchmarks and on par with the scale of synthetic benchmarks. DriveTrack unlocks new use cases for point tracking in real-world videos. First, we show that fine-tuning keypoint trackers on DriveTrack improves accuracy on real-world scenes by up to 7%. Second, we analyze the sensitivity of trackers to visual artifacts in real scenes and motivate the idea of running assistive keypoint selectors alongside trackers.
Authors: Gensheng Pei, Fumin Shen, Yazhou Yao, Tao Chen, Xian-Sheng Hua, Heng-Tao Shen
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene. The temporal consistency provided by the optical flow could be effectively supplemented by modeling in a structural form. This paper proposes a new hierarchical graph neural network (GNN) architecture, dubbed hierarchical graph pattern understanding (HGPU), for zero-shot video object segmentation (ZS-VOS). Inspired by the strong ability of GNNs in capturing structural relations, HGPU innovatively leverages motion cues (\ie, optical flow) to enhance the high-order representations from the neighbors of target frames. Specifically, a hierarchical graph pattern encoder with message aggregation is introduced to acquire different levels of motion and appearance features in a sequential manner. Furthermore, a decoder is designed for hierarchically parsing and understanding the transformed multi-modal contexts to achieve more accurate and robust results. HGPU achieves state-of-the-art performance on four publicly available benchmarks (DAVIS-16, YouTube-Objects, Long-Videos and DAVIS-17). Code and pre-trained model can be found at \url{https://github.com/NUST-Machine-Intelligence-Laboratory/HGPU}.
Authors: Ruijie Zhu, Jiahao Chang, Ziyang Song, Jiahuan Yu, Tianzhu Zhang
This report describes the solution that secured the first place in the "View Synthesis Challenge for Human Heads (VSCHH)" at the ICCV 2023 workshop. Given the sparse view images of human heads, the objective of this challenge is to synthesize images from novel viewpoints. Due to the complexity of textures on the face and the impact of lighting, the baseline method TensoRF yields results with significant artifacts, seriously affecting facial reconstruction. To address this issue, we propose TI-Face, which improves facial reconstruction through tensorial radiance fields (T-Face) and implicit surfaces (I-Face), respectively. Specifically, we employ an SAM-based approach to obtain the foreground mask, thereby filtering out intense lighting in the background. Additionally, we design mask-based constraints and sparsity constraints to eliminate rendering artifacts effectively. The experimental results demonstrate the effectiveness of the proposed improvements and superior performance of our method on face reconstruction. The code will be available at https://github.com/RuijieZhu94/TI-Face.
Authors: Kazuma Kobayashi, Yasuyuki Takamizawa, Mototaka Miyake, Sono Ito, Lin Gu, Tatsuya Nakatsuka, Yu Akagi, Tatsuya Harada, Yukihide Kanemitsu, Ryuji Hamamoto
Explainability is key to enhancing artificial intelligence's trustworthiness in medicine. However, several issues remain concerning the actual benefit of explainable models for clinical decision-making. Firstly, there is a lack of consensus on an evaluation framework for quantitatively assessing the practical benefits that effective explainability should provide to practitioners. Secondly, physician-centered evaluations of explainability are limited. Thirdly, the utility of built-in attention mechanisms in transformer-based models as an explainability technique is unclear. We hypothesize that superior attention maps should align with the information that physicians focus on, potentially reducing prediction uncertainty and increasing model reliability. We employed a multimodal transformer to predict lymph node metastasis in rectal cancer using clinical data and magnetic resonance imaging, exploring how well attention maps, visualized through a state-of-the-art technique, can achieve agreement with physician understanding. We estimated the model's uncertainty using meta-level information like prediction probability variance and quantified agreement. Our assessment of whether this agreement reduces uncertainty found no significant effect. In conclusion, this case study did not confirm the anticipated benefit of attention maps in enhancing model reliability. Superficial explanations could do more harm than good by misleading physicians into relying on uncertain predictions, suggesting that the current state of attention mechanisms in explainability should not be overestimated. Identifying explainability mechanisms truly beneficial for clinical decision-making remains essential.
Authors: Rollin Omari, Junae Kim, Paul Montague
In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks, emphasising the associated security risks. Our study investigates the impact of incremental attack strength on training, introduces the concept of transferability between supervised and unsupervised models, and highlights the sensitivity of unsupervised models to sample distributions. We additionally introduce and evaluate an adversarial training method that improves testing performance in adversarial scenarios, and we highlight the importance of various parameters in the proposed training method, such as continuous learning, centroid initialisation, and adversarial step-count.
Authors: Blake Gella, Howard Zhang, Rishi Upadhyay, Tiffany Chang, Matthew Waliman, Yunhao Ba, Alex Wong, Achuta Kadambi
The introduction of large, foundational models to computer vision has led to drastically improved performance on the task of semantic segmentation. However, these existing methods exhibit a large performance drop when testing on images degraded by weather conditions such as rain, fog, or snow. We introduce a general paired-training method that can be applied to all current foundational model architectures that leads to improved performance on images in adverse weather conditions. To this end, we create the WeatherProof Dataset, the first semantic segmentation dataset with accurate clear and adverse weather image pairs, which not only enables our new training paradigm, but also improves the evaluation of the performance gap between clear and degraded segmentation. We find that training on these paired clear and adverse weather frames which share an underlying scene results in improved performance on adverse weather data. With this knowledge, we propose a training pipeline which accentuates the advantages of paired-data training using consistency losses and language guidance, which leads to performance improvements by up to 18.4% as compared to standard training procedures.
Authors: Yuhang Ming, Jian Ma, Xingrui Yang, Weichen Dai, Yong Peng, Wanzeng Kong
We present AEGIS-Net, a novel indoor place recognition model that takes in RGB point clouds and generates global place descriptors by aggregating lower-level color, geometry features and higher-level implicit semantic features. However, rather than simple feature concatenation, self-attention modules are employed to select the most important local features that best describe an indoor place. Our AEGIS-Net is made of a semantic encoder, a semantic decoder and an attention-guided feature embedding. The model is trained in a 2-stage process with the first stage focusing on an auxiliary semantic segmentation task and the second one on the place recognition task. We evaluate our AEGIS-Net on the ScanNetPR dataset and compare its performance with a pre-deep-learning feature-based method and five state-of-the-art deep-learning-based methods. Our AEGIS-Net achieves exceptional performance and outperforms all six methods.
Authors: Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong, Tae-Hyun Oh
Video motion magnification amplifies invisible small motions to be perceptible, which provides humans with spatially dense and holistic understanding about small motions from the scene of interest. This is based on the premise that magnifying small motions enhances the legibility of the motion. In the real world, however, vibrating objects often possess complex systems, having complex natural frequencies, modes, and directions. Existing motion magnification often fails to improve the legibility since the intricate motions still retain complex characteristics even when magnified, which distracts us from analyzing them. In this work, we focus on improving the legibility by proposing a new concept, axial motion magnification, which magnifies decomposed motions along the user-specified direction. Axial motion magnification can be applied to various applications where motions of specific axes are critical, by providing simplified and easily readable motion information. We propose a novel learning-based axial motion magnification method with the Motion Separation Module that enables to disentangle and magnify the motion representation along axes of interest. Further, we build a new synthetic training dataset for the axial motion magnification task. Our proposed method improves the legibility of resulting motions along certain axes, while adding additional user controllability. Our method can be directly adopted to the generic motion magnification and achieves favorable performance against competing methods. Our project page is available at https://axial-momag.github.io/axial-momag/.
Authors: Shuanghao Bai, Min Zhang, Wanqi Zhou, Siteng Huang, Zhirong Luan, Donglin Wang, Badong Chen
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.
Authors: Yitong Sun, Yao Huang, Xingxing Wei
As physical adversarial attacks become extensively applied in unearthing the potential risk of security-critical scenarios, especially in autonomous driving, their vulnerability to environmental changes has also been brought to light. The non-robust nature of physical adversarial attack methods brings less-than-stable performance consequently. To enhance the robustness of physical adversarial attacks in the real world, instead of statically optimizing a robust adversarial example via an off-line training manner like the existing methods, this paper proposes a brand new robust adversarial attack framework: Embodied Adversarial Attack (EAA) from the perspective of dynamic adaptation, which aims to employ the paradigm of embodied intelligence: Perception-Decision-Control to dynamically adjust the optimal attack strategy according to the current situations in real time. For the perception module, given the challenge of needing simulation for the victim's viewpoint, EAA innovatively devises a Perspective Transformation Network to estimate the target's transformation from the attacker's perspective. For the decision and control module, EAA adopts the laser-a highly manipulable medium to implement physical attacks, and further trains an attack agent with reinforcement learning to make it capable of instantaneously determining the best attack strategy based on the perceived information. Finally, we apply our framework to the autonomous driving scenario. A variety of experiments verify the high effectiveness of our method under complex scenes.
Authors: Yao Huang, Yinpeng Dong, Shouwei Ruan, Xiao Yang, Hang Su, Xingxing Wei
Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D adversarial samples, due to their potential of multi-view robustness, can more comprehensively identify weaknesses in existing deep learning systems, possessing great application value. However, the field of transferable targeted 3D adversarial attacks remains vacant. The goal of this work is to develop a more effective technique that could generate transferable targeted 3D adversarial examples, filling the gap in this field. To achieve this goal, we design a novel framework named TT3D that could rapidly reconstruct from few multi-view images into Transferable Targeted 3D textured meshes. While existing mesh-based texture optimization methods compute gradients in the high-dimensional mesh space and easily fall into local optima, leading to unsatisfactory transferability and distinct distortions, TT3D innovatively performs dual optimization towards both feature grid and Multi-layer Perceptron (MLP) parameters in the grid-based NeRF space, which significantly enhances black-box transferability while enjoying naturalness. Experimental results show that TT3D not only exhibits superior cross-model transferability but also maintains considerable adaptability across different renders and vision tasks. More importantly, we produce 3D adversarial examples with 3D printing techniques in the real world and verify their robust performance under various scenarios.
Authors: Jiayi Liu, Hou In Ivan Tam, Ali Mahdavi-Amiri, Manolis Savva
We address the challenge of generating 3D articulated objects in a controllable fashion. Currently, modeling articulated 3D objects is either achieved through laborious manual authoring, or using methods from prior work that are hard to scale and control directly. We leverage the interplay between part shape, connectivity, and motion using a denoising diffusion-based method with attention modules designed to extract correlations between part attributes. Our method takes an object category label and a part connectivity graph as input and generates an object's geometry and motion parameters. The generated objects conform to user-specified constraints on the object category, part shape, and part articulation. Our experiments show that our method outperforms the state-of-the-art in articulated object generation, producing more realistic objects while conforming better to user constraints.
Video Summary at: this http URL
Authors: Xiangde Luo, Jia Fu, Yunxin Zhong, Shuolin Liu, Bing Han, Mehdi Astaraki, Simone Bendazzoli, Iuliana Toma-Dasu, Yiwen Ye, Ziyang Chen, Yong Xia, Yanzhou Su, Jin Ye, Junjun He, Zhaohu Xing, Hongqiu Wang, Lei Zhu, Kaixiang Yang, Xin Fang, Zhiwei Wang, Chan Woong Lee, Sang Joon Park, Jaehee Chun, Constantin Ulrich, Klaus H. Maier-Hein, Nchongmaje Ndipenoch, Alina Miron, Yongmin Li, Yimeng Zhang, Yu Chen, Lu Bai, Jinlong Huang, Chengyang An, Lisheng Wang, Kaiwen Huang, Yunqi Gu, Tao Zhou, Mu Zhou, Shichuan Zhang, Wenjun Liao, Guotai Wang, Shaoting Zhang
Radiation therapy is a primary and effective NasoPharyngeal Carcinoma (NPC) treatment strategy. The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis. Previously, the delineation of GTVs and OARs was performed by experienced radiation oncologists. Recently, deep learning has achieved promising results in many medical image segmentation tasks. However, for NPC OARs and GTVs segmentation, few public datasets are available for model development and evaluation. To alleviate this problem, the SegRap2023 challenge was organized in conjunction with MICCAI2023 and presented a large-scale benchmark for OAR and GTV segmentation with 400 Computed Tomography (CT) scans from 200 NPC patients, each with a pair of pre-aligned non-contrast and contrast-enhanced CT scans. The challenge's goal was to segment 45 OARs and 2 GTVs from the paired CT scans. In this paper, we detail the challenge and analyze the solutions of all participants. The average Dice similarity coefficient scores for all submissions ranged from 76.68\% to 86.70\%, and 70.42\% to 73.44\% for OARs and GTVs, respectively. We conclude that the segmentation of large-size OARs is well-addressed, and more efforts are needed for GTVs and small-size or thin-structure OARs. The benchmark will remain publicly available here: https://segrap2023.grand-challenge.org
Authors: Chaoning Zhang, Dongshen Han, Sheng Zheng, Jinwoo Choi, Tae-Ho Kim, Choong Seon Hong
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)}, which predicts the masks for all objects on the image. What makes SegAny slow for SAM is its heavyweight image encoder, which has been addressed by MobileSAM via decoupled knowledge distillation. The efficiency bottleneck of SegEvery with SAM, however, lies in its mask decoder because it needs to first generate numerous masks with redundant grid-search prompts and then perform filtering to obtain the final valid masks. We propose to improve its efficiency by directly generating the final masks with only valid prompts, which can be obtained through object discovery. Our proposed approach not only helps reduce the total time on the mask decoder by at least 16 times but also achieves superior performance. Specifically, our approach yields an average performance boost of 3.6\% (42.5\% \textit{v.s.} 38.9\%) for zero-shot object proposal on the LVIS dataset with the mask AR@$K$ metric. Qualitative results show that our approach generates fine-grained masks while avoiding over-segmenting things. This project targeting faster SegEvery than the original SAM is termed MobileSAMv2 to differentiate from MobileSAM which targets faster SegAny. Moreover, we demonstrate that our new prompt sampling is also compatible with the distilled image encoders in MobileSAM, contributing to a unified framework for efficient SegAny and SegEvery. The code is available at the same link as MobileSAM Project \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{https://github.com/ChaoningZhang/MobileSAM}}. \end{abstract}
Authors: David Kim, Sinhae Cha, Byeongkeun Kang
This work addresses the task of weakly-supervised object localization. The goal is to learn object localization using only image-level class labels, which are much easier to obtain compared to bounding box annotations. This task is important because it reduces the need for labor-intensive ground-truth annotations. However, methods for object localization trained using weak supervision often suffer from limited accuracy in localization. To address this challenge and enhance localization accuracy, we propose a multiscale object localization transformer (MOLT). It comprises multiple object localization transformers that extract patch embeddings across various scales. Moreover, we introduce a deep clustering-guided refinement method that further enhances localization accuracy by utilizing separately extracted image segments. These segments are obtained by clustering pixels using convolutional neural networks. Finally, we demonstrate the effectiveness of our proposed method by conducting experiments on the publicly available ILSVRC-2012 dataset.
Authors: Shuanghao Bai, Wanqi Zhou, Zhirong Luan, Donglin Wang, Badong Chen
Cross-domain few-shot classification (CDFSC) is a challenging and tough task due to the significant distribution discrepancies across different domains. To address this challenge, many approaches aim to learn transferable representations. Multilayer perceptron (MLP) has shown its capability to learn transferable representations in various downstream tasks, such as unsupervised image classification and supervised concept generalization. However, its potential in the few-shot settings has yet to be comprehensively explored. In this study, we investigate the potential of MLP to assist in addressing the challenges of CDFSC. Specifically, we introduce three distinct frameworks incorporating MLP in accordance with three types of few-shot classification methods to verify the effectiveness of MLP. We reveal that MLP can significantly enhance discriminative capabilities and alleviate distribution shifts, which can be supported by our expensive experiments involving 10 baseline models and 12 benchmark datasets. Furthermore, our method even compares favorably against other state-of-the-art CDFSC algorithms.
Authors: Shizhan Liu, Zhengkai Jiang, Yuxi Li, Jinlong Peng, Yabiao Wang, Weiyao Lin
Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation. However, existing works usually ignore the correlation between selected samples and its local context in feature space, which leads to inferior usage of annotation budgets. In this work, we revisit the theoretical bound of the classical Core-set method and identify that the performance is closely related to the local sample distribution around selected samples. To estimate the density of local samples efficiently, we introduce a local proxy estimator with Dynamic Masked Convolution and develop a Density-aware Greedy algorithm to optimize the bound. Extensive experiments demonstrate the superiority of our approach. Moreover, with very few labels, our scheme achieves comparable performance to the fully supervised counterpart.
Authors: Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan
Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular applications with few labeled data and abundant unlabeled data. One common manner is assigning pseudo-labels to unlabeled samples and selecting positive and negative samples from pseudo-labeled samples to apply contrastive learning. However, the real-world data may be imbalanced, causing pseudo-labels to be biased toward the majority classes and further undermining the effectiveness of contrastive learning. To address the challenge, we propose Contrastive Learning with Augmented Features (CLAF). We design a class-dependent feature augmentation module to alleviate the scarcity of minority class samples in contrastive learning. For each pseudo-labeled sample, we select positive and negative samples from labeled data instead of unlabeled data to compute contrastive loss. Comprehensive experiments on imbalanced image classification datasets demonstrate the effectiveness of CLAF in the context of imbalanced semi-supervised learning.
Authors: Senmao Li, Taihang Hu, Fahad Shahbaz Khan, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, Jian Yang
One of the key components within diffusion models is the UNet for noise prediction. While several works have explored basic properties of the UNet decoder, its encoder largely remains unexplored. In this work, we conduct the first comprehensive study of the UNet encoder. We empirically analyze the encoder features and provide insights to important questions regarding their changes at the inference process. In particular, we find that encoder features change gently, whereas the decoder features exhibit substantial variations across different time-steps. This finding inspired us to omit the encoder at certain adjacent time-steps and reuse cyclically the encoder features in the previous time-steps for the decoder. Further based on this observation, we introduce a simple yet effective encoder propagation scheme to accelerate the diffusion sampling for a diverse set of tasks. By benefiting from our propagation scheme, we are able to perform in parallel the decoder at certain adjacent time-steps. Additionally, we introduce a prior noise injection method to improve the texture details in the generated image. Besides the standard text-to-image task, we also validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation. Without utilizing any knowledge distillation technique, our approach accelerates both the Stable Diffusion (SD) and the DeepFloyd-IF models sampling by 41$\%$ and 24$\%$ respectively, while maintaining high-quality generation performance. Our code is available in \href{https://github.com/hutaiHang/Faster-Diffusion}{FasterDiffusion}.
Authors: Guo-Ye Yang, George Kiyohiro Nakayama, Zi-Kai Xiao, Tai-Jiang Mu, Xiaolei Huang, Shi-Min Hu
Great progress has been made in learning-based object detection methods in the last decade. Two-stage detectors often have higher detection accuracy than one-stage detectors, due to the use of region of interest (RoI) feature extractors which extract transformation-invariant RoI features for different RoI proposals, making refinement of bounding boxes and prediction of object categories more robust and accurate. However, previous RoI feature extractors can only extract invariant features under limited transformations. In this paper, we propose a novel RoI feature extractor, termed Semantic RoI Align (SRA), which is capable of extracting invariant RoI features under a variety of transformations for two-stage detectors. Specifically, we propose a semantic attention module to adaptively determine different sampling areas by leveraging the global and local semantic relationship within the RoI. We also propose a Dynamic Feature Sampler which dynamically samples features based on the RoI aspect ratio to enhance the efficiency of SRA, and a new position embedding, \ie Area Embedding, to provide more accurate position information for SRA through an improved sampling area representation. Experiments show that our model significantly outperforms baseline models with slight computational overhead. In addition, it shows excellent generalization ability and can be used to improve performance with various state-of-the-art backbones and detection methods.
Authors: Yuhao Wang, Xuehu Liu, Pingping Zhang, Hu Lu, Zhengzheng Tu, Huchuan Lu
Multi-spectral object Re-identification (ReID) aims to retrieve specific objects by leveraging complementary information from different image spectra. It delivers great advantages over traditional single-spectral ReID in complex visual environment. However, the significant distribution gap among different image spectra poses great challenges for effective multi-spectral feature representations. In addition, most of current Transformer-based ReID methods only utilize the global feature of class tokens to achieve the holistic retrieval, ignoring the local discriminative ones. To address the above issues, we step further to utilize all the tokens of Transformers and propose a cyclic token permutation framework for multi-spectral object ReID, dubbled TOP-ReID. More specifically, we first deploy a multi-stream deep network based on vision Transformers to preserve distinct information from different image spectra. Then, we propose a Token Permutation Module (TPM) for cyclic multi-spectral feature aggregation. It not only facilitates the spatial feature alignment across different image spectra, but also allows the class token of each spectrum to perceive the local details of other spectra. Meanwhile, we propose a Complementary Reconstruction Module (CRM), which introduces dense token-level reconstruction constraints to reduce the distribution gap across different image spectra. With the above modules, our proposed framework can generate more discriminative multi-spectral features for robust object ReID. Extensive experiments on three ReID benchmarks (i.e., RGBNT201, RGBNT100 and MSVR310) verify the effectiveness of our methods. The code is available at https://github.com/924973292/TOP-ReID.
Authors: Xiaoxu Xu, Yitian Yuan, Qiudan Zhang, Wenhui Wu, Zequn Jie, Lin Ma, Xu Wang
Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual grounding approaches require a substantial number of bounding box annotations for text queries, which is time-consuming and labor-intensive to obtain. In this paper, we propose \textbf{3D-VLA}, a weakly supervised approach for \textbf{3D} visual grounding based on \textbf{V}isual \textbf{L}inguistic \textbf{A}lignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models (VLMs) on aligning the semantics between texts and 2D images, as well as the naturally existing correspondences between 2D images and 3D point clouds, and thus implicitly constructs correspondences between texts and 3D point clouds with no need for fine-grained box annotations in the training procedure. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images. To the best of our knowledge, this is the first work to investigate 3D visual grounding in a weakly supervised manner by involving large scale vision-language models, and extensive experiments on ReferIt3D and ScanRefer datasets demonstrate that our 3D-VLA achieves comparable and even superior results over the fully supervised methods.
Authors: Chenyang Yu, Xuehu Liu, Yingquan Wang, Pingping Zhang, Huchuan Lu
Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based person re-identification (ReID) has barely been explored. In addition, there is a lack of decent text descriptions in current ReID benchmarks. To address these issues, in this work, we propose a novel one-stage text-free CLIP-based learning framework named TF-CLIP for video-based person ReID. More specifically, we extract the identity-specific sequence feature as the CLIP-Memory to replace the text feature. Meanwhile, we design a Sequence-Specific Prompt (SSP) module to update the CLIP-Memory online. To capture temporal information, we further propose a Temporal Memory Diffusion (TMD) module, which consists of two key components: Temporal Memory Construction (TMC) and Memory Diffusion (MD). Technically, TMC allows the frame-level memories in a sequence to communicate with each other, and to extract temporal information based on the relations within the sequence. MD further diffuses the temporal memories to each token in the original features to obtain more robust sequence features. Extensive experiments demonstrate that our proposed method shows much better results than other state-of-the-art methods on MARS, LS-VID and iLIDS-VID. The code is available at https://github.com/AsuradaYuci/TF-CLIP.
Authors: Renxiang Guan, Zihao Li, Xianju Li, Chang Tang
Hyperspectral image (HSI) clustering is gaining considerable attention owing to recent methods that overcome the inefficiency and misleading results from the absence of supervised information. Contrastive learning methods excel at existing pixel level and super pixel level HSI clustering tasks. The pixel-level contrastive learning method can effectively improve the ability of the model to capture fine features of HSI but requires a large time overhead. The super pixel-level contrastive learning method utilizes the homogeneity of HSI and reduces computing resources; however, it yields rough classification results. To exploit the strengths of both methods, we present a pixel super pixel contrastive learning and pseudo-label correction (PSCPC) method for the HSI clustering. PSCPC can reasonably capture domain-specific and fine-grained features through super pixels and the comparative learning of a small number of pixels within the super pixels. To improve the clustering performance of super pixels, this paper proposes a pseudo-label correction module that aligns the clustering pseudo-labels of pixels and super-pixels. In addition, pixel-level clustering results are used to supervise super pixel-level clustering, improving the generalization ability of the model. Extensive experiments demonstrate the effectiveness and efficiency of PSCPC.
Authors: Jiajun Zhang, Yuxiang Zhang, Hongwen Zhang, Boyao Zhou, Ruizhi Shao, Zonghai Hu, Yebin Liu
Recovering detailed interactions between humans/hands and objects is an appealing yet challenging task. Existing methods typically use template-based representations to track human/hand and objects in interactions. Despite the progress, they fail to handle the invisible contact surfaces. In this paper, we propose Ins-HOI, an end-to-end solution to recover human/hand-object reconstruction via instance-level implicit reconstruction. To this end, we introduce an instance-level occupancy field to support simultaneous human/hand and object representation, and a complementary training strategy to handle the lack of instance-level ground truths. Such a representation enables learning a contact prior implicitly from sparse observations. During the complementary training, we augment the real-captured data with synthesized data by randomly composing individual scans of humans/hands and objects and intentionally allowing for penetration. In this way, our network learns to recover individual shapes as completely as possible from the synthesized data, while being aware of the contact constraints and overall reasonability based on real-captured scans. As demonstrated in experiments, our method Ins-HOI can produce reasonable and realistic non-visible contact surfaces even in cases of extremely close interaction. To facilitate the research of this task, we collect a large-scale, high-fidelity 3D scan dataset, including 5.2k high-quality scans with real-world human-chair and hand-object interactions. We will release our dataset and source codes. Data examples and the video results of our method can be found on the project page.
Authors: Xiaoming Wang, Zhiguo Gong
Robot calligraphy is an emerging exploration of artificial intelligence in the fields of art and education. Traditional calligraphy generation researches mainly focus on methods such as tool-based image processing, generative models, and style transfer. Unlike the English alphabet, the number of Chinese characters is tens of thousands, which leads to difficulties in the generation of a style consistent Chinese calligraphic font with over 6000 characters. Due to the lack of high-quality data sets, formal definitions of calligraphy knowledge, and scientific art evaluation methods, The results generated are frequently of low quality and falls short of professional-level requirements. To address the above problem, this paper proposes an automatic calligraphy generation model based on deep generative adversarial networks (deepGAN) that can generate style calligraphy fonts with professional standards. The key highlights of the proposed method include: (1) The datasets use a high-precision calligraphy synthesis method to ensure its high quality and sufficient quantity; (2) Professional calligraphers are invited to conduct a series of Turing tests to evaluate the gap between model generation results and human artistic level; (3) Experimental results indicate that the proposed model is the state-of-the-art among current calligraphy generation methods. The Turing tests and similarity evaluations validate the effectiveness of the proposed method.
Authors: Leon Mlodzian, Zhigang Sun, Hendrik Berkemeyer, Sebastian Monka, Zixu Wang, Stefan Dietze, Lavdim Halilaj, Juergen Luettin
Trajectory prediction in traffic scenes involves accurately forecasting the behaviour of surrounding vehicles. To achieve this objective it is crucial to consider contextual information, including the driving path of vehicles, road topology, lane dividers, and traffic rules. Although studies demonstrated the potential of leveraging heterogeneous context for improving trajectory prediction, state-of-the-art deep learning approaches still rely on a limited subset of this information. This is mainly due to the limited availability of comprehensive representations. This paper presents an approach that utilizes knowledge graphs to model the diverse entities and their semantic connections within traffic scenes. Further, we present nuScenes Knowledge Graph (nSKG), a knowledge graph for the nuScenes dataset, that models explicitly all scene participants and road elements, as well as their semantic and spatial relationships. To facilitate the usage of the nSKG via graph neural networks for trajectory prediction, we provide the data in a format, ready-to-use by the PyG library. All artefacts can be found here: https://github.com/boschresearch/nuScenes_Knowledge_Graph
Authors: Zechen Li, Weiming Huang, Kai Zhao, Min Yang, Yongshun Gong, Meng Chen
Recently, learning urban region representations utilizing multi-modal data (information views) has become increasingly popular, for deep understanding of the distributions of various socioeconomic features in cities. However, previous methods usually blend multi-view information in a posteriors stage, falling short in learning coherent and consistent representations across different views. In this paper, we form a new pipeline to learn consistent representations across varying views, and propose the multi-view Contrastive Prediction model for urban Region embedding (ReCP), which leverages the multiple information views from point-of-interest (POI) and human mobility data. Specifically, ReCP comprises two major modules, namely an intra-view learning module utilizing contrastive learning and feature reconstruction to capture the unique information from each single view, and inter-view learning module that perceives the consistency between the two views using a contrastive prediction learning scheme. We conduct thorough experiments on two downstream tasks to assess the proposed model, i.e., land use clustering and region popularity prediction. The experimental results demonstrate that our model outperforms state-of-the-art baseline methods significantly in urban region representation learning.
Authors: Selcuk Anil Karatopak, Deniz Sen
Many species face the threat of extinction. It's important to study these species and gather information about them as much as possible to preserve biodiversity. Due to the rarity of endangered species, there is a limited amount of data available, making it difficult to apply data requiring generative AI methods to this domain. We aim to study the feasibility of generating consistent and real-like 3D models of endangered animals using limited data. Such a phenomenon leads us to utilize zero-shot stable diffusion models that can generate a 3D model out of a single image of the target species. This paper investigates the intricate relationship between elevation angle and the output quality of 3D model generation, focusing on the innovative approach presented in DreamGaussian. DreamGaussian, a novel framework utilizing Generative Gaussian Splatting along with novel mesh extraction and refinement algorithms, serves as the focal point of our study. We conduct a comprehensive analysis, analyzing the effect of varying elevation angles on DreamGaussian's ability to reconstruct 3D scenes accurately. Through an empirical evaluation, we demonstrate how changes in elevation angle impact the generated images' spatial coherence, structural integrity, and perceptual realism. We observed that giving a correct elevation angle with the input image significantly affects the result of the generated 3D model. We hope this study to be influential for the usability of AI to preserve endangered animals; while the penultimate aim is to obtain a model that can output biologically consistent 3D models via small samples, the qualitative interpretation of an existing state-of-the-art model such as DreamGaussian will be a step forward in our goal.
Authors: Jingcai Guo, Qihua Zhou, Ruibing Li, Xiaocheng Lu, Ziming Liu, Junyang Chen, Xin Xie, Jie Zhang
This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL), dubbed ParsNets, where we are interested in learning a composition of on-device friendly linear networks, each with orthogonality and low-rankness properties, to achieve equivalent or even better performance against existing deep models. Concretely, we first refactor the core module of ZSL, i.e., visual-semantics mapping function, into several base linear networks that correspond to diverse components of the semantic space, where the complex nonlinearity can be collapsed into simple local linearities. Then, to facilitate the generalization of local linearities, we construct a maximal margin geometry on the learned features by enforcing low-rank constraints on intra-class samples and high-rank constraints on inter-class samples, resulting in orthogonal subspaces for different classes and each subspace lies on a compact manifold. To enhance the model's adaptability and counterbalance over/under-fittings in ZSL, a set of sample-wise indicators is employed to select a sparse subset from these base linear networks to form a composite semantic predictor for each sample. Notably, maximal margin geometry can guarantee the diversity of features, and meanwhile, local linearities guarantee efficiency. Thus, our ParsNets can generalize better to unseen classes and can be deployed flexibly on resource-constrained devices. Theoretical explanations and extensive experiments are conducted to verify the effectiveness of the proposed method.
Authors: Zhe Ma, Jianfeng Dong, Shouling Ji, Zhenguang Liu, Xuhong Zhang, Zonghui Wang, Sifeng He, Feng Qian, Xiaobo Zhang, Lei Yang
Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval. Furthermore, we discover that the similarities obtained by different retrieval models are diversified and incommensurable, which makes it challenging to jointly distill knowledge from multiple models. Therefore, we propose to whiten the output of teacher models before fusion, which enables effective multi-teacher distillation for retrieval models. Whiten-MTD is conceptually simple and practically effective. Extensive experiments on two landmark image retrieval datasets and one video retrieval dataset demonstrate the effectiveness of our proposed method, and its good balance of retrieval performance and efficiency. Our source code is released at https://github.com/Maryeon/whiten_mtd.
Authors: Alexander Kurz, Hendrik A. Mehrtens, Tabea-Clara Bucher, Titus J. Brinker
Deep Neural Networks have shown promising classification performance when predicting certain biomarkers from Whole Slide Images in digital pathology. However, the calibration of the networks' output probabilities is often not evaluated. Communicating uncertainty by providing reliable confidence scores is of high relevance in the medical context. In this work, we compare three neural network architectures that combine feature representations on patch-level to a slide-level prediction with respect to their classification performance and evaluate their calibration. As slide-level classification task, we choose the prediction of Microsatellite Instability from Colorectal Cancer tissue sections. We observe that Transformers lead to good results in terms of classification performance and calibration. When evaluating the classification performance on a separate dataset, we observe that Transformers generalize best. The investigation of reliability diagrams provides additional insights to the Expected Calibration Error metric and we observe that especially Transformers push the output probabilities to extreme values, which results in overconfident predictions.
Authors: Matteo Dunnhofer, Luca Sordi, Niki Martinel, Christian Micheloni
Skiing is a popular winter sport discipline with a long history of competitive events. In this domain, computer vision has the potential to enhance the understanding of athletes' performance, but its application lags behind other sports due to limited studies and datasets. This paper makes a step forward in filling such gaps. A thorough investigation is performed on the task of skier tracking in a video capturing his/her complete performance. Obtaining continuous and accurate skier localization is preemptive for further higher-level performance analyses. To enable the study, the largest and most annotated dataset for computer vision in skiing, SkiTB, is introduced. Several visual object tracking algorithms, including both established methodologies and a newly introduced skier-optimized baseline algorithm, are tested using the dataset. The results provide valuable insights into the applicability of different tracking methods for vision-based skiing analysis. SkiTB, code, and results are available at https://machinelearning.uniud.it/datasets/skitb.
Authors: Hendrik Laux, Emil Mededovic, Ahmed Hallawa, Lukas Martin, Arne Peine, Anke Schmeink
This paper proposes a novel, resource-efficient approach to Visual Speech Recognition (VSR) leveraging speech representations produced by any trained Automatic Speech Recognition (ASR) model. Moving away from the resource-intensive trends prevalent in recent literature, our method distills knowledge from a trained Conformer-based ASR model, achieving competitive performance on standard VSR benchmarks with significantly less resource utilization. Using unlabeled audio-visual data only, our baseline model achieves a word error rate (WER) of 47.4% and 54.7% on the LRS2 and LRS3 test benchmarks, respectively. After fine-tuning the model with limited labeled data, the word error rate reduces to 35% (LRS2) and 45.7% (LRS3). Our model can be trained on a single consumer-grade GPU within a few days and is capable of performing real-time end-to-end VSR on dated hardware, suggesting a path towards more accessible and resource-efficient VSR methodologies.
Authors: Qi-Yuan Feng, Hao-Xiang Chen, Qun-Ce Xu, Tai-Jiang Mu
Neural radiance field (NeRF) has achieved great success in novel view synthesis and 3D representation for static scenarios. Existing dynamic NeRFs usually exploit a locally dense grid to fit the deformation field; however, they fail to capture the global dynamics and concomitantly yield models of heavy parameters. We observe that the 4D space is inherently sparse. Firstly, the deformation field is sparse in spatial but dense in temporal due to the continuity of of motion. Secondly, the radiance field is only valid on the surface of the underlying scene, usually occupying a small fraction of the whole space. We thus propose to represent the 4D scene using a learnable sparse latent space, a.k.a. SLS4D. Specifically, SLS4D first uses dense learnable time slot features to depict the temporal space, from which the deformation field is fitted with linear multi-layer perceptions (MLP) to predict the displacement of a 3D position at any time. It then learns the spatial features of a 3D position using another sparse latent space. This is achieved by learning the adaptive weights of each latent code with the attention mechanism. Extensive experiments demonstrate the effectiveness of our SLS4D: it achieves the best 4D novel view synthesis using only about $6\%$ parameters of the most recent work.
Authors: Andre Rochow, Max Schwarz, Sven Behnke
Facial animation in virtual reality environments is essential for applications that necessitate clear visibility of the user's face and the ability to convey emotional signals. In our scenario, we animate the face of an operator who controls a robotic Avatar system. The use of facial animation is particularly valuable when the perception of interacting with a specific individual, rather than just a robot, is intended. Purely keypoint-driven animation approaches struggle with the complexity of facial movements. We present a hybrid method that uses both keypoints and direct visual guidance from a mouth camera. Our method generalizes to unseen operators and requires only a quick enrolment step with capture of two short videos. Multiple source images are selected with the intention to cover different facial expressions. Given a mouth camera frame from the HMD, we dynamically construct the target keypoints and apply an attention mechanism to determine the importance of each source image. To resolve keypoint ambiguities and animate a broader range of mouth expressions, we propose to inject visual mouth camera information into the latent space. We enable training on large-scale speaking head datasets by simulating the mouth camera input with its perspective differences and facial deformations. Our method outperforms a baseline in quality, capability, and temporal consistency. In addition, we highlight how the facial animation contributed to our victory at the ANA Avatar XPRIZE Finals.
Authors: Dennis Hein, Staffan Holmin, Timothy Szczykutowicz, Jonathan S Maltz, Mats Danielsson, Ge Wang, Mats Persson
Diffusion and Poisson flow models have shown impressive performance in a wide range of generative tasks, including low-dose CT image denoising. However, one limitation in general, and for clinical applications in particular, is slow sampling. Due to their iterative nature, the number of function evaluations (NFE) required is usually on the order of $10-10^3$, both for conditional and unconditional generation. In this paper, we present posterior sampling Poisson flow generative models (PPFM), a novel image denoising technique for low-dose and photon-counting CT that produces excellent image quality whilst keeping NFE=1. Updating the training and sampling processes of Poisson flow generative models (PFGM)++, we learn a conditional generator which defines a trajectory between the prior noise distribution and the posterior distribution of interest. We additionally hijack and regularize the sampling process to achieve NFE=1. Our results shed light on the benefits of the PFGM++ framework compared to diffusion models. In addition, PPFM is shown to perform favorably compared to current state-of-the-art diffusion-style models with NFE=1, consistency models, as well as popular deep learning and non-deep learning-based image denoising techniques, on clinical low-dose CT images and clinical images from a prototype photon-counting CT system.
Authors: Yifeng Ma, Shiwei Zhang, Jiayu Wang, Xiang Wang, Yingya Zhang, Zhidong Deng
Diffusion models have shown remarkable success in a variety of downstream generative tasks, yet remain under-explored in the important and challenging expressive talking head generation. In this work, we propose a DreamTalk framework to fulfill this gap, which employs meticulous design to unlock the potential of diffusion models in generating expressive talking heads. Specifically, DreamTalk consists of three crucial components: a denoising network, a style-aware lip expert, and a style predictor. The diffusion-based denoising network is able to consistently synthesize high-quality audio-driven face motions across diverse expressions. To enhance the expressiveness and accuracy of lip motions, we introduce a style-aware lip expert that can guide lip-sync while being mindful of the speaking styles. To eliminate the need for expression reference video or text, an extra diffusion-based style predictor is utilized to predict the target expression directly from the audio. By this means, DreamTalk can harness powerful diffusion models to generate expressive faces effectively and reduce the reliance on expensive style references. Experimental results demonstrate that DreamTalk is capable of generating photo-realistic talking faces with diverse speaking styles and achieving accurate lip motions, surpassing existing state-of-the-art counterparts.
Authors: Benno Buschmann, Andreea Dogaru, Elmar Eisemann, Michael Weinmann, Bernhard Egger
We introduce RANRAC, a robust reconstruction algorithm for 3D objects handling occluded and distracted images, which is a particularly challenging scenario that prior robust reconstruction methods cannot deal with. Our solution supports single-shot reconstruction by involving light-field networks, and is also applicable to photo-realistic, robust, multi-view reconstruction from real-world images based on neural radiance fields. While the algorithm imposes certain limitations on the scene representation and, thereby, the supported scene types, it reliably detects and excludes inconsistent perspectives, resulting in clean images without floating artifacts. Our solution is based on a fuzzy adaption of the random sample consensus paradigm, enabling its application to large scale models. We interpret the minimal number of samples to determine the model parameters as a tunable hyperparameter. This is applicable, as a cleaner set of samples improves reconstruction quality. Further, this procedure also handles outliers. Especially for conditioned models, it can result in the same local minimum in the latent space as would be obtained with a completely clean set. We report significant improvements for novel-view synthesis in occluded scenarios, of up to 8dB PSNR compared to the baseline.
Authors: Tom Nuno Wolf, Fabian Bongratz, Anne-Marie Rickmann, Sebastian Pölsterl, Christian Wachinger
Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations based on similar examples. To this end, ProtoPNet learns a set of class-representative feature vectors (prototypes) for case-based reasoning. During inference, similarities of latent features to prototypes are linearly classified to form predictions and attribution maps are provided to explain the similarity. In this work, we evaluate whether architectures for case-based reasoning fulfill established axioms required for faithful explanations using the example of ProtoPNet. We show that such architectures allow the extraction of faithful explanations. However, we prove that the attribution maps used to explain the similarities violate the axioms. We propose a new procedure to extract explanations for trained ProtoPNets, named ProtoPFaith. Conceptually, these explanations are Shapley values, calculated on the similarity scores of each prototype. They allow to faithfully answer which prototypes are present in an unseen image and quantify each pixel's contribution to that presence, thereby complying with all axioms. The theoretical violations of ProtoPNet manifest in our experiments on three datasets (CUB-200-2011, Stanford Dogs, RSNA) and five architectures (ConvNet, ResNet, ResNet50, WideResNet50, ResNeXt50). Our experiments show a qualitative difference between the explanations given by ProtoPNet and ProtoPFaith. Additionally, we quantify the explanations with the Area Over the Perturbation Curve, on which ProtoPFaith outperforms ProtoPNet on all experiments by a factor $>10^3$.
Authors: Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGSS methods typically effectuate robust features by means of Domain Randomization (DR). Such an approach is often limited as it can only account for style diversification and not content. In this work, we take an orthogonal approach to DGSS and propose to use an assembly of CoLlaborative FOUndation models for Domain Generalized Semantic Segmentation (CLOUDS). In detail, CLOUDS is a framework that integrates FMs of various kinds: (i) CLIP backbone for its robust feature representation, (ii) generative models to diversify the content, thereby covering various modes of the possible target distribution, and (iii) Segment Anything Model (SAM) for iteratively refining the predictions of the segmentation model. Extensive experiments show that our CLOUDS excels in adapting from synthetic to real DGSS benchmarks and under varying weather conditions, notably outperforming prior methods by 5.6% and 6.7% on averaged miou, respectively. The code is available at : https://github.com/yasserben/CLOUDS
Authors: Pedro Osorio, Guillermo Jimenez-Perez, Javier Montalt-Tordera, Jens Hooge, Guillem Duran-Ballester, Shivam Singh, Moritz Radbruch, Ute Bach, Sabrina Schroeder, Krystyna Siudak, Julia Vienenkoetter, Bettina Lawrenz, Sadegh Mohammadi
Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fr\'echet Inception Distance (FID) from 178.8 to 90.2. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively trains AI models.
Authors: Shang Gao, Chenyang Yu, Pingping Zhang, Huchuan Lu
Occluded person re-identification (ReID) is a very challenging task due to the occlusion disturbance and incomplete target information. Leveraging external cues such as human pose or parsing to locate and align part features has been proven to be very effective in occluded person ReID. Meanwhile, recent Transformer structures have a strong ability of long-range modeling. Considering the above facts, we propose a Teacher-Student Decoder (TSD) framework for occluded person ReID, which utilizes the Transformer decoder with the help of human parsing. More specifically, our proposed TSD consists of a Parsing-aware Teacher Decoder (PTD) and a Standard Student Decoder (SSD). PTD employs human parsing cues to restrict Transformer's attention and imparts this information to SSD through feature distillation. Thereby, SSD can learn from PTD to aggregate information of body parts automatically. Moreover, a mask generator is designed to provide discriminative regions for better ReID. In addition, existing occluded person ReID benchmarks utilize occluded samples as queries, which will amplify the role of alleviating occlusion interference and underestimate the impact of the feature absence issue. Contrastively, we propose a new benchmark with non-occluded queries, serving as a complement to the existing benchmark. Extensive experiments demonstrate that our proposed method is superior and the new benchmark is essential. The source codes are available at https://github.com/hh23333/TSD.
Authors: Yu-Han Sun, Chiang Lo-Hsuan Lee, Tian-Sheuan Chang
Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41\%/15\% and 53\%/19\% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.
Authors: Simon Klenk, Marvin Motzet, Lukas Koestler, Daniel Cremers
Event cameras offer the exciting possibility of tracking the camera's pose during high-speed motion and in adverse lighting conditions. Despite this promise, existing event-based monocular visual odometry (VO) approaches demonstrate limited performance on recent benchmarks. To address this limitation, some methods resort to additional sensors such as IMUs, stereo event cameras, or frame-based cameras. Nonetheless, these additional sensors limit the application of event cameras in real-world devices since they increase cost and complicate system requirements. Moreover, relying on a frame-based camera makes the system susceptible to motion blur and HDR. To remove the dependency on additional sensors and to push the limits of using only a single event camera, we present Deep Event VO (DEVO), the first monocular event-only system with strong performance on a large number of real-world benchmarks. DEVO sparsely tracks selected event patches over time. A key component of DEVO is a novel deep patch selection mechanism tailored to event data. We significantly decrease the pose tracking error on seven real-world benchmarks by up to 97% compared to event-only methods and often surpass or are close to stereo or inertial methods. Code is available at https://github.com/tum-vision/DEVO
Authors: Xiao Wang, Wentao Wu, Chenglong Li, Zhicheng Zhao, Zhe Chen, Yukai Shi, Jin Tang
Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-train models on large-scale classification datasets and then fine-tune them for specific downstream tasks. However, they neglect the specific characteristics of vehicle perception in different tasks and might thus lead to sub-optimal performance. To address this issue, we propose a novel vehicle-centric pre-training framework called VehicleMAE, which incorporates the structural information including the spatial structure from vehicle profile information and the semantic structure from informative high-level natural language descriptions for effective masked vehicle appearance reconstruction. To be specific, we explicitly extract the sketch lines of vehicles as a form of the spatial structure to guide vehicle reconstruction. The more comprehensive knowledge distilled from the CLIP big model based on the similarity between the paired/unpaired vehicle image-text sample is further taken into consideration to help achieve a better understanding of vehicles. A large-scale dataset is built to pre-train our model, termed Autobot1M, which contains about 1M vehicle images and 12693 text information. Extensive experiments on four vehicle-based downstream tasks fully validated the effectiveness of our VehicleMAE. The source code and pre-trained models will be released at https://github.com/Event-AHU/VehicleMAE.
Authors: Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha
We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifies the fragility, robustness and antifragility characteristics of DNN parameters. Our proposed analysis investigates if the DNN performance is impacted negatively, invariantly, or positively on both clean and adversarially perturbed test datasets when the DNN undergoes synaptic filtering. We define three \textit{filtering scores} for quantifying the fragility, robustness and antifragility characteristics of DNN parameters based on the performances for (i) clean dataset, (ii) adversarial dataset, and (iii) the difference in performances of clean and adversarial datasets. We validate the proposed systematic analysis on ResNet-18, ResNet-50, SqueezeNet-v1.1 and ShuffleNet V2 x1.0 network architectures for MNIST, CIFAR10 and Tiny ImageNet datasets. The filtering scores, for a given network architecture, identify network parameters that are invariant in characteristics across different datasets over learning epochs. Vice-versa, for a given dataset, the filtering scores identify the parameters that are invariant in characteristics across different network architectures. We show that our synaptic filtering method improves the test accuracy of ResNet and ShuffleNet models on adversarial datasets when only the robust and antifragile parameters are selectively retrained at any given epoch, thus demonstrating applications of the proposed strategy in improving model robustness.
Authors: Pietro Bonazzi, Julian Moosmann, Yawei Li, Sizhen Bian, Michele Magno
This paper addresses the growing interest in deploying deep learning models directly in-sensor. We present "Q-Segment", a quantized real-time segmentation algorithm, and conduct a comprehensive evaluation on two low-power edge vision platforms, namely Sony IMX500, which has an in-sensors processor, and Sony Spresense, a low-power multi-core ARM Cortex-M microcontroller. One of the main goals of the model is to achieve end-to-end image segmentation for vessel-based medical diagnosis. Deployed on the IMX500 platform, Q-Segment achieves ultra-low inference time in-sensor of only 1.9 ms and energy consumption of only 5.7 mJ. We compare the proposed network with outperforming existing networks on various platforms by a factor of 75x (compared to ERFNet). The network architecture employs an encoder-decoder structure with skip connections, and results in a binary accuracy of 97.25% and an Area Under the Receiver Operating Characteristic Curve (AUC) of 96.97% on the CHASE dataset. This research contributes valuable insights into edge-based image segmentation, laying the foundation for efficient algorithms tailored to low-power environments.
Authors: Tianchen Deng, Guole Shen, Tong Qin, Jianyu Wang, Wentao Zhao, Jingchuan Wang, Danwei Wang, Weidong Chen
Neural implicit scene representations have recently shown encouraging results in dense visual SLAM. However, existing methods produce low-quality scene reconstruction and low-accuracy localization performance when scaling up to large indoor scenes and long sequences. These limitations are mainly due to their single, global radiance field with finite capacity, which does not adapt to large scenarios. Their end-to-end pose networks are also not robust enough with the growth of cumulative errors in large scenes. To this end, we present PLGSLAM, a neural visual SLAM system which performs high-fidelity surface reconstruction and robust camera tracking in real time. To handle large-scale indoor scenes, PLGSLAM proposes a progressive scene representation method which dynamically allocates new local scene representation trained with frames within a local sliding window. This allows us to scale up to larger indoor scenes and improves robustness (even under pose drifts). In local scene representation, PLGSLAM utilizes tri-planes for local high-frequency features. We also incorporate multi-layer perceptron (MLP) networks for the low-frequency feature, smoothness, and scene completion in unobserved areas. Moreover, we propose local-to-global bundle adjustment method with a global keyframe database to address the increased pose drifts on long sequences. Experimental results demonstrate that PLGSLAM achieves state-of-the-art scene reconstruction results and tracking performance across various datasets and scenarios (both in small and large-scale indoor environments). The code will be open-sourced upon paper acceptance.
Authors: Aditya Parikh
In this project we have designed and described a model which colourize a gray-scale image, with no human intervention. We propose a fully automatic process of colouring and re-colouring faded or gray-scale image with vibrant and pragmatic colours. We have used Convolutional Neural Network to hallucinate input images and feed-forwarded by training thousands of images. This approach results in trailblazing results.
Authors: Aditya Parikh
Process of information extraction (IE) is often used to extract meaningful information from unstructured and unlabeled data. Conventional methods of data extraction including application of OCR and passing extraction engine, are inefficient on large data and have their limitation. In this paper, a peculiar technique of information extraction is proposed using A2I and computer vision technologies, which also includes NLP.
Authors: Shengyi Hua, Fang Yan, Tianle Shen, Xiaofan Zhang
Large amounts of digitized histopathological data display a promising future for developing pathological foundation models via self-supervised learning methods. Foundation models pretrained with these methods serve as a good basis for downstream tasks. However, the gap between natural and histopathological images hinders the direct application of existing methods. In this work, we present PathoDuet, a series of pretrained models on histopathological images, and a new self-supervised learning framework in histopathology. The framework is featured by a newly-introduced pretext token and later task raisers to explicitly utilize certain relations between images, like multiple magnifications and multiple stains. Based on this, two pretext tasks, cross-scale positioning and cross-stain transferring, are designed to pretrain the model on Hematoxylin and Eosin (H\&E) images and transfer the model to immunohistochemistry (IHC) images, respectively. To validate the efficacy of our models, we evaluate the performance over a wide variety of downstream tasks, including patch-level colorectal cancer subtyping and whole slide image (WSI)-level classification in H\&E field, together with expression level prediction of IHC marker and tumor identification in IHC field. The experimental results show the superiority of our models over most tasks and the efficacy of proposed pretext tasks. The codes and models are available at https://github.com/openmedlab/PathoDuet.
Authors: Yizhe Zhang, Shuo Wang, Tao Zhou, Qi Dou, Danny Z. Chen
Segmentation quality assessment (SQA) plays a critical role in the deployment of a medical image based AI system. Users need to be informed/alerted whenever an AI system generates unreliable/incorrect predictions. With the introduction of the Segment Anything Model (SAM), a general foundation segmentation model, new research opportunities emerged in how one can utilize SAM for medical image segmentation. In this paper, we propose a novel SQA method, called SQA-SAM, which exploits SAM to enhance the accuracy of quality assessment for medical image segmentation. When a medical image segmentation model (MedSeg) produces predictions for a test image, we generate visual prompts based on the predictions, and SAM is utilized to generate segmentation maps corresponding to the visual prompts. How well MedSeg's segmentation aligns with SAM's segmentation indicates how well MedSeg's segmentation aligns with the general perception of objectness and image region partition. We develop a score measure for such alignment. In experiments, we find that the generated scores exhibit moderate to strong positive correlation (in Pearson correlation and Spearman correlation) with Dice coefficient scores reflecting the true segmentation quality.
Authors: Zhengqiang Zhang, Ruihuang Li, Shi Guo, Yang Cao, Lei Zhang
Online video super-resolution (online-VSR) highly relies on an effective alignment module to aggregate temporal information, while the strict latency requirement makes accurate and efficient alignment very challenging. Though much progress has been achieved, most of the existing online-VSR methods estimate the motion fields of each frame separately to perform alignment, which is computationally redundant and ignores the fact that the motion fields of adjacent frames are correlated. In this work, we propose an efficient Temporal Motion Propagation (TMP) method, which leverages the continuity of motion field to achieve fast pixel-level alignment among consecutive frames. Specifically, we first propagate the offsets from previous frames to the current frame, and then refine them in the neighborhood, which significantly reduces the matching space and speeds up the offset estimation process. Furthermore, to enhance the robustness of alignment, we perform spatial-wise weighting on the warped features, where the positions with more precise offsets are assigned higher importance. Experiments on benchmark datasets demonstrate that the proposed TMP method achieves leading online-VSR accuracy as well as inference speed. The source code of TMP can be found at \href{https://github.com/xtudbxk/TMP}{https://github.com/xtudbxk/TMP}.
Authors: Lukas Radl, Michael Steiner, Andreas Kurz, Markus Steinberger
Due to the omnipresence of Neural Radiance Fields (NeRFs), the interest towards editable implicit 3D representations has surged over the last years. However, editing implicit or hybrid representations as used for NeRFs is difficult due to the entanglement of appearance and geometry encoded in the model parameters. Despite these challenges, recent research has shown first promising steps towards photorealistic and non-photorealistic appearance edits. The main open issues of related work include limited interactivity, a lack of support for local edits and large memory requirements, rendering them less useful in practice. We address these limitations with LAENeRF, a unified framework for photorealistic and non-photorealistic appearance editing of NeRFs. To tackle local editing, we leverage a voxel grid as starting point for region selection. We learn a mapping from expected ray terminations to final output color, which can optionally be supervised by a style loss, resulting in a framework which can perform photorealistic and non-photorealistic appearance editing of selected regions. Relying on a single point per ray for our mapping, we limit memory requirements and enable fast optimization. To guarantee interactivity, we compose the output color using a set of learned, modifiable base colors, composed with additive layer mixing. Compared to concurrent work, LAENeRF enables recoloring and stylization while keeping processing time low. Furthermore, we demonstrate that our approach surpasses baseline methods both quantitatively and qualitatively.
Authors: Jason Chun Lok Li, Rui Lin, Jiajun Zhou, Edmund Yin Mun Lam, Ngai Wong
Despite the decomposition of convolutional kernels for lightweight CNNs being well studied, existing works that rely on tensor network diagrams or hyperdimensional abstraction lack geometry intuition. This work devises a new perspective by linking a 3D-reshaped kernel tensor to its various slice-wise and rank-1 decompositions, permitting a straightforward connection between various tensor approximations and efficient CNN modules. Specifically, it is discovered that a pointwise-depthwise-pointwise (PDP) configuration constitutes a viable construct for lightweight CNNs. Moreover, a novel link to the latest ShiftNet is established, inspiring a first-ever shift layer pruning that achieves nearly 50% compression with < 1% drop in accuracy for ShiftResNet.
Authors: Mohsen Yavartanoo, Sangmin Hong, Reyhaneh Neshatavar, Kyoung Mu Lee
CNC manufacturing is a process that employs computer numerical control (CNC) machines to govern the movements of various industrial tools and machinery, encompassing equipment ranging from grinders and lathes to mills and CNC routers. However, the reliance on manual CNC programming has become a bottleneck, and the requirement for expert knowledge can result in significant costs. Therefore, we introduce a pioneering approach named CNC-Net, representing the use of deep neural networks (DNNs) to simulate CNC machines and grasp intricate operations when supplied with raw materials. CNC-Net constitutes a self-supervised framework that exclusively takes an input 3D model and subsequently generates the essential operation parameters required by the CNC machine to construct the object. Our method has the potential to transformative automation in manufacturing by offering a cost-effective alternative to the high costs of manual CNC programming while maintaining exceptional precision in 3D object production. Our experiments underscore the effectiveness of our CNC-Net in constructing the desired 3D objects through the utilization of CNC operations. Notably, it excels in preserving finer local details, exhibiting a marked enhancement in precision compared to the state-of-the-art 3D CAD reconstruction approaches.
Authors: Yuxin Cao, Ziyu Zhao, Xi Xiao, Derui Wang, Minhui Xue, Jin Lu
Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used in video attacks recently. In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization. We solve the first challenge by scaling down the perturbation range to a regional logo, while the second challenge is addressed by complementing an optimization stage after reinforcement learning. Experimental results substantiate the overall superiority of LogoStyleFool over three state-of-the-art patch-based attacks in terms of attack performance and semantic preservation. Meanwhile, LogoStyleFool still maintains its performance against two existing patch-based defense methods. We believe that our research is beneficial in increasing the attention of the security community to such subregional style transfer attacks.
Authors: Abdul Wasi, O. Jeba Shiney
Images acquired in hazy conditions have degradations induced in them. Dehazing such images is a vexed and ill-posed problem. Scores of prior-based and learning-based approaches have been proposed to mitigate the effect of haze and generate haze-free images. Many conventional methods are constrained by their lack of awareness regarding scene depth and their incapacity to capture long-range dependencies. In this paper, a method that uses residual learning and vision transformers in an attention module is proposed. It essentially comprises two networks: In the first one, the network takes the ratio of a hazy image and the approximated transmission matrix to estimate a residual map. The second network takes this residual image as input and passes it through convolution layers before superposing it on the generated feature maps. It is then passed through global context and depth-aware transformer encoders to obtain channel attention. The attention module then infers the spatial attention map before generating the final haze-free image. Experimental results, including several quantitative metrics, demonstrate the efficiency and scalability of the suggested methodology.
Authors: Doruk Aksoy, Huolin L. Xin, Timothy J. Rupert, William J. Bowman
Accurate segmentation of interconnected line networks, such as grain boundaries in polycrystalline material microstructures, poses a significant challenge due to the fragmented masks produced by conventional computer vision algorithms, including convolutional neural networks. These algorithms struggle with thin masks, often necessitating intricate post-processing for effective contour closure and continuity. Addressing this issue, this paper introduces a fast, high-fidelity post-processing technique, leveraging domain knowledge about grain boundary connectivity and employing conditional random fields and perceptual grouping rules. This approach significantly enhances segmentation mask accuracy, achieving a 79% segment identification accuracy in validation with a U-Net model on electron microscopy images of a polycrystalline oxide. Additionally, a novel grain alignment metric is introduced, showing a 51% improvement in grain alignment, providing a more detailed assessment of segmentation performance for complex microstructures. This method not only enables rapid and accurate segmentation but also facilitates an unprecedented level of data analysis, significantly improving the statistical representation of grain boundary networks, making it suitable for a range of disciplines where precise segmentation of interconnected line networks is essential.
Authors: Yilin Liu, Yunkui Pang, Jiang Li, Yong Chen, Pew-Thian Yap
Untrained neural networks pioneered by Deep Image Prior (DIP) have recently enabled MRI reconstruction without requiring fully-sampled measurements for training. Their success is widely attributed to the implicit regularization induced by suitable network architectures. However, the lack of understanding of such architectural priors results in superfluous design choices and sub-optimal outcomes. This work aims to simplify the architectural design decisions for DIP-MRI to facilitate its practical deployment. We observe that certain architectural components are more prone to causing overfitting regardless of the number of parameters, incurring severe reconstruction artifacts by hindering accurate extrapolation on the un-acquired measurements. We interpret this phenomenon from a frequency perspective and find that the architectural characteristics favoring low frequencies, i.e., deep and narrow with unlearnt upsampling, can lead to enhanced generalization and hence better reconstruction. Building on this insight, we propose two architecture-agnostic remedies: one to constrain the frequency range of the white-noise input and the other to penalize the Lipschitz constants of the network. We demonstrate that even with just one extra line of code on the input, the performance gap between the ill-designed models and the high-performing ones can be closed. These results signify that for the first time, architectural biases on untrained MRI reconstruction can be mitigated without architectural modifications.
Authors: Mikołaj Małkiński, Jacek Mańdziuk
Abstract Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
Authors: Yuqian Yuan, Wentong Li, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, Jianke Zhu
Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs primarily focus on image-level or box-level understanding, falling short of achieving fine-grained vision-language alignment at the pixel level. Besides, the lack of mask-based instruction data limits their advancements. In this paper, we propose Osprey, a mask-text instruction tuning approach, to extend MLLMs by incorporating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual understanding. To achieve this goal, we first meticulously curate a mask-based region-text dataset with 724K samples, and then design a vision-language model by injecting pixel-level representation into LLM. Especially, Osprey adopts a convolutional CLIP backbone as the vision encoder and employs a mask-aware visual extractor to extract precise visual mask features from high resolution input. Experimental results demonstrate Osprey's superiority in various region understanding tasks, showcasing its new capability for pixel-level instruction tuning. In particular, Osprey can be integrated with Segment Anything Model (SAM) seamlessly to obtain multi-granularity semantics. The source code, dataset and demo can be found at https://github.com/CircleRadon/Osprey.
Authors: Shiran Yuan, Hao Zhao
Neural Radiance Field (NeRF) and its variants have recently emerged as successful methods for novel view synthesis and 3D scene reconstruction. However, most current NeRF models either achieve high accuracy using large model sizes, or achieve high memory-efficiency by trading off accuracy. This limits the applicable scope of any single model, since high-accuracy models might not fit in low-memory devices, and memory-efficient models might not satisfy high-quality requirements. To this end, we present SlimmeRF, a model that allows for instant test-time trade-offs between model size and accuracy through slimming, thus making the model simultaneously suitable for scenarios with different computing budgets. We achieve this through a newly proposed algorithm named Tensorial Rank Incrementation (TRaIn) which increases the rank of the model's tensorial representation gradually during training. We also observe that our model allows for more effective trade-offs in sparse-view scenarios, at times even achieving higher accuracy after being slimmed. We credit this to the fact that erroneous information such as floaters tend to be stored in components corresponding to higher ranks. Our implementation is available at https://github.com/Shiran-Yuan/SlimmeRF.
Authors: Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao
This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling, expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor, PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training, PTv3 pushes these results to a higher level.
Authors: Nina M. Gottschling, Vegard Antun, Anders C. Hansen, Ben Adcock
Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is becoming a major concern. In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, but significant deterioration on others. This paper presents a theoretical foundation for these phenomena. We give a mathematical framework describing how and when such effects arise in arbitrary reconstruction methods, not just AI-inspired techniques. Several of our results take the form of `no free lunch' theorems. Specifically, we show that (i) methods that overperform on a single image can wrongly transfer details from one image to another, creating a hallucination, (ii) methods that overperform on two or more images can hallucinate or be unstable, (iii) optimizing the accuracy-stability trade-off is generally difficult, (iv) hallucinations and instabilities, if they occur, are not rare events, and may be encouraged by standard training, (v) it may be impossible to construct optimal reconstruction maps for certain problems. Our results trace these effects to the kernel of the forward operator whenever it is nontrivial, but also extend to the case when the forward operator is ill-conditioned. Based on these insights, our work aims to spur research into new ways to develop robust and reliable AI-inspired methods for inverse problems in imaging.
Authors: Kun Wu, Chengxiang Yin, Zhengping Che, Bo Jiang, Jian Tang, Zheng Guan, Gangyi Ding
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity, the main challenge remains and comes from two fundamental issues: pose ambiguity and appearance inconsistency. To alleviate the current limitations and improve the quality of the synthesized images, we propose a pose transfer network with augmented Disentangled Feature Consistency (DFC-Net) to facilitate human pose transfer. Given a pair of images containing the source and target person, DFC-Net extracts pose and static information from the source and target respectively, then synthesizes an image of the target person with the desired pose from the source. Moreover, DFC-Net leverages disentangled feature consistency losses in the adversarial training to strengthen the transfer coherence and integrates a keypoint amplifier to enhance the pose feature extraction. With the help of the disentangled feature consistency losses, we further propose a novel data augmentation scheme that introduces unpaired support data with the augmented consistency constraints to improve the generality and robustness of DFC-Net. Extensive experimental results on Mixamo-Pose and EDN-10k have demonstrated DFC-Net achieves state-of-the-art performance on pose transfer.
Authors: Anita Rau, Binod Bhattarai, Lourdes Agapito, Danail Stoyanov
Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging. In addition to deformation and view-dependent lighting, tubular structures like the colon present problems stemming from their self-occluding and repetitive anatomical structure. In this paper, we propose SimCol, a synthetic dataset for camera pose estimation in colonoscopy, and a novel method that explicitly learns a bimodal distribution to predict the endoscope pose. Our dataset replicates real colonoscope motion and highlights the drawbacks of existing methods. We publish 18k RGB images from simulated colonoscopy with corresponding depth and camera poses and make our data generation environment in Unity publicly available. We evaluate different camera pose prediction methods and demonstrate that, when trained on our data, they generalize to real colonoscopy sequences, and our bimodal approach outperforms prior unimodal work.
Authors: Gihyun Kim, Juyeop Kim, Jong-Seok Lee
The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robustness of Transformers against adversarial attacks. However, previous researches have focused solely on perturbations in the spatial domain. This paper proposes an additional perspective that explores the adversarial robustness of Transformers against frequency-selective perturbations in the spectral domain. To facilitate comparison between these two domains, an attack framework is formulated as a flexible tool for implementing attacks on images in the spatial and spectral domains. The experiments reveal that Transformers rely more on phase and low frequency information, which can render them more vulnerable to frequency-selective attacks than CNNs. This work offers new insights into the properties and adversarial robustness of Transformers.
Authors: Brandon Victor, Zhen He, Aiden Nibali
Agricultural research is essential for increasing food production to meet the requirements of an increasing population in the coming decades. Recently, satellite technology has been improving rapidly and deep learning has seen much success in generic computer vision tasks and many application areas which presents an important opportunity to improve analysis of agricultural land. Here we present a systematic review of 150 studies to find the current uses of deep learning on satellite imagery for agricultural research. Although we identify 5 categories of agricultural monitoring tasks, the majority of the research interest is in crop segmentation and yield prediction. We found that, when used, modern deep learning methods consistently outperformed traditional machine learning across most tasks; the only exception was that Long Short-Term Memory (LSTM) Recurrent Neural Networks did not consistently outperform Random Forests (RF) for yield prediction. The reviewed studies have largely adopted methodologies from generic computer vision, except for one major omission: benchmark datasets are not utilised to evaluate models across studies, making it difficult to compare results. Additionally, some studies have specifically utilised the extra spectral resolution available in satellite imagery, but other divergent properties of satellite images - such as the hugely different scales of spatial patterns - are not being taken advantage of in the reviewed studies.
Authors: Chiyu Zhang, Xiaogang Xu, Lei Wang, Zaiyan Dai, Jun Yang
Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling. This paper introduces Strips Window Attention Transformer (S2WAT), a novel hierarchical vision transformer designed for style transfer. S2WAT employs attention computation in diverse window shapes to capture both short- and long-range dependencies. The merged dependencies utilize the "Attn Merge" strategy, which adaptively determines spatial weights based on their relevance to the target. Extensive experiments on representative datasets show the proposed method's effectiveness compared to state-of-the-art (SOTA) transformer-based and other approaches. The code and pre-trained models are available at https://github.com/AlienZhang1996/S2WAT.
Authors: Xin Wen, Bingchen Zhao, Xiaojuan Qi
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. Previous studies argued that parametric classifiers are prone to overfitting to seen categories, and endorsed using a non-parametric classifier formed with semi-supervised k-means. However, in this study, we investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We demonstrate that two prediction biases exist: the classifier tends to predict seen classes more often, and produces an imbalanced distribution across seen and novel categories. Based on these findings, we propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers. We hope the investigation and proposed simple framework can serve as a strong baseline to facilitate future studies in this field. Our code is available at: https://github.com/CVMI-Lab/SimGCD.
Authors: Fushuo Huo, Wenchao Xu, Song Guo, Jingcai Guo, Haozhao Wang, Ziming Liu, Xiaocheng Lu
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output space containing all possible state-object compositions. Existing works either learn the joint compositional state-object embedding or predict simple primitives with separate classifiers. However, the former heavily relies on external word embedding methods, and the latter ignores the interactions of interdependent primitives, respectively. In this paper, we revisit the primitive prediction approach and propose a novel method, termed Progressive Cross-primitive Compatibility (ProCC), to mimic the human learning process for OW-CZSL tasks. Specifically, the cross-primitive compatibility module explicitly learns to model the interactions of state and object features with the trainable memory units, which efficiently acquires cross-primitive visual attention to reason high-feasibility compositions, without the aid of external knowledge. Moreover, considering the partial-supervision setting (pCZSL) as well as the imbalance issue of multiple task prediction, we design a progressive training paradigm to enable the primitive classifiers to interact to obtain discriminative information in an easy-to-hard manner. Extensive experiments on three widely used benchmark datasets demonstrate that our method outperforms other representative methods on both OW-CZSL and pCZSL settings by large margins.
Authors: Samira Kabri, Alexander Auras, Danilo Riccio, Hartmut Bauermeister, Martin Benning, Michael Moeller, Martin Burger
The reconstruction of images from their corresponding noisy Radon transform is a typical example of an ill-posed linear inverse problem as arising in the application of computerized tomography (CT). As the (naive) solution does not depend on the measured data continuously, regularization is needed to re-establish a continuous dependence. In this work, we investigate simple, but yet still provably convergent approaches to learning linear regularization methods from data. More specifically, we analyze two approaches: One generic linear regularization that learns how to manipulate the singular values of the linear operator in an extension of our previous work, and one tailored approach in the Fourier domain that is specific to CT-reconstruction. We prove that such approaches become convergent regularization methods as well as the fact that the reconstructions they provide are typically much smoother than the training data they were trained on. Finally, we compare the spectral as well as the Fourier-based approaches for CT-reconstruction numerically, discuss their advantages and disadvantages and investigate the effect of discretization errors at different resolutions.
Authors: Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Deyu Meng
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity. Specifically, based on the theoretical formulation that feature diversity is correlated with the rank of the unfolded kernel matrix, we rectify 3D convolution by modifying its topology to enhance the rank upper-bound. This modification yields a rank-enhanced spatial-spectral symmetrical convolution set (ReS$^3$-ConvSet), which not only learns diverse and powerful feature representations but also saves network parameters. Additionally, we also propose a novel diversity-aware regularization (DA-Reg) term that directly acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed ReS$^3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks, including denoising, spatial super-resolution, and classification. Extensive experiments show that the proposed approaches outperform state-of-the-art methods both quantitatively and qualitatively to a significant extent. The code is publicly available at https://github.com/jinnh/ReSSS-ConvSet.
Authors: Qiuhui Chen, Yi Hong
Structural magnetic resonance imaging (sMRI) is widely used for brain neurological disease diagnosis; while longitudinal MRIs are often collected to monitor and capture disease progression, as clinically used in diagnosing Alzheimer's disease (AD). However, most current methods neglect AD's progressive nature and only take a single sMRI for recognizing AD. In this paper, we consider the problem of leveraging the longitudinal MRIs of a subject for AD identification. To capture longitudinal changes in sMRIs, we propose a novel model Longformer, a spatiotemporal transformer network that performs attention mechanisms spatially on sMRIs at each time point and integrates brain region features over time to obtain longitudinal embeddings for classification. Our Longformer achieves state-of-the-art performance on two binary classification tasks of separating different stages of AD using the ADNI dataset. Our source code is available at https://github.com/Qybc/LongFormer.
Authors: Ning Liao, Bowen Shi, Xiaopeng Zhang, Min Cao, Junchi Yan, Qi Tian
Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus improving the performance stably. However, when transferring it to the vision area, current visual prompt learning methods are almost designed on discriminative pre-trained models, and there is also a lack of careful design to unify the forms of pre-training and downstream tasks. To explore prompt learning on the generative pre-trained visual model, as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction. In addition, we develop the prototypical verbalizer for mapping the predicted visual token with implicit semantics to explicit downstream labels. To our best knowledge, VPTM is the first visual prompt method on the generative pre-trained visual model, which achieves consistency between pre-training and downstream visual classification by task reformulation. Experiments show that VPTM outperforms other visual prompt methods and achieves excellent efficiency. Moreover, the task consistency of VPTM contributes to the robustness against prompt location, prompt length and prototype dimension, and could be deployed uniformly.
Authors: Hyungjin Chung, Suhyeon Lee, Jong Chul Ye
Krylov subspace, which is generated by multiplying a given vector by the matrix of a linear transformation and its successive powers, has been extensively studied in classical optimization literature to design algorithms that converge quickly for large linear inverse problems. For example, the conjugate gradient method (CG), one of the most popular Krylov subspace methods, is based on the idea of minimizing the residual error in the Krylov subspace. However, with the recent advancement of high-performance diffusion solvers for inverse problems, it is not clear how classical wisdom can be synergistically combined with modern diffusion models. In this study, we propose a novel and efficient diffusion sampling strategy that synergistically combine the diffusion sampling and Krylov subspace methods. Specifically, we prove that if the tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG initialized with the denoised data ensures the data consistency update to remain in the tangent space. This negates the need to compute the manifold-constrained gradient (MCG), leading to a more efficient diffusion sampling method. Our method is applicable regardless of the parametrization and setting (i.e., VE, VP). Notably, we achieve state-of-the-art reconstruction quality on challenging real-world medical inverse imaging problems, including multi-coil MRI reconstruction and 3D CT reconstruction. Moreover, our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
Authors: Fushuo Huo, Wenchao Xu, Jingcai Guo, Haozhao Wang, Yunfeng Fan, Song Guo
This paper investigates a new, practical, but challenging problem named Non-exemplar Online Class-incremental continual Learning (NO-CL), which aims to preserve the discernibility of base classes without buffering data examples and efficiently learn novel classes continuously in a single-pass (i.e., online) data stream. The challenges of this task are mainly two-fold: (1) Both base and novel classes suffer from severe catastrophic forgetting as no previous samples are available for replay. (2) As the online data can only be observed once, there is no way to fully re-train the whole model, e.g., re-calibrate the decision boundaries via prototype alignment or feature distillation. In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for NO-CL problem, which consists of two strategies: 1) Dual class prototypes: vanilla and high-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction. 2) Self-augment and refinement: Instead of updating the whole network, we optimize high-dimensional prototypes alternatively with the extra projection module based on self-augment vanilla prototypes, through a bi-level optimization problem. Extensive experiments demonstrate the effectiveness and superiority of the proposed DSR in NO-CL.
Authors: Jamie Tolan, Hung-I Yang, Ben Nosarzewski, Guillaume Couairon, Huy Vo, John Brandt, Justine Spore, Sayantan Majumdar, Daniel Haziza, Janaki Vamaraju, Theo Moutakanni, Piotr Bojanowski, Tracy Johns, Brian White, Tobias Tiecke, Camille Couprie
Vegetation structure mapping is critical for understanding the global carbon cycle and monitoring nature-based approaches to climate adaptation and mitigation. Repeated measurements of these data allow for the observation of deforestation or degradation of existing forests, natural forest regeneration, and the implementation of sustainable agricultural practices like agroforestry. Assessments of tree canopy height and crown projected area at a high spatial resolution are also important for monitoring carbon fluxes and assessing tree-based land uses, since forest structures can be highly spatially heterogeneous, especially in agroforestry systems. Very high resolution satellite imagery (less than one meter (1m) Ground Sample Distance) makes it possible to extract information at the tree level while allowing monitoring at a very large scale. This paper presents the first high-resolution canopy height map concurrently produced for multiple sub-national jurisdictions. Specifically, we produce very high resolution canopy height maps for the states of California and Sao Paulo, a significant improvement in resolution over the ten meter (10m) resolution of previous Sentinel / GEDI based worldwide maps of canopy height. The maps are generated by the extraction of features from a self-supervised model trained on Maxar imagery from 2017 to 2020, and the training of a dense prediction decoder against aerial lidar maps. We also introduce a post-processing step using a convolutional network trained on GEDI observations. We evaluate the proposed maps with set-aside validation lidar data as well as by comparing with other remotely sensed maps and field-collected data, and find our model produces an average Mean Absolute Error (MAE) of 2.8 meters and Mean Error (ME) of 0.6 meters.
Authors: Yucheng Lu, Zhixin Xu, Moon Hyung Choi, Jimin Kim, Seung-Won Jung
Computed tomography (CT) has been used worldwide as a non-invasive test in assisting diagnosis. However, the ionizing nature of X-ray exposure raises concerns about potential health risks such as cancer. The desire for lower radiation doses has driven researchers to improve reconstruction quality. Although previous studies on low-dose computed tomography (LDCT) denoising have demonstrated the effectiveness of learning-based methods, most were developed on the simulated data collected using the Radon transform. However, the real-world scenario differs significantly from the simulation domain, especially when using the multi-slice spiral scanner geometry. This paper proposes a two-stage method for the commercially available third-generation multi-slice spiral CT scanners that better exploits the complete reconstruction pipeline for LDCT denoising across different domains. Our approach makes good use of the high redundancy of the multi-slice projections and the volumetric reconstructions while leveraging the over-smoothing of high-frequency information in conventional cascaded frameworks due to aggressive denoising. The dedicated design also provides a more explicit interpretation of the data flow. Extensive experiments on various datasets showed that the proposed method could remove up to 70% of noise without compromised spatial resolution, while subjective evaluations by two radiologists further supported its superior performance against state-of-the-art methods in clinical practice.
Authors: Iris de Gélis (1 and 2), Sébastien Lefèvre (2), Thomas Corpetti (3) ((1) Magellium, (2) Institut de Recherche en Informatique et Systèmes Aléatoires IRISA - UMR 6074 - Université Bretagne Sud, (3) Littoral - Environnement - Télédétection - Géomatique LETG - UMR 6554 - Université Rennes 2)
In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical 2D images. In this context, 3D point clouds (PCs), whether obtained through LiDAR or photogrammetric techniques, provide valuable information. While recent studies showed the considerable benefit of using deep learning-based methods to detect and characterize changes into raw 3D PCs, these studies rely on large annotated training data to obtain accurate results. The collection of these annotations are tricky and time-consuming. The availability of unsupervised or weakly supervised approaches is then of prime interest. In this paper, we propose an unsupervised method, called DeepCluster 3D Change Detection (DC3DCD), to detect and categorize multiclass changes at point level. We classify our approach in the unsupervised family given the fact that we extract in a completely unsupervised way a number of clusters associated with potential changes. Let us precise that in the end of the process, the user has only to assign a label to each of these clusters to derive the final change map. Our method builds upon the DeepCluster approach, originally designed for image classification, to handle complex raw 3D PCs and perform change segmentation task. An assessment of the method on both simulated and real public dataset is provided. The proposed method allows to outperform fully-supervised traditional machine learning algorithm and to be competitive with fully-supervised deep learning networks applied on rasterization of 3D PCs with a mean of IoU over classes of change of 57.06\% and 66.69\% for the simulated and the real datasets, respectively.
Authors: Fabio Bellavia
This paper presents Slime, a novel non-deep image matching framework which models the scene as rough local overlapping planes. This intermediate representation sits in-between the local affine approximation of the keypoint patches and the global matching based on both spatial and similarity constraints, providing a progressive pruning of the correspondences, as planes are easier to handle with respect to general scenes.
Slime decomposes the images into overlapping regions at different scales and computes loose planar homographies. Planes are mutually extended by compatible matches and the images are split into fixed tiles, with only the best homographies retained for each pair of tiles. Stable matches are identified according to the consensus of the admissible stereo configurations provided by pairwise homographies. Within tiles, the rough planes are then merged according to their overlap in terms of matches and further consistent correspondences are extracted.
The whole process only involves homography constraints. As a result, both the coverage and the stability of correct matches over the scene are amplified, together with the ability to spot matches in challenging scenes, allowing traditional hybrid matching pipelines to make up lost ground against recent end-to-end deep matching methods.
In addition, the paper gives a thorough comparative analysis of recent state-of-the-art in image matching represented by end-to-end deep networks and hybrid pipelines. The evaluation considers both planar and non-planar scenes, taking into account critical and challenging scenarios including abrupt temporal image changes and strong variations in relative image rotations. According to this analysis, although the impressive progress done in this field, there is still a wide room for improvements to be investigated in future research.
Authors: Linus Kreitner, Johannes C. Paetzold, Nikolaus Rauch, Chen Chen, Ahmed M. Hagag, Alaa E. Fayed, Sobha Sivaprasad, Sebastian Rausch, Julian Weichsel, Bjoern H. Menze, Matthias Harders, Benjamin Knier, Daniel Rueckert, Martin J. Menten
Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality that can acquire high-resolution volumes of the retinal vasculature and aid the diagnosis of ocular, neurological and cardiac diseases. Segmenting the visible blood vessels is a common first step when extracting quantitative biomarkers from these images. Classical segmentation algorithms based on thresholding are strongly affected by image artifacts and limited signal-to-noise ratio. The use of modern, deep learning-based segmentation methods has been inhibited by a lack of large datasets with detailed annotations of the blood vessels. To address this issue, recent work has employed transfer learning, where a segmentation network is trained on synthetic OCTA images and is then applied to real data. However, the previously proposed simulations fail to faithfully model the retinal vasculature and do not provide effective domain adaptation. Because of this, current methods are unable to fully segment the retinal vasculature, in particular the smallest capillaries. In this work, we present a lightweight simulation of the retinal vascular network based on space colonization for faster and more realistic OCTA synthesis. We then introduce three contrast adaptation pipelines to decrease the domain gap between real and artificial images. We demonstrate the superior segmentation performance of our approach in extensive quantitative and qualitative experiments on three public datasets that compare our method to traditional computer vision algorithms and supervised training using human annotations. Finally, we make our entire pipeline publicly available, including the source code, pretrained models, and a large dataset of synthetic OCTA images.
Authors: Weinan Song, Yaxuan Zhu, Lei He, Yingnian Wu, Jianwen Xie
This paper studies a novel energy-based cooperative learning framework for multi-domain image-to-image translation. The framework consists of four components: descriptor, translator, style encoder, and style generator. The descriptor is a multi-head energy-based model that represents a multi-domain image distribution. The components of translator, style encoder, and style generator constitute a diversified image generator. Specifically, given an input image from a source domain, the translator turns it into a stylised output image of the target domain according to a style code, which can be inferred by the style encoder from a reference image or produced by the style generator from a random noise. Since the style generator is represented as an domain-specific distribution of style codes, the translator can provide a one-to-many transformation (i.e., diversified generation) between source domain and target domain. To train our framework, we propose a likelihood-based multi-domain cooperative learning algorithm to jointly train the multi-domain descriptor and the diversified image generator (including translator, style encoder, and style generator modules) via multi-domain MCMC teaching, in which the descriptor guides the diversified image generator to shift its probability density toward the data distribution, while the diversified image generator uses its randomly translated images to initialize the descriptor's Langevin dynamics process for efficient sampling.
Authors: Qi Mao, Tinghan Yang, Yinuo Zhang, Zijian Wang, Meng Wang, Shiqi Wang, Siwei Ma
Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve extreme compression ratios ($<0.05$ bpp) remain constrained. In this work, we propose a simple yet effective coding framework by introducing vector quantization (VQ)--based generative models into the image compression domain. The main insight is that the codebook learned by the VQGAN model yields a strong expressive capacity, facilitating efficient compression of continuous information in the latent space while maintaining reconstruction quality. Specifically, an image can be represented as VQ-indices by finding the nearest codeword, which can be encoded using lossless compression methods into bitstreams. We propose clustering a pre-trained large-scale codebook into smaller codebooks through the K-means algorithm, yielding variable bitrates and different levels of reconstruction quality within the coding framework. Furthermore, we introduce a transformer to predict lost indices and restore images in unstable environments. Extensive qualitative and quantitative experiments on various benchmark datasets demonstrate that the proposed framework outperforms state-of-the-art codecs in terms of perceptual quality-oriented metrics and human perception at extremely low bitrates ($\le 0.04$ bpp). Remarkably, even with the loss of up to $20\%$ of indices, the images can be effectively restored with minimal perceptual loss.
Authors: Michael Gableman, Avinash Kak
As a result of Shadow NeRF and Sat-NeRF, it is possible to take the solar angle into account in a NeRF-based framework for rendering a scene from a novel viewpoint using satellite images for training. Our work extends those contributions and shows how one can make the renderings season-specific. Our main challenge was creating a Neural Radiance Field (NeRF) that could render seasonal features independently of viewing angle and solar angle while still being able to render shadows. We teach our network to render seasonal features by introducing one more input variable -- time of the year. However, the small training datasets typical of satellite imagery can introduce ambiguities in cases where shadows are present in the same location for every image of a particular season. We add additional terms to the loss function to discourage the network from using seasonal features for accounting for shadows. We show the performance of our network on eight Areas of Interest containing images captured by the Maxar WorldView-3 satellite. This evaluation includes tests measuring the ability of our framework to accurately render novel views, generate height maps, predict shadows, and specify seasonal features independently from shadows. Our ablation studies justify the choices made for network design parameters.
Authors: Wangbo Zhao, Kepan Nan, Songyang Zhang, Kai Chen, Dahua Lin, Yang You
Referring video object segmentation (RVOS) is a task that aims to segment the target object in all video frames based on a sentence describing the object. Although existing RVOS methods have achieved significant performance, they depend on densely-annotated datasets, which are expensive and time-consuming to obtain. In this paper, we propose a new annotation scheme that reduces the annotation effort by 8 times, while providing sufficient supervision for RVOS. Our scheme only requires a mask for the frame where the object first appears and bounding boxes for the rest of the frames. Based on this scheme, we develop a novel RVOS method that exploits weak annotations effectively. Specifically, we build a simple but effective baseline model, SimRVOS, for RVOS with weak annotation. Then, we design a cross frame segmentation module, which uses the language-guided dynamic filters from one frame to segment the target object in other frames to thoroughly leverage the valuable mask annotation and bounding boxes. Finally, we develop a bi-level contrastive learning method to enhance the pixel-level discriminative representation of the model with weak annotation. We conduct extensive experiments to show that our method achieves comparable or even superior performance to fully-supervised methods, without requiring dense mask annotations.
Authors: Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang
The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful visual representations with rich semantics. An open and worthwhile problem is efficiently adapting such a strong model to the video domain and designing a robust video anomaly detector. In this work, we propose VadCLIP, a new paradigm for weakly supervised video anomaly detection (WSVAD) by leveraging the frozen CLIP model directly without any pre-training and fine-tuning process. Unlike current works that directly feed extracted features into the weakly supervised classifier for frame-level binary classification, VadCLIP makes full use of fine-grained associations between vision and language on the strength of CLIP and involves dual branch. One branch simply utilizes visual features for coarse-grained binary classification, while the other fully leverages the fine-grained language-image alignment. With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task. We conduct extensive experiments on two commonly-used benchmarks, demonstrating that VadCLIP achieves the best performance on both coarse-grained and fine-grained WSVAD, surpassing the state-of-the-art methods by a large margin. Specifically, VadCLIP achieves 84.51% AP and 88.02% AUC on XD-Violence and UCF-Crime, respectively. Code and features are released at https://github.com/nwpu-zxr/VadCLIP.
Authors: Dehuan Zhang, Jingchun Zhou, ChunLe Guo, Weishi Zhang, Chongyi Li
Visually restoring underwater scenes primarily involves mitigating interference from underwater media. Existing methods ignore the inherent scale-related characteristics in underwater scenes. Therefore, we present the synergistic multi-scale detail refinement via intrinsic supervision (SMDR-IS) for enhancing underwater scene details, which contain multi-stages. The low-degradation stage from the original images furnishes the original stage with multi-scale details, achieved through feature propagation using the Adaptive Selective Intrinsic Supervised Feature (ASISF) module. By using intrinsic supervision, the ASISF module can precisely control and guide feature transmission across multi-degradation stages, enhancing multi-scale detail refinement and minimizing the interference from irrelevant information in the low-degradation stage. In multi-degradation encoder-decoder framework of SMDR-IS, we introduce the Bifocal Intrinsic-Context Attention Module (BICA). Based on the intrinsic supervision principles, BICA efficiently exploits multi-scale scene information in images. BICA directs higher-resolution spaces by tapping into the insights of lower-resolution ones, underscoring the pivotal role of spatial contextual relationships in underwater image restoration. Throughout training, the inclusion of a multi-degradation loss function can enhance the network, allowing it to adeptly extract information across diverse scales. When benchmarked against state-of-the-art methods, SMDR-IS consistently showcases superior performance. The code is publicly available at: https://github.com/zhoujingchun03/SMDR-IS.
Authors: Urs Waldmann, Alex Hoi Hang Chan, Hemal Naik, Máté Nagy, Iain D. Couzin, Oliver Deussen, Bastian Goldluecke, Fumihiro Kano
Markerless methods for animal posture tracking have been rapidly developing recently, but frameworks and benchmarks for tracking large animal groups in 3D are still lacking. To overcome this gap in the literature, we present 3D-MuPPET, a framework to estimate and track 3D poses of up to 10 pigeons at interactive speed using multiple camera views. We train a pose estimator to infer 2D keypoints and bounding boxes of multiple pigeons, then triangulate the keypoints to 3D. For identity matching of individuals in all views, we first dynamically match 2D detections to global identities in the first frame, then use a 2D tracker to maintain IDs across views in subsequent frames. We achieve comparable accuracy to a state of the art 3D pose estimator in terms of median error and Percentage of Correct Keypoints. Additionally, we benchmark the inference speed of 3D-MuPPET, with up to 9.45 fps in 2D and 1.89 fps in 3D, and perform quantitative tracking evaluation, which yields encouraging results. Finally, we showcase two novel applications for 3D-MuPPET. First, we train a model with data of single pigeons and achieve comparable results in 2D and 3D posture estimation for up to 5 pigeons. Second, we show that 3D-MuPPET also works in outdoors without additional annotations from natural environments. Both use cases simplify the domain shift to new species and environments, largely reducing annotation effort needed for 3D posture tracking. To the best of our knowledge we are the first to present a framework for 2D/3D animal posture and trajectory tracking that works in both indoor and outdoor environments for up to 10 individuals. We hope that the framework can open up new opportunities in studying animal collective behaviour and encourages further developments in 3D multi-animal posture tracking.
Authors: Tao Pu, Tianshui Chen, Hefeng Wu, Yongyi Lu, Liang Lin
Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations. Specifically, we first learn spatial co-occurrence and temporal transition correlations in a statistical manner. Then, we design spatial and temporal knowledge-embedded layers that introduce the multi-head cross-attention mechanism to fully explore the interaction between visual representation and the knowledge to generate spatial- and temporal-embedded representations, respectively. Finally, we aggregate these representations for each subject-object pair to predict the final semantic labels and their relationships. Extensive experiments show that STKET outperforms current competing algorithms by a large margin, e.g., improving the mR@50 by 8.1%, 4.7%, and 2.1% on different settings over current algorithms.
Authors: Yuanmin Tang, Jing Yu, Keke Gai, Jiamin Zhuang, Gang Xiong, Yue Hu, Qi Wu
Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to learn a more accurate image representation that has adaptive attention to the reference image for various manipulation descriptions. In this paper, we propose a novel context-dependent mapping network, named Context-I2W, for adaptively converting description-relevant Image information into a pseudo-word token composed of the description for accurate ZS-CIR. Specifically, an Intent View Selector first dynamically learns a rotation rule to map the identical image to a task-specific manipulation view. Then a Visual Target Extractor further captures local information covering the main targets in ZS-CIR tasks under the guidance of multiple learnable queries. The two complementary modules work together to map an image to a context-dependent pseudo-word token without extra supervision. Our model shows strong generalization ability on four ZS-CIR tasks, including domain conversion, object composition, object manipulation, and attribute manipulation. It obtains consistent and significant performance boosts ranging from 1.88% to 3.60% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://github.com/Pter61/context-i2w.
Authors: Boyang Zheng, Chumeng Liang, Xiaoyu Wu, Yan Liu
Latent Diffusion Model (LDM) achieves state-of-the-art performances in image generation yet raising copyright and privacy concerns. Adversarial attacks on LDM are then born to protect unauthorized images from being used in LDM-driven few-shot generation. However, these attacks suffer from moderate performance and excessive computational cost, especially in GPU memory. In this paper, we propose an effective adversarial attack on LDM that shows superior performance against state-of-the-art few-shot generation pipeline of LDM, for example, LoRA. We implement the attack with memory efficiency by introducing several mechanisms and decrease the memory cost of the attack to less than 6GB, which allows individual users to run the attack on a majority of consumer GPUs. Our proposed attack can be a practical tool for people facing the copyright and privacy risk brought by LDM to protect themselves.
Authors: Wei Zhang, Tiecheng Sun, Sen Wang, Qing Cheng, Norbert Haala
In this letter, we present a neural field-based real-time monocular mapping framework for accurate and dense Simultaneous Localization and Mapping (SLAM). Recent neural mapping frameworks show promising results, but rely on RGB-D or pose inputs, or cannot run in real-time. To address these limitations, our approach integrates dense-SLAM with neural implicit fields. Specifically, our dense SLAM approach runs parallel tracking and global optimization, while a neural field-based map is constructed incrementally based on the latest SLAM estimates. For the efficient construction of neural fields, we employ multi-resolution grid encoding and signed distance function (SDF) representation. This allows us to keep the map always up-to-date and adapt instantly to global updates via loop closing. For global consistency, we propose an efficient Sim(3)-based pose graph bundle adjustment (PGBA) approach to run online loop closing and mitigate the pose and scale drift. To enhance depth accuracy further, we incorporate learned monocular depth priors. We propose a novel joint depth and scale adjustment (JDSA) module to solve the scale ambiguity inherent in depth priors. Extensive evaluations across synthetic and real-world datasets validate that our approach outperforms existing methods in accuracy and map completeness while preserving real-time performance.
Authors: Yoo Yeon Sung, Jordan Boyd-Graber, Naeemul Hassan
Polarization and the marketplace for impressions have conspired to make navigating information online difficult for users, and while there has been a significant effort to detect false or misleading text, multimodal datasets have received considerably less attention. To complement existing resources, we present multimodal Video Misleading Headline (VMH), a dataset that consists of videos and whether annotators believe the headline is representative of the video's contents. After collecting and annotating this dataset, we analyze multimodal baselines for detecting misleading headlines. Our annotation process also focuses on why annotators view a video as misleading, allowing us to better understand the interplay of annotators' background and the content of the videos.
Authors: Sergio Calvo-Ordonez, Chun-Wun Cheng, Jiahao Huang, Lipei Zhang, Guang Yang, Carola-Bibiane Schonlieb, Angelica I Aviles-Rivero
Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse process, remains a challenge due to slow convergence rates and high computational costs. In this paper, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with Denoising Diffusion Probabilistic Models (DDPMs), our framework operates with approximately a quarter of the parameters, and $\sim$ 30\% of the Floating Point Operations (FLOPs) compared to standard U-Nets in DDPMs. Furthermore, our model is notably faster in inference than the baseline when measured in fair and equal conditions. We also provide a mathematical intuition as to why our proposed reverse process is faster as well as a mathematical discussion of the empirical tradeoffs in the denoising downstream task. Finally, we argue that our method is compatible with existing performance enhancement techniques, enabling further improvements in efficiency, quality, and speed.
Authors: Yuxiang Tuo, Wangmeng Xiang, Jun-Yan He, Yifeng Geng, Xuansong Xie
Diffusion model based Text-to-Image has achieved impressive achievements recently. Although current technology for synthesizing images is highly advanced and capable of generating images with high fidelity, it is still possible to give the show away when focusing on the text area in the generated image. To address this issue, we introduce AnyText, a diffusion-based multilingual visual text generation and editing model, that focuses on rendering accurate and coherent text in the image. AnyText comprises a diffusion pipeline with two primary elements: an auxiliary latent module and a text embedding module. The former uses inputs like text glyph, position, and masked image to generate latent features for text generation or editing. The latter employs an OCR model for encoding stroke data as embeddings, which blend with image caption embeddings from the tokenizer to generate texts that seamlessly integrate with the background. We employed text-control diffusion loss and text perceptual loss for training to further enhance writing accuracy. AnyText can write characters in multiple languages, to the best of our knowledge, this is the first work to address multilingual visual text generation. It is worth mentioning that AnyText can be plugged into existing diffusion models from the community for rendering or editing text accurately. After conducting extensive evaluation experiments, our method has outperformed all other approaches by a significant margin. Additionally, we contribute the first large-scale multilingual text images dataset, AnyWord-3M, containing 3 million image-text pairs with OCR annotations in multiple languages. Based on AnyWord-3M dataset, we propose AnyText-benchmark for the evaluation of visual text generation accuracy and quality. Our project will be open-sourced on https://github.com/tyxsspa/AnyText to improve and promote the development of text generation technology.
Authors: Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.
Authors: Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin
Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which involves an irreconcilable training imbalance. Precisely, to generate realistic persons, they need to sufficiently tune the pre-trained model, which inevitably causes the model to forget the rich semantic scene prior and makes scene generation over-fit to the training data. Moreover, even with sufficient fine-tuning, these methods can still not generate high-fidelity persons since joint learning of the scene and person generation also lead to quality compromise. In this paper, we propose Face-diffuser, an effective collaborative generation pipeline to eliminate the above training imbalance and quality compromise. Specifically, we first develop two specialized pre-trained diffusion models, i.e., Text-driven Diffusion Model (TDM) and Subject-augmented Diffusion Model (SDM), for scene and person generation, respectively. The sampling process is divided into three sequential stages, i.e., semantic scene construction, subject-scene fusion, and subject enhancement. The first and last stages are performed by TDM and SDM respectively. The subject-scene fusion stage, that is the collaboration achieved through a novel and highly effective mechanism, Saliency-adaptive Noise Fusion (SNF). Specifically, it is based on our key observation that there exists a robust link between classifier-free guidance responses and the saliency of generated images. In each time step, SNF leverages the unique strengths of each model and allows for the spatial blending of predicted noises from both models automatically in a saliency-aware manner. Extensive experiments confirm the impressive effectiveness and robustness of the Face-diffuser.
Authors: Yonghui Wang, Wengang Zhou, Hao Feng, Keyi Zhou, Houqiang Li
In the field of document understanding, significant advances have been made in the fine-tuning of Multimodal Large Language Models (MLLMs) with instruction-following data. Nevertheless, the potential of text-grounding capability within text-rich scenarios remains underexplored. In this paper, we present a text-grounding document understanding model, termed TGDoc, which addresses this deficiency by enhancing MLLMs with the ability to discern the spatial positioning of text within images. Empirical evidence suggests that text-grounding improves the model's interpretation of textual content, thereby elevating its proficiency in comprehending text-rich images. Specifically, we compile a dataset containing 99K PowerPoint presentations sourced from the internet. We formulate instruction tuning tasks including text detection, recognition, and spotting to facilitate the cohesive alignment between the visual encoder and large language model. Moreover, we curate a collection of text-rich images and prompt the text-only GPT-4 to generate 12K high-quality conversations, featuring textual locations within text-rich scenarios. By integrating text location data into the instructions, TGDoc is adept at discerning text locations during the visual question process. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple text-rich benchmarks, validating the effectiveness of our method.
Authors: Kunpeng Wang, Chenglong Li, Zhengzheng Tu, Bin Luo
Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we make the first attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which performs structural switching solely relied on single-modal and multi-modal inputs. UniSOD achieves consistent performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks.
Authors: Ruoyi Du, Dongliang Chang, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma
High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls. This paper aims to democratise high-resolution GenAI by advancing the frontier of high-resolution generation while remaining accessible to a broad audience. We demonstrate that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation. Our novel DemoFusion framework seamlessly extends open-source GenAI models, employing Progressive Upscaling, Skip Residual, and Dilated Sampling mechanisms to achieve higher-resolution image generation. The progressive nature of DemoFusion requires more passes, but the intermediate results can serve as "previews", facilitating rapid prompt iteration.
Authors: Kairui Yang, Zihao Guo, Gengjie Lin, Haotian Dong, Die Zuo, Jibin Peng, Zhao Huang, Zhecheng Xu, Fupeng Li, Ziyun Bai, Di Lin
We advocate the idea of the natural-language-driven(NLD) simulation to efficiently produce the object interactions between multiple objects in the virtual road scenes, for teaching and testing the autonomous driving systems that should take quick action to avoid collision with obstacles with unpredictable motions. The NLD simulation allows the brief natural-language description to control the object interactions, significantly reducing the human efforts for creating a large amount of interaction data. To facilitate the research of NLD simulation, we collect the Language-to-Interaction(L2I) benchmark dataset with 120,000 natural-language descriptions of object interactions in 6 common types of road topologies. Each description is associated with the programming code, which the graphic render can use to visually reconstruct the object interactions in the virtual scenes. As a methodology contribution, we design SimCopilot to translate the interaction descriptions to the renderable code. We use the L2I dataset to evaluate SimCopilot's abilities to control the object motions, generate complex interactions, and generalize interactions across road topologies. The L2I dataset and the evaluation results motivate the relevant research of the NLD simulation.
Authors: Kang Ge, Chen Wang, Yutao Guo, Yansong Tang, Zhenzhong Hu
Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two parameter-efficient fine-tuning methods, adapter and low-rank adaptation, are adopted to fine-tune the foundation model in semantic segmentation: the Segment Anything Model (SAM). The fine-tuned CrackSAM model is much larger than all the existing crack segmentation models but shows excellent performance. To test the zero-shot performance of the proposed method, two unique datasets related to road and exterior wall cracks are collected, annotated and open-sourced, for a total of 810 images. Comparative experiments are conducted with twelve mature semantic segmentation models. On datasets with artificial noise and previously unseen datasets, the performance of CrackSAM far exceeds that of all state-of-the-art models. CrackSAM exhibits remarkable superiority, particularly under challenging conditions such as dim lighting, shadows, road markings, construction joints, and other interference factors. These cross-scenario results demonstrate the outstanding zero-shot capability of foundation models and provide new ideas for developing vision models in civil engineering.
Authors: Xu Zhang, Hao Li, Mang Ye
Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable performance when the noise increases. In this paper, we present a novel Negative Pre-aware Cross-modal (NPC) matching solution for large visual-language model fine-tuning on noisy downstream tasks. It is featured in two aspects: (1) For noise recognition and resistance, previous methods usually directly filter out a noise subset, we propose to estimate the negative impact of each sample. It does not need additional correction mechanisms that may predict unreliable correction results, leading to self-reinforcing error. We assign a confidence weight to each sample according to its negative impact in the training process. This adaptively adjusts the contribution of each sample to avoid noisy accumulation. (2) For maintaining stable performance with increasing noise, we utilize the memorization effect of DNNs by maintaining a memory bank. Specifically, we apply GMM to select high-confident clean samples as the memory entry, where the memory entry is used to estimate the negative impact of each sample. Since clean samples are easier distinguished by GMM with increasing noise, the memory bank can still maintain high quality at a high noise ratio. Compared to the correction mechanism focusing on noise samples, memory bank-based estimation is more robust, which makes the model performance stable on noisy datasets. Extensive experiments demonstrate that our method significantly improves matching accuracy and performance stability at increasing noise ratio. Our approach also surpasses the state-of-the-art methods by a large margin. The code is available at: https://github.com/ZhangXu0963/NPC.
Authors: Kongming Liang, Xinran Wang, Rui Wang, Donghui Gao, Ling Jin, Weidong Liu, Xiatian Zhu, Zhanyu Ma, Jun Guo
Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during training, either of which could hamper the model performance to a great extent. To overcome these limitations, in this paper we leverage the available vision-language knowledge to explicitly disclose the missing labels for enhancing model learning. Given an image, we predict the likelihood of each missing attribute label assisted by an off-the-shelf vision-language model, and randomly select to ignore those with high scores in training. Our strategy strikes a good balance between fully ignoring and negatifying the missing labels, as these high scores are found to be informative on revealing label ambiguity. Extensive experiments show that our proposed vision-language assisted loss can achieve state-of-the-art performance on the newly cleaned VAW dataset. Qualitative evaluation demonstrates the ability of the proposed method in predicting more complete attributes.
Authors: Zifan Wang, Zhuorui Ye, Haoran Wu, Junyu Chen, Li Yi
We study a new problem of semantic complete scene forecasting (SCSF) in this work. Given a 4D dynamic point cloud sequence, our goal is to forecast the complete scene corresponding to the future next frame along with its semantic labels. To tackle this challenging problem, we properly model the synergetic relationship between future forecasting and semantic scene completion through a novel network named SCSFNet. SCSFNet leverages a hybrid geometric representation for high-resolution complete scene forecasting. To leverage multi-frame observation as well as the understanding of scene dynamics to ease the completion task, SCSFNet introduces an attention-based skip connection scheme. To ease the need to model occlusion variations and to better focus on the occluded part, SCSFNet utilizes auxiliary visibility grids to guide the forecasting task. To evaluate the effectiveness of SCSFNet, we conduct experiments on various benchmarks including two large-scale indoor benchmarks we contributed and the outdoor SemanticKITTI benchmark. Extensive experiments show SCSFNet outperforms baseline methods on multiple metrics by a large margin, and also prove the synergy between future forecasting and semantic scene completion.
Authors: Wenting Chen, Xiang Li, Linlin Shen, Yixuan Yuan
To address these issues, we propose a novel Adaptive patch-word Matching (AdaMatch) model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explainability for the generation process. AdaMatch exploits the fine-grained relation between adaptive patches and words to provide explanations of specific image regions with corresponding words. To capture the abnormal regions of varying sizes and positions, we introduce the Adaptive Patch extraction (AdaPatch) module to acquire the adaptive patches for these regions adaptively. In order to provide explicit explainability for CXR-report generation task, we propose an AdaMatch-based bidirectional large language model for Cyclic CXR-report generation (AdaMatch-Cyclic). It employs the AdaMatch to obtain the keywords for CXR images and `keypatches' for medical reports as hints to guide CXR-report generation. Extensive experiments on two publicly available CXR datasets prove the effectiveness of our method and its superior performance to existing methods.
Authors: Yi Xin, Junlong Du, Qiang Wang, Zhiwen Lin, Ke Yan
Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of computational and storage costs. Recently, inspired by Natural Language Processing (NLP), parameter-efficient transfer learning has been successfully applied to vision tasks. However, most existing techniques primarily focus on single-task adaptation, and despite limited research on multi-task adaptation, these methods often exhibit suboptimal training and inference efficiency. In this paper, we first propose an once-for-all Vision Multi-Task Adapter (VMT-Adapter), which strikes approximately O(1) training and inference efficiency w.r.t task number. Concretely, VMT-Adapter shares the knowledge from multiple tasks to enhance cross-task interaction while preserves task-specific knowledge via independent knowledge extraction modules. Notably, since task-specific modules require few parameters, VMT-Adapter can handle an arbitrary number of tasks with a negligible increase of trainable parameters. We also propose VMT-Adapter-Lite, which further reduces the trainable parameters by learning shared parameters between down- and up-projections. Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3.96%(1.34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0.36%) trainable parameters of the pre-trained model.
Authors: Tangfei Liao, Xiaoqin Zhang, Li Zhao, Tao Wang, Guobao Xiao
Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (\eg texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks.
Authors: Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Shibo Zhao, Yu Quan Chong, Chen Wang, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Zsolt Kira, Fei Xia, Yonatan Bisk
Building general-purpose robots that can operate seamlessly, in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. Unfortunately, however, most existing robotic systems have been constrained - having been designed for specific tasks, trained on specific datasets, and deployed within specific environments. These systems usually require extensively-labeled data, rely on task-specific models, have numerous generalization issues when deployed in real-world scenarios, and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing an overview of what constitutes a conventional robotic system and the fundamental barriers to making it universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our living GitHub repository of resources, including papers reviewed in this survey as well as related projects and repositories for developing foundation models for robotics.
Authors: Weilong Chai, DanDan Zheng, Jiajiong Cao, Zhiquan Chen, Changbao Wang, Chenguang Ma
Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Though many acceleration methods have been proposed, they suffer from generation quality degradation or extra training cost generalizing to new fine-tuned models. To address these limitations, we propose a novel and universal Stable-Diffusion (SD) acceleration module called SpeedUpNet(SUN). SUN can be directly plugged into various fine-tuned SD models without extra training. This technique utilizes cross-attention layers to learn the relative offsets in the generated image results between negative and positive prompts achieving classifier-free guidance distillation with negative prompts controllable, and introduces a Multi-Step Consistency (MSC) loss to ensure a harmonious balance between reducing inference steps and maintaining consistency in the generated output. Consequently, SUN significantly reduces the number of inference steps to just 4 steps and eliminates the need for classifier-free guidance. It leads to an overall speedup of more than 10 times for SD models compared to the state-of-the-art 25-step DPM-solver++, and offers two extra advantages: (1) classifier-free guidance distillation with controllable negative prompts and (2) seamless integration into various fine-tuned Stable-Diffusion models without training. The effectiveness of the SUN has been verified through extensive experimentation. Project Page: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io
Authors: Tianchen Deng, Siyang Liu, Xuan Wang, Yejia Liu, Danwei Wang, Weidong Chen
Implicit neural representation has demonstrated promising results in view synthesis for large and complex scenes. However, existing approaches either fail to capture the fast-moving objects or need to build the scene graph without camera ego-motions, leading to low-quality synthesized views of the scene. We aim to jointly solve the view synthesis problem of large-scale urban scenes and fast-moving vehicles, which is more practical and challenging. To this end, we first leverage a graph structure to learn the local scene representations of dynamic objects and the background. Then, we design a progressive scheme that dynamically allocates a new local scene graph trained with frames within a temporal window, allowing us to scale up the representation to an arbitrarily large scene. Besides, the training views of urban scenes are relatively sparse, which leads to a significant decline in reconstruction accuracy for dynamic objects. Therefore, we design a frequency auto-encoder network to encode the latent code and regularize the frequency range of objects, which can enhance the representation of dynamic objects and address the issue of sparse image inputs. Additionally, we employ lidar point projection to maintain geometry consistency in large-scale urban scenes. Experimental results demonstrate that our method achieves state-of-the-art view synthesis accuracy, object manipulation, and scene roaming ability. The code will be open-sourced upon paper acceptance.
Authors: Ziteng Cui, Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada
The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from 3D points. This simplified rendering approach presents challenges in accurately modeling images captured under adverse lighting conditions, such as low light or over-exposure. Motivated by the ancient Greek emission theory that posits visual perception as a result of rays emanating from the eyes, we slightly refine the conventional NeRF framework to train NeRF under challenging light conditions and generate normal-light condition novel views unsupervised. We introduce the concept of a "Concealing Field," which assigns transmittance values to the surrounding air to account for illumination effects. In dark scenarios, we assume that object emissions maintain a standard lighting level but are attenuated as they traverse the air during the rendering process. Concealing Field thus compel NeRF to learn reasonable density and colour estimations for objects even in dimly lit situations. Similarly, the Concealing Field can mitigate over-exposed emissions during the rendering stage. Furthermore, we present a comprehensive multi-view dataset captured under challenging illumination conditions for evaluation. Our code and dataset available at https://github.com/cuiziteng/Aleth-NeRF
Authors: Zhangkai Ni, Peiqi Yang, Wenhan Yang, Hanli Wang, Lin Ma, Sam Kwong
Neural Radiance Fields (NeRF) have demonstrated impressive potential in synthesizing novel views from dense input, however, their effectiveness is challenged when dealing with sparse input. Existing approaches that incorporate additional depth or semantic supervision can alleviate this issue to an extent. However, the process of supervision collection is not only costly but also potentially inaccurate, leading to poor performance and generalization ability in diverse scenarios. In our work, we introduce a novel model: the Collaborative Neural Radiance Fields (ColNeRF) designed to work with sparse input. The collaboration in ColNeRF includes both the cooperation between sparse input images and the cooperation between the output of the neural radiation field. Through this, we construct a novel collaborative module that aligns information from various views and meanwhile imposes self-supervised constraints to ensure multi-view consistency in both geometry and appearance. A Collaborative Cross-View Volume Integration module (CCVI) is proposed to capture complex occlusions and implicitly infer the spatial location of objects. Moreover, we introduce self-supervision of target rays projected in multiple directions to ensure geometric and color consistency in adjacent regions. Benefiting from the collaboration at the input and output ends, ColNeRF is capable of capturing richer and more generalized scene representation, thereby facilitating higher-quality results of the novel view synthesis. Extensive experiments demonstrate that ColNeRF outperforms state-of-the-art sparse input generalizable NeRF methods. Furthermore, our approach exhibits superiority in fine-tuning towards adapting to new scenes, achieving competitive performance compared to per-scene optimized NeRF-based methods while significantly reducing computational costs. Our code is available at: https://github.com/eezkni/ColNeRF.
Authors: Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang
We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often require days of training, and are extremely slow at inference time. Recently, the community has explored fast grid structures for efficient training of clothed avatars. Albeit being extremely fast at training, these methods can barely achieve an interactive rendering frame rate with around 15 FPS. In this paper, we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS). Given the explicit nature of our representation, we further introduce as-isometric-as-possible regularizations on both the Gaussian mean vectors and the covariance matrices, enhancing the generalization of our model on highly articulated unseen poses. Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input, while being 400x and 250x faster in training and inference, respectively.