Authors: Andrew Hou, Feng Liu, Zhiyuan Ren, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
We propose INFAMOUS-NeRF, an implicit morphable face model that introduces hypernetworks to NeRF to improve the representation power in the presence of many training subjects. At the same time, INFAMOUS-NeRF resolves the classic hypernetwork tradeoff of representation power and editability by learning semantically-aligned latent spaces despite the subject-specific models, all without requiring a large pretrained model. INFAMOUS-NeRF further introduces a novel constraint to improve NeRF rendering along the face boundary. Our constraint can leverage photometric surface rendering and multi-view supervision to guide surface color prediction and improve rendering near the surface. Finally, we introduce a novel, loss-guided adaptive sampling method for more effective NeRF training by reducing the sampling redundancy. We show quantitatively and qualitatively that our method achieves higher representation power than prior face modeling methods in both controlled and in-the-wild settings. Code and models will be released upon publication.
Authors: Keyan Chen, Chengyang Liu, Wenyuan Li, Zili Liu, Hao Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
Change detection, a prominent research area in remote sensing, is pivotal in observing and analyzing surface transformations. Despite significant advancements achieved through deep learning-based methods, executing high-precision change detection in spatio-temporally complex remote sensing scenarios still presents a substantial challenge. The recent emergence of foundation models, with their powerful universality and generalization capabilities, offers potential solutions. However, bridging the gap of data and tasks remains a significant obstacle. In this paper, we introduce Time Travelling Pixels (TTP), a novel approach that integrates the latent knowledge of the SAM foundation model into change detection. This method effectively addresses the domain shift in general knowledge transfer and the challenge of expressing homogeneous and heterogeneous characteristics of multi-temporal images. The state-of-the-art results obtained on the LEVIR-CD underscore the efficacy of the TTP. The Code is available at \url{https://kychen.me/TTP}.
Authors: Jiaxin Ge, Xinyan Chen, Tianjun Zhang, Shanghang Zhang
Diffusion models have shown impressive performance in many domains, including image generation, time series prediction, and reinforcement learning. The algorithm demonstrates superior performance over the traditional GAN and transformer based methods. However, the model's capability to follow natural language instructions (e.g., spatial relationships between objects, generating complex scenes) is still unsatisfactory. This has been an important research area to enhance such capability. Prior works adopt reinforcement learning to adjust the behavior of the diffusion models. However, RL methods not only require careful reward design and complex hyperparameter tuning, but also fails to incorporate rich natural language feedback. In this work, we propose iterative prompt relabeling (IP-RLDF), a novel algorithm that aligns images to text through iterative image sampling and prompt relabeling. IP-RLDF first samples a batch of images conditioned on the text, then relabels the text prompts of unmatched text-image pairs with classifier feedback. We conduct thorough experiments on three different models, including SDv2, GLIGEN, and SDXL, testing their capability to generate images following instructions. With IP-RLDF, we improved up to 15.22% (absolute improvement) on the challenging spatial relation VISOR benchmark, demonstrating superior performance compared to previous RL methods.
Authors: Nikhil Behari, Akshat Dave, Kushagra Tiwary, William Yang, Ramesh Raskar
3D modeling from satellite imagery is essential in areas of environmental science, urban planning, agriculture, and disaster response. However, traditional 3D modeling techniques face unique challenges in the remote sensing context, including limited multi-view baselines over extensive regions, varying direct, ambient, and complex illumination conditions, and time-varying scene changes across captures. In this work, we introduce SUNDIAL, a comprehensive approach to 3D reconstruction of satellite imagery using neural radiance fields. We jointly learn satellite scene geometry, illumination components, and sun direction in this single-model approach, and propose a secondary shadow ray casting technique to 1) improve scene geometry using oblique sun angles to render shadows, 2) enable physically-based disentanglement of scene albedo and illumination, and 3) determine the components of illumination from direct, ambient (sky), and complex sources. To achieve this, we incorporate lighting cues and geometric priors from remote sensing literature in a neural rendering approach, modeling physical properties of satellite scenes such as shadows, scattered sky illumination, and complex illumination and shading of vegetation and water. We evaluate the performance of SUNDIAL against existing NeRF-based techniques for satellite scene modeling and demonstrate improved scene and lighting disentanglement, novel view and lighting rendering, and geometry and sun direction estimation on challenging scenes with small baselines, sparse inputs, and variable illumination.
Authors: Xiaoqi Li, Mingxu Zhang, Yiran Geng, Haoran Geng, Yuxing Long, Yan Shen, Renrui Zhang, Jiaming Liu, Hao Dong
Robot manipulation relies on accurately predicting contact points and end-effector directions to ensure successful operation. However, learning-based robot manipulation, trained on a limited category within a simulator, often struggles to achieve generalizability, especially when confronted with extensive categories. Therefore, we introduce an innovative approach for robot manipulation that leverages the robust reasoning capabilities of Multimodal Large Language Models (MLLMs) to enhance the stability and generalization of manipulation. By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation. The fundamental insight lies in the introduced fine-tuning paradigm, encompassing object category understanding, affordance prior reasoning, and object-centric pose prediction to stimulate the reasoning ability of MLLM in manipulation. During inference, our approach utilizes an RGB image and text prompt to predict the end effector's pose in chain of thoughts. After the initial contact is established, an active impedance adaptation policy is introduced to plan the upcoming waypoints in a closed-loop manner. Moreover, in real world, we design a test-time adaptation (TTA) strategy for manipulation to enable the model better adapt to the current real-world scene configuration. Experiments in simulator and real-world show the promising performance of ManipLLM. More details and demonstrations can be found at https://sites.google.com/view/manipllm.
Authors: Christian Simon, Sen He, Juan-Manuel Perez-Rua, Frost Xu, Amine Benhalloum, Tao Xiang
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To overcome the limitations of existing approaches regarding generalization and consistency, we introduce a novel neural rendering technique. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Specifically, our method builds neural encoding volumes from generated multi-view inputs. We adjust the weights of the SDF network conditioned on an input image at test-time to allow model adaptation to novel scenes in a feed-forward manner via HyperNetworks. To mitigate artifacts derived from the synthesized views, we propose the use of a volume transformer module to improve the aggregation of image features instead of processing each viewpoint separately. Through our proposed method, dubbed as Hyper-VolTran, we avoid the bottleneck of scene-specific optimization and maintain consistency across the images generated from multiple viewpoints. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
Authors: Mirko Casu, Luca Guarnera, Pasquale Caponnetto, Sebastiano Battiato
This paper provides a comprehensive analysis of cognitive biases in forensics and digital forensics, examining their implications for decision-making processes in these fields. It explores the various types of cognitive biases that may arise during forensic investigations and digital forensic analyses, such as confirmation bias, expectation bias, overconfidence in errors, contextual bias, and attributional biases. It also evaluates existing methods and techniques used to mitigate cognitive biases in these contexts, assessing the effectiveness of interventions aimed at reducing biases and improving decision-making outcomes. Additionally, this paper introduces a new cognitive bias, called "impostor bias", that may affect the use of generative Artificial Intelligence (AI) tools in forensics and digital forensics. The impostor bias is the tendency to doubt the authenticity or validity of the output generated by AI tools, such as deepfakes, in the form of audio, images, and videos. This bias may lead to erroneous judgments or false accusations, undermining the reliability and credibility of forensic evidence. The paper discusses the potential causes and consequences of the impostor bias, and suggests some strategies to prevent or counteract it. By addressing these topics, this paper seeks to offer valuable insights into understanding cognitive biases in forensic practices and provide recommendations for future research and practical applications to enhance the objectivity and validity of forensic investigations.
Authors: Rohit Lal, Yash Garg, Arindam Dutta, Calvin-Khang Ta, Dripta S. Raychaudhuri, M. Salman Asif, Amit K. Roy-Chowdhury
Existing 3D human pose estimation methods perform remarkably well in both monocular and multi-view settings. However, their efficacy diminishes significantly in the presence of heavy occlusions, which limits their practical utility. For video sequences, temporal continuity can help infer accurate poses, especially in heavily occluded frames. In this paper, we aim to leverage this potential of temporal continuity through human motion priors, coupled with large-scale pre-training on 3D poses and self-supervised learning, to enhance 3D pose estimation in a given video sequence. This leads to a temporally continuous 3D pose estimate on unlabelled in-the-wild videos, which may contain occlusions, while exclusively relying on pre-trained 3D pose models. We propose an unsupervised method named TEMP3D that aligns a motion prior model on a given in-the-wild video using existing SOTA single image-based 3D pose estimation methods to give temporally continuous output under occlusions. To evaluate our method, we test it on the Occluded Human3.6M dataset, our custom-built dataset which contains significantly large (up to 100%) human body occlusions incorporated into the Human3.6M dataset. We achieve SOTA results on Occluded Human3.6M and the OcMotion dataset while maintaining competitive performance on non-occluded data. URL: https://sites.google.com/ucr.edu/temp3d
Authors: Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu
In this paper, we delve into the nuanced challenge of tailoring the Segment Anything Models (SAMs) for integration with event data, with the overarching objective of attaining robust and universal object segmentation within the event-centric domain. One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery. Capitalizing on the vast repositories of datasets with paired events and RGB images, our proposition is to harness and extrapolate the profound knowledge encapsulated within the pre-trained SAM framework. As a cornerstone to achieving this, we introduce a multi-scale feature distillation methodology. This methodology rigorously optimizes the alignment of token embeddings originating from event data with their RGB image counterparts, thereby preserving and enhancing the robustness of the overall architecture. Considering the distinct significance that token embeddings from intermediate layers hold for higher-level embeddings, our strategy is centered on accurately calibrating the pivotal token embeddings. This targeted calibration is aimed at effectively managing the discrepancies in high-level embeddings originating from both the event and image domains. Extensive experiments on different datasets demonstrate the effectiveness of the proposed distillation method. Code in this http URL
Authors: Akram Abderraouf Gharbi, Ammar Chouchane, Abdelmalik Ouamane
Person re-identification (PRe-ID) is a computer vision issue, that has been a fertile research area in the last few years. It aims to identify persons across different non-overlapping camera views. In this paper, We propose a novel PRe-ID system that combines tensor feature representation and multilinear subspace learning. Our method exploits the power of pre-trained Convolutional Neural Networks (CNNs) as a strong deep feature extractor, along with two complementary descriptors, Local Maximal Occurrence (LOMO) and Gaussian Of Gaussian (GOG). Then, Tensor-based Cross-View Quadratic Discriminant Analysis (TXQDA) is used to learn a discriminative subspace that enhances the separability between different individuals. Mahalanobis distance is used to match and similarity computation between query and gallery samples. Finally, we evaluate our approach by conducting experiments on three datasets VIPeR, GRID, and PRID450s.
Authors: Peng Ye, Chenyu Huang, Mingzhu Shen, Tao Chen, Yongqi Huang, Yuning Zhang, Wanli Ouyang
This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified model, yielding still good performance on each task or domain. Previous model merging works focus on either CNNs or NLP models, leaving the ViTs merging research untouched. To fill this gap, we first explore and find that existing model merging methods cannot well handle the merging of the whole ViT models and still have improvement space. To enable the merging of the whole ViT, we propose a simple-but-effective gating network that can both merge all kinds of layers (e.g., Embedding, Norm, Attention, and MLP) and select the suitable classifier. Specifically, the gating network is trained by unlabeled datasets from all the tasks (domains), and predicts the probability of which task (domain) the input belongs to for merging the models during inference. To further boost the performance of the merged model, especially when the difficulty of merging tasks increases, we design a novel metric of model weight similarity, and utilize it to realize controllable and combined weight merging. Comprehensive experiments on kinds of newly established benchmarks, validate the superiority of the proposed ViT merging framework for different tasks and domains. Our method can even merge beyond 10 ViT models from different vision tasks with a negligible effect on the performance of each task.
Authors: Andong Lu, jiacong Zhao, Chenglong Li, Jin Tang, Bin Luo
Current RGBT tracking researches mainly focus on the modality-complete scenarios, overlooking the modality-missing challenge in real-world scenes. In this work, we comprehensively investigate the impact of modality-missing challenge in RGBT tracking and propose a novel invertible prompt learning approach, which integrates the content-preserving prompts into a well-trained tracking model to adapt to various modality-missing scenarios, for modality-missing RGBT tracking. In particular, given one modality-missing scenario, we propose to utilize the available modality to generate the prompt of the missing modality to adapt to RGBT tracking model. However, the cross-modality gap between available and missing modalities usually causes semantic distortion and information loss in prompt generation. To handle this issue, we propose the invertible prompt learning scheme by incorporating the full reconstruction of the input available modality from the prompt in prompt generation model. Considering that there lacks a modality-missing RGBT tracking dataset and many modality-missing scenarios are difficult to capture, we design a high-quality data simulation method based on hierarchical combination schemes to generate real-world modality-missing data. Extensive experiments on three modality-missing datasets show that our method achieves significant performance improvements compared with state-of-the-art methods. We will release the code and simulation dataset.
Authors: Yunhao Du, Cheng Lei, Zhicheng Zhao, Fei Su
Referring multi-object tracking (RMOT) aims to track multiple objects based on input textual descriptions. Previous works realize it by simply integrating an extra textual module into the multi-object tracker. However, they typically need to retrain the entire framework and have difficulties in optimization. In this work, we propose an insertable Knowledge Unification Network, termed iKUN, to enable communication with off-the-shelf trackers in a plug-and-play manner. Concretely, a knowledge unification module (KUM) is designed to adaptively extract visual features based on textual guidance. Meanwhile, to improve the localization accuracy, we present a neural version of Kalman filter (NKF) to dynamically adjust process noise and observation noise based on the current motion status. Moreover, to address the problem of open-set long-tail distribution of textual descriptions, a test-time similarity calibration method is proposed to refine the confidence score with pseudo frequency. Extensive experiments on Refer-KITTI dataset verify the effectiveness of our framework. Finally, to speed up the development of RMOT, we also contribute a more challenging dataset, Refer-Dance, by extending public DanceTrack dataset with motion and dressing descriptions. The code and dataset will be released in https://github.com/dyhBUPT/iKUN.
Authors: Andong Lu, Tianrui Zha, Chenglong Li, Jin Tang, Xiaofeng Wang, Bin Luo
Prevalent nighttime ReID methods typically combine relighting networks and ReID networks in a sequential manner, which not only restricts the ReID performance by the quality of relighting images, but also neglects the effective collaborative modeling between image relighting and person ReID tasks. To handle these problems, we propose a novel Collaborative Enhancement Network called CENet, which performs the multilevel feature interactions in a parallel framework, for nighttime person ReID. In particular, CENet is a parallel Transformer network, in which the designed parallel structure can avoid the impact of the quality of relighting images on ReID performance. To perform effective collaborative modeling between image relighting and person ReID tasks, we integrate the multilevel feature interactions in CENet. Specifically, we share the Transformer encoder to build the low-level feature interaction, and then perform the feature distillation to transfer the high-level features from image relighting to ReID. In addition, the sizes of existing real-world nighttime person ReID datasets are small, and large-scale synthetic ones exhibit substantial domain gaps with real-world data. To leverage both small-scale real-world and large-scale synthetic training data, we develop a multi-domain learning algorithm, which alternately utilizes both kinds of data to reduce the inter-domain difference in the training of CENet. Extensive experiments on two real nighttime datasets, \textit{Night600} and \textit{RGBNT201$_{rgb}$}, and a synthetic nighttime ReID dataset are conducted to validate the effectiveness of CENet. We will release the code and synthetic dataset.
Authors: Shi Guo, Jianqi Ma, Xi Yang, Zhengqiang Zhang, Lei Zhang
Denoising and demosaicking are two fundamental steps in reconstructing a clean full-color video from raw data, while performing video denoising and demosaicking jointly, namely VJDD, could lead to better video restoration performance than performing them separately. In addition to restoration accuracy, another key challenge to VJDD lies in the temporal consistency of consecutive frames. This issue exacerbates when perceptual regularization terms are introduced to enhance video perceptual quality. To address these challenges, we present a new VJDD framework by consistent and accurate latent space propagation, which leverages the estimation of previous frames as prior knowledge to ensure consistent recovery of the current frame. A data temporal consistency (DTC) loss and a relational perception consistency (RPC) loss are accordingly designed. Compared with the commonly used flow-based losses, the proposed losses can circumvent the error accumulation problem caused by inaccurate flow estimation and effectively handle intensity changes in videos, improving much the temporal consistency of output videos while preserving texture details. Extensive experiments demonstrate the leading VJDD performance of our method in term of restoration accuracy, perceptual quality and temporal consistency. Codes and dataset are available at \url{https://github.com/GuoShi28/VJDD}.
Authors: Anqi Yi, Nantheera Anantrasirichai
Accurate object tracking in low-light environments is crucial, particularly in surveillance and ethology applications. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as noise, color imbalance, and low contrast contribute to these challenges. This paper presents a comprehensive study examining the impact of these distortions on automatic object trackers. Additionally, we propose a solution to enhance tracking performance by integrating denoising and low-light enhancement methods into the transformer-based object tracking system. Experimental results show that the proposed tracker, trained with low-light synthetic datasets, outperforms both the vanilla MixFormer and Siam R-CNN.
Authors: Xiangyuan Xue, Kailing Wang, Jiazi Bu, Qirui Li, Zhiyuan Zhang
In this work, we propose MetaScript, a novel Chinese content generation system designed to address the diminishing presence of personal handwriting styles in the digital representation of Chinese characters. Our approach harnesses the power of few-shot learning to generate Chinese characters that not only retain the individual's unique handwriting style but also maintain the efficiency of digital typing. Trained on a diverse dataset of handwritten styles, MetaScript is adept at producing high-quality stylistic imitations from minimal style references and standard fonts. Our work demonstrates a practical solution to the challenges of digital typography in preserving the personal touch in written communication, particularly in the context of Chinese script. Notably, our system has demonstrated superior performance in various evaluations, including recognition accuracy, inception score, and Frechet inception distance. At the same time, the training conditions of our model are easy to meet and facilitate generalization to real applications.
Authors: Lu Ling, Yichen Sheng, Zhi Tu, Wentian Zhao, Cheng Xin, Kun Wan, Lantao Yu, Qianyu Guo, Zixun Yu, Yawen Lu, Xuanmao Li, Xingpeng Sun, Rohan Ashok, Aniruddha Mukherjee, Hao Kang, Xiangrui Kong, Gang Hua, Tianti Zhang, Bedrich Benes, Aniket Bera
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/.
Authors: Seungchan Lim, Sumin Kim, Sung-Hee Lee
This paper presents a novel method for reconstructing 3D garment models from a single image of a posed user. Previous studies that have primarily focused on accurately reconstructing garment geometries to match the input garment image may often result in unnatural-looking garments when deformed for new poses. To overcome this limitation, our approach takes a different approach by inferring the fundamental shape of the garment through sewing patterns from a single image, rather than directly reconstructing 3D garments. Our method consists of two stages. Firstly, given a single image of a posed user, it predicts the garment image worn on a T-pose, representing the baseline form of the garment. Then, it estimates the sewing pattern parameters based on the T-pose garment image. By simulating the stitching and draping of the sewing pattern using physics simulation, we can generate 3D garments that can adaptively deform to arbitrary poses. The effectiveness of our method is validated through ablation studies on the major components and a comparison with other approaches.
Authors: Zhijie Shen, Chunyu Lin, Junsong Zhang, Lang Nie, Kang Liao, Yao Zhao
Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these data-driven approaches impose an urgent demand for massive data annotations, which are laborious and time-consuming. For the first problem, we propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. DOPNet consists of three modules that are integrated to deliver distortion-free, semantics-clean, and detail-sharp disentangled representations, which benefit the subsequent layout recovery. For the second problem, we present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Concretely, we introduce an optimization strategy for decision-level layout analysis and a 1D cost volume construction method for feature-level multi-view aggregation, both of which are designed to fully exploit the geometric consistency across multiple perspectives. The optimizer provides a reliable set of pseudo-labels for network training, while the 1D cost volume enriches each view with comprehensive scene information derived from other perspectives. Extensive experiments demonstrate that our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks.
Authors: Yuxuan Zhang, Jiaming Liu, Yiren Song, Rui Wang, Hao Tang, Jinpeng Yu, Huaxia Li, Xu Tang, Yao Hu, Han Pan, Zhongliang Jing
Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging. Addressing this, we introduce the SSR-Encoder, a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks, without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and preserving fine features of the subjects, thereby generating subject embeddings. These embeddings, used in conjunction with original text embeddings, condition the generation process. Characterized by its model generalizability and efficiency, the SSR-Encoder adapts to a range of custom models and control modules. Enhanced by the Embedding Consistency Regularization Loss for improved training, our extensive experiments demonstrate its effectiveness in versatile and high-quality image generation, indicating its broad applicability. Project page: https://ssr-encoder.github.io
Authors: Jingjing Ren, Cheng Xu, Haoyu Chen, Xinran Qin, Chongyi Li, Lei Zhu
Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images. Yet, current methods still face issues with scalability, limited flexibility, and a one-size-fits-all approach to control strength, not accounting for the differing levels of conditional entropy, a measure of unpredictability in data given some condition, across modalities. To address these challenges, we introduce a novel uni-modal training approach with modal surrogates, coupled with an entropy-aware modal-adaptive modulation, to support flexible, scalable, and scalable multi-modal conditioned face synthesis network. Our uni-modal training with modal surrogate that only leverage uni-modal data, use modal surrogate to decorate condition with modal-specific characteristic and serve as linker for inter-modal collaboration , fully learns each modality control in face synthesis process as well as inter-modal collaboration. The entropy-aware modal-adaptive modulation finely adjust diffusion noise according to modal-specific characteristics and given conditions, enabling well-informed step along denoising trajectory and ultimately leading to synthesis results of high fidelity and quality. Our framework improves multi-modal face synthesis under various conditions, surpassing current methods in image quality and fidelity, as demonstrated by our thorough experimental results.
Authors: Guanqun Wang, Jiaming Liu, Chenxuan Li, Junpeng Ma, Yuan Zhang, Xinyu Wei, Kevin Zhang, Maurice Chong, Ray Zhang, Yijiang Liu, Shanghang Zhang
The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters, leading to a notable decline in generalization capabilities when these models are compressed for device deployment. Addressing this challenge, we introduce a Cloud-Device Collaborative Continual Adaptation framework, designed to enhance the performance of compressed, device-deployed MLLMs by leveraging the robust capabilities of cloud-based, larger-scale MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission, cloud-based knowledge adaptation, and an optimized cloud-to-device downlink for model deployment. In the uplink phase, we employ an Uncertainty-guided Token Sampling (UTS) strategy to effectively filter out-of-distribution tokens, thereby reducing transmission costs and improving training efficiency. On the cloud side, we propose Adapter-based Knowledge Distillation (AKD) method to transfer refined knowledge from large-scale to compressed, pocket-size MLLMs. Furthermore, we propose a Dynamic Weight update Compression (DWC) strategy for the downlink, which adaptively selects and quantizes updated weight parameters, enhancing transmission efficiency and reducing the representational disparity between cloud and device models. Extensive experiments on several multimodal benchmarks demonstrate the superiority of our proposed framework over prior Knowledge Distillation and device-cloud collaboration methods. Notably, we also validate the feasibility of our approach to real-world experiments.
Authors: Asim Khan, Umair Nawaz, Lochan Kshetrimayum, Lakmal Seneviratne, Irfan Hussain
Tomato leaf diseases pose a significant challenge for tomato farmers, resulting in substantial reductions in crop productivity. The timely and precise identification of tomato leaf diseases is crucial for successfully implementing disease management strategies. This paper introduces a transformer-based model called TomFormer for the purpose of tomato leaf disease detection. The paper's primary contributions include the following: Firstly, we present a novel approach for detecting tomato leaf diseases by employing a fusion model that combines a visual transformer and a convolutional neural network. Secondly, we aim to apply our proposed methodology to the Hello Stretch robot to achieve real-time diagnosis of tomato leaf diseases. Thirdly, we assessed our method by comparing it to models like YOLOS, DETR, ViT, and Swin, demonstrating its ability to achieve state-of-the-art outcomes. For the purpose of the experiment, we used three datasets of tomato leaf diseases, namely KUTomaDATA, PlantDoc, and PlanVillage, where KUTomaDATA is being collected from a greenhouse in Abu Dhabi, UAE. Finally, we present a comprehensive analysis of the performance of our model and thoroughly discuss the limitations inherent in our approach. TomFormer performed well on the KUTomaDATA, PlantDoc, and PlantVillage datasets, with mean average accuracy (mAP) scores of 87%, 81%, and 83%, respectively. The comparative results in terms of mAP demonstrate that our method exhibits robustness, accuracy, efficiency, and scalability. Furthermore, it can be readily adapted to new datasets. We are confident that our work holds the potential to significantly influence the tomato industry by effectively mitigating crop losses and enhancing crop yields.
Authors: Fatih Cagatay Akyon, Alptekin Temizel
This paper presents a comparative analysis of existing nudity classification techniques for classifying images based on the presence of nudity, with a focus on their application in content moderation. The evaluation focuses on CNN-based models, vision transformer, and popular open-source safety checkers from Stable Diffusion and Large-scale Artificial Intelligence Open Network (LAION). The study identifies the limitations of current evaluation datasets and highlights the need for more diverse and challenging datasets. The paper discusses the potential implications of these findings for developing more accurate and effective image classification systems on online platforms. Overall, the study emphasizes the importance of continually improving image classification models to ensure the safety and well-being of platform users. The project page, including the demonstrations and results is publicly available at https://github.com/fcakyon/content-moderation-deep-learning.
Authors: Ping-yeh Chiang, Yipin Zhou, Omid Poursaeed, Satya Narayan Shukla, Ashish Shah, Tom Goldstein, Ser-Nam Lim
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transformers. However, due to the iterative nature of adversarial training, the technique is up to 7 times more expensive than standard training. To make the method more efficient, we propose Universal Pyramid Adversarial training, where we learn a single pyramid adversarial pattern shared across the whole dataset instead of the sample-wise patterns. With our proposed technique, we decrease the computational cost of Pyramid Adversarial training by up to 70% while retaining the majority of its benefit on clean performance and distribution-shift robustness. In addition, to the best of our knowledge, we are also the first to find that universal adversarial training can be leveraged to improve clean model performance.
Authors: Sunoh Kim, Jungchan Cho, Joonsang Yu, YoungJoon Yoo, Jin Young Choi
In the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query. To enhance the expression ability of a proposal, we propose a Gaussian mixture proposal (GMP) that can depict arbitrary shapes by learning importance, centroid, and range of every Gaussian in the mixture. In learning GMP, each Gaussian is not trained in a feature space but is implemented over a temporal location. Thus the conventional feature-based learning for Gaussian mixture model is not valid for our case. In our special setting, to learn moderately coupled Gaussian mixture capturing diverse events, we newly propose a pull-push learning scheme using pulling and pushing losses, each of which plays an opposite role to the other. The effects of components in our scheme are verified in-depth with extensive ablation studies and the overall scheme achieves state-of-the-art performance. Our code is available at https://github.com/sunoh-kim/pps.
Authors: Woochul Kang
Systematic adaptation of network depths at runtime can be an effective way to control inference latency and meet the resource condition of various devices. However, previous depth adaptive networks do not provide general principles and a formal explanation on why and which layers can be skipped, and, hence, their approaches are hard to be generalized and require long and complex training steps. In this paper, we present an architectural pattern and training method for adaptive depth networks that can provide flexible accuracy-efficiency trade-offs in a single network. In our approach, every residual stage is divided into 2 consecutive sub-paths with different properties. While the first sub-path is mandatory for hierarchical feature learning, the other is optimized to incur minimal performance degradation even if it is skipped. Unlike previous adaptive networks, our approach does not iteratively self-distill a fixed set of sub-networks, resulting in significantly shorter training time. However, once deployed on devices, it can instantly construct sub-networks of varying depths to provide various accuracy-efficiency trade-offs in a single model. We provide a formal rationale for why the proposed architectural pattern and training method can reduce overall prediction errors while minimizing the impact of skipping selected sub-paths. We also demonstrate the generality and effectiveness of our approach with various residual networks, both from convolutional neural networks and vision transformers.
Authors: Xianyi Chen, Fazhan Liu, Dong Jiang, Kai Yan
Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial patches, with their conspicuous and unusual patterns, lack camouflage and can easily raise suspicion in the real world. To solve this problem, this paper proposed a novel adversarial patch method called the Latent Diffusion Patch (LDP), in which, a pretrained encoder is first designed to compress the natural images into a feature space with key characteristics. Then trains the diffusion model using the above feature space. Finally, explore the latent space of the pretrained diffusion model using the image denoising technology. It polishes the patches and images through the powerful natural abilities of diffusion models, making them more acceptable to the human visual system. Experimental results, both digital and physical worlds, show that LDPs achieve a visual subjectivity score of 87.3%, while still maintaining effective attack capabilities.
Authors: Yan Fan, Yu Wang, Pengfei Zhu, Qinghua Hu
Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem severely impacts the performance of SSCL. To address the limitations, we propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning, which leverages both semantic and structural information to achieve more stable knowledge distillation on unlabeled data and exhibit robustness against distribution bias. Firstly, we formalize a general model of structural distillation and design a dynamic graph construction for the continual learning progress. Next, we define a structure distillation vector and design a dynamic sub-graph distillation algorithm, which enables end-to-end training and adaptability to scale up tasks. The entire proposed method is adaptable to various CL methods and supervision settings. Finally, experiments conducted on three datasets CIFAR10, CIFAR100, and ImageNet-100, with varying supervision ratios, demonstrate the effectiveness of our proposed approach in mitigating the catastrophic forgetting problem in semi-supervised continual learning scenarios.
Authors: Xiaoliang Tan, Guanzhou Chen, Tong Wang, Jiaqi Wang, Xiaodong Zhang
The field of Remote Sensing (RS) widely employs Change Detection (CD) on very-high-resolution (VHR) images. A majority of extant deep-learning-based methods hinge on annotated samples to complete the CD process. Recently, the emergence of Vision Foundation Model (VFM) enables zero-shot predictions in particular vision tasks. In this work, we propose an unsupervised CD method named Segment Change Model (SCM), built upon the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP). Our method recalibrates features extracted at different scales and integrates them in a top-down manner to enhance discriminative change edges. We further design an innovative Piecewise Semantic Attention (PSA) scheme, which can offer semantic representation without training, thereby minimize pseudo change phenomenon. Through conducting experiments on two public datasets, the proposed SCM increases the mIoU from 46.09% to 53.67% on the LEVIR-CD dataset, and from 47.56% to 52.14% on the WHU-CD dataset. Our codes are available at https://github.com/StephenApX/UCD-SCM.
Authors: Bao Nguyen, Binh Nguyen, Viet Anh Nguyen
Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the fine-tuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Step-size Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programming algorithm that optimizes the step sizes of the pretrained network. Then, it refines the velocity network to match the optimal step sizes, aiming to straighten the generation paths. Extensive experimental evaluations across image generation tasks demonstrate the efficacy of BOSS in terms of both resource utilization and image quality. Our results reveal that BOSS achieves substantial gains in efficiency while maintaining competitive sample quality, effectively bridging the gap between low-resource constraints and the demanding requirements of flow-matching generative models. Our paper also fortifies the responsible development of artificial intelligence, offering a more sustainable generative model that reduces computational costs and environmental footprints. Our code can be found at https://anonymous.4open.science/r/DRL-8E88.
Authors: Shijian Jiang, Qi Ye, Rengan Xie, Yuchi Huo, Xiang Li, Yang Zhou, Jiming Chen
Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object. However, these methods falter in accurately capturing the shape within the hand-object contact region due to occlusion. In this paper, we propose a novel method that deals with surface reconstruction under occlusion by incorporating priors of 2D occlusion elucidation and physical contact constraints. For the former, we introduce an object amodal completion network to infer the 2D complete mask of objects under occlusion. To ensure the accuracy and view consistency of the predicted 2D amodal masks, we devise a joint optimization method for both amodal mask refinement and 3D reconstruction. For the latter, we impose penetration and attraction constraints on the local geometry in contact regions. We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD. Project webpage: https://east-j.github.io/ihor.
Authors: Ingyun Lee, Wooju Lee, Hyun Myung
Deep neural networks have shown remarkable performance in image classification. However, their performance significantly deteriorates with corrupted input data. Domain generalization methods have been proposed to train robust models against out-of-distribution data. Data augmentation in the frequency domain is one of such approaches that enable a model to learn phase features to establish domain-invariant representations. This approach changes the amplitudes of the input data while preserving the phases. However, using fixed phases leads to susceptibility to phase fluctuations because amplitudes and phase fluctuations commonly occur in out-of-distribution. In this study, to address this problem, we introduce an approach using finite variation of the phases of input data rather than maintaining fixed phases. Based on the assumption that the degree of domain-invariant features varies for each phase, we propose a method to distinguish phases based on this degree. In addition, we propose a method called vital phase augmentation (VIPAug) that applies the variation to the phases differently according to the degree of domain-invariant features of given phases. The model depends more on the vital phases that contain more domain-invariant features for attaining robustness to amplitude and phase fluctuations. We present experimental evaluations of our proposed approach, which exhibited improved performance for both clean and corrupted data. VIPAug achieved SOTA performance on the benchmark CIFAR-10 and CIFAR-100 datasets, as well as near-SOTA performance on the ImageNet-100 and ImageNet datasets. Our code is available at https://github.com/excitedkid/vipaug.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Kaiyuan Jiang, Zhengmi Tang, Shinichiro Omachi
Background and objective: High-resolution radiographic images play a pivotal role in the early diagnosis and treatment of skeletal muscle-related diseases. It is promising to enhance image quality by introducing single-image super-resolution (SISR) model into the radiology image field. However, the conventional image pipeline, which can learn a mixed mapping between SR and denoising from the color space and inter-pixel patterns, poses a particular challenge for radiographic images with limited pattern features. To address this issue, this paper introduces a novel approach: Orientation Operator Transformer - $O^{2}$former. Methods: We incorporate an orientation operator in the encoder to enhance sensitivity to denoising mapping and to integrate orientation prior. Furthermore, we propose a multi-scale feature fusion strategy to amalgamate features captured by different receptive fields with the directional prior, thereby providing a more effective latent representation for the decoder. Based on these innovative components, we propose a transformer-based SISR model, i.e., $O^{2}$former, specifically designed for radiographic images. Results: The experimental results demonstrate that our method achieves the best or second-best performance in the objective metrics compared with the competitors at $\times 4$ upsampling factor. For qualitative, more objective details are observed to be recovered. Conclusions: In this study, we propose a novel framework called $O^{2}$former for radiological image super-resolution tasks, which improves the reconstruction model's performance by introducing an orientation operator and multi-scale feature fusion strategy. Our approach is promising to further promote the radiographic image enhancement field.
Authors: Kaiwen Song, Juyong Zhang
NeRF has significantly advanced 3D scene reconstruction, capturing intricate details across various environments. Existing methods have successfully leveraged radiance field baking to facilitate real-time rendering of small scenes. However, when applied to large-scale scenes, these techniques encounter significant challenges, struggling to provide a seamless real-time experience due to limited resources in computation, memory, and bandwidth. In this paper, we propose City-on-Web, which represents the whole scene by partitioning it into manageable blocks, each with its own Level-of-Detail, ensuring high fidelity, efficient memory management and fast rendering. Meanwhile, we carefully design the training and inference process such that the final rendering result on web is consistent with training. Thanks to our novel representation and carefully designed training/inference process, we are the first to achieve real-time rendering of large-scale scenes in resource-constrained environments. Extensive experimental results demonstrate that our method facilitates real-time rendering of large-scale scenes on a web platform, achieving 32FPS at 1080P resolution with an RTX 3060 GPU, while simultaneously achieving a quality that closely rivals that of state-of-the-art methods. Project page: https://ustc3dv.github.io/City-on-Web/
Authors: Jingqi Niu, Qinji Yu, Shiwen Dong, Zilong Wang, Kang Dang, Xiaowei Ding
Detecting anomalies in fundus images through unsupervised methods is a challenging task due to the similarity between normal and abnormal tissues, as well as their indistinct boundaries. The current methods have limitations in accurately detecting subtle anomalies while avoiding false positives. To address these challenges, we propose the ReSynthDetect network which utilizes a reconstruction network for modeling normal images, and an anomaly generator that produces synthetic anomalies consistent with the appearance of fundus images. By combining the features of consistent anomaly generation and image reconstruction, our method is suited for detecting fundus abnormalities. The proposed approach has been extensively tested on benchmark datasets such as EyeQ and IDRiD, demonstrating state-of-the-art performance in both image-level and pixel-level anomaly detection. Our experiments indicate a substantial 9% improvement in AUROC on EyeQ and a significant 17.1% improvement in AUPR on IDRiD.
Authors: Ankush Maity, Roshan Pious, Sourabh Kumar Lenka, Vishal Choudhary, Prof.Sharyau Lokande
This compilation of various research paper highlights provides a comprehensive overview of recent developments in super-resolution image and video using deep learning algorithms such as Generative Adversarial Networks. The studies covered in these summaries provide fresh techniques to addressing the issues of improving image and video quality, such as recursive learning for video super-resolution, novel loss functions, frame-rate enhancement, and attention model integration. These approaches are frequently evaluated using criteria such as PSNR, SSIM, and perceptual indices. These advancements, which aim to increase the visual clarity and quality of low-resolution video, have tremendous potential in a variety of sectors ranging from surveillance technology to medical imaging. In addition, this collection delves into the wider field of Generative Adversarial Networks, exploring their principles, training approaches, and applications across a broad range of domains, while also emphasizing the challenges and opportunities for future research in this rapidly advancing and changing field of artificial intelligence.
Authors: Ximing Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu
Recently, text-guided scalable vector graphics (SVGs) synthesis has shown promise in domains such as iconography and sketch. However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity. To address these limitations, we propose a novel text-guided vector graphics synthesis method called SVGDreamer. SVGDreamer incorporates a semantic-driven image vectorization (SIVE) process that enables the decomposition of synthesis into foreground objects and background, thereby enhancing editability. Specifically, the SIVE process introduce attention-based primitive control and an attention-mask loss function for effective control and manipulation of individual elements. Additionally, we propose a Vectorized Particle-based Score Distillation (VPSD) approach to tackle the challenges of color over-saturation, vector primitives over-smoothing, and limited result diversity in existing text-to-SVG generation methods. Furthermore, on the basis of VPSD, we introduce Reward Feedback Learning (ReFL) to accelerate VPSD convergence and improve aesthetic appeal. Extensive experiments have been conducted to validate the effectiveness of SVGDreamer, demonstrating its superiority over baseline methods in terms of editability, visual quality, and diversity.
Authors: Lixiang Xu, Qingzhe Cui, Richang Hong, Wei Xu, Enhong Chen, Xin Yuan, Yuanyan Tang
In recent years, the results of view-based 3D shape recognition methods have saturated, and models with excellent performance cannot be deployed on memory-limited devices due to their huge size of parameters. To address this problem, we introduce a compression method based on knowledge distillation for this field, which largely reduces the number of parameters while preserving model performance as much as possible. Specifically, to enhance the capabilities of smaller models, we design a high-performing large model called Group Multi-view Vision Transformer (GMViT). In GMViT, the view-level ViT first establishes relationships between view-level features. Additionally, to capture deeper features, we employ the grouping module to enhance view-level features into group-level features. Finally, the group-level ViT aggregates group-level features into complete, well-formed 3D shape descriptors. Notably, in both ViTs, we introduce spatial encoding of camera coordinates as innovative position embeddings. Furthermore, we propose two compressed versions based on GMViT, namely GMViT-simple and GMViT-mini. To enhance the training effectiveness of the small models, we introduce a knowledge distillation method throughout the GMViT process, where the key outputs of each GMViT component serve as distillation targets. Extensive experiments demonstrate the efficacy of the proposed method. The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB. The smaller models, GMViT-simple and GMViT-mini, reduce the parameter size by 8 and 17.6 times, respectively, and improve shape recognition speed by 1.5 times on average, while preserving at least 90% of the classification and retrieval performance.
Authors: Guansong Lu, Yuanfan Guo, Jianhua Han, Minzhe Niu, Yihan Zeng, Songcen Xu, Zeyi Huang, Zhao Zhong, Wei Zhang, Hang Xu
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present "PanGu-Draw", a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce "Coop-Diffusion", an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model is released on the Ascend platform. Project page: $\href{https://pangu-draw.github.io}{this~https~URL}$
Authors: Xiao Fang, Xin Gao, Baofeng Li, Feng Zhai, Yu Qin, Zhihang Meng, Jiansheng Lu, Chun Xiao
Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing methods cannot adaptively extract the differentiated luminance information, which will easily cause over-exposure and under-exposure. From the perspective of unsupervised learning, we propose a multi-scale attention Transformer named MSATr, which sufficiently extracts local and global features for light balance to improve the visual quality. Specifically, we present a multi-scale window division scheme, which uses exponential sequences to adjust the window size of each layer. Within different-sized windows, the self-attention computation can be refined, ensuring the pixel-level feature processing capability of the model. For feature interaction across windows, a global transformer branch is constructed to provide comprehensive brightness perception and alleviate exposure problems. Furthermore, we propose a loop training strategy, using the diverse images generated by weighted mixing and a luminance consistency loss to improve the model's generalization ability effectively. Extensive experiments on several benchmark datasets quantitatively and qualitatively prove that our MSATr is superior to state-of-the-art low-light image enhancement methods, and the enhanced images have more natural brightness and outstanding details. The code is released at https://github.com/fang001021/MSATr.
Authors: L Qin, C Lin, S Huang, S Yang, Y Zhao
Surround-view system (SVS) is widely used in the Advanced Driver Assistance System (ADAS). SVS uses four fisheye lenses to monitor real-time scenes around the vehicle. However, accurate intrinsic and extrinsic parameter estimation is required for the proper functioning of the system. At present, the intrinsic calibration can be pipeline by utilizing checkerboard algorithm, while extrinsic calibration is still immature. Therefore, we proposed a specific calibration pipeline to estimate extrinsic parameters robustly. This scheme takes a driving sequence of four cameras as input. It firstly utilizes lane line to roughly estimate each camera pose. Considering the environmental condition differences in each camera, we separately select strategies from two methods to accurately estimate the extrinsic parameters. To achieve accurate estimates for both front and rear camera, we proposed a method that mutually iterating line detection and pose estimation. As for bilateral camera, we iteratively adjust the camera pose and position by minimizing texture and edge error between ground projections of adjacent cameras. After estimating the extrinsic parameters, the surround-view image can be synthesized by homography-based transformation. The proposed pipeline can robustly estimate the four SVS camera extrinsic parameters in real driving environments. In addition, to evaluate the proposed scheme, we build a surround-view fisheye dataset, which contains 40 videos with 32,000 frames, acquired from different real traffic scenarios. All the frames in each video are manually labeled with lane annotation, with its GT extrinsic parameters. Moreover, this surround-view dataset could be used by other researchers to evaluate their performance. The dataset will be available soon.
Authors: Maghsood Salimi, Mohammad Loni, Sara Afshar, Marjan Sirjani, Antonio Cicchetti
The increasing demand for autonomous machines in construction environments necessitates the development of robust object detection algorithms that can perform effectively across various weather and environmental conditions. This paper introduces a new semantic segmentation dataset specifically tailored for construction sites, taking into account the diverse challenges posed by adverse weather and environmental conditions. The dataset is designed to enhance the training and evaluation of object detection models, fostering their adaptability and reliability in real-world construction applications. Our dataset comprises annotated images captured under a wide range of different weather conditions, including but not limited to sunny days, rainy periods, foggy atmospheres, and low-light situations. Additionally, environmental factors such as the existence of dirt/mud on the camera lens are integrated into the dataset through actual captures and synthetic generation to simulate the complex conditions prevalent in construction sites. We also generate synthetic images of the annotations including precise semantic segmentation masks for various objects commonly found in construction environments, such as wheel loader machines, personnel, cars, and structural elements. To demonstrate the dataset's utility, we evaluate state-of-the-art object detection algorithms on our proposed benchmark. The results highlight the dataset's success in adversarial training models across diverse conditions, showcasing its efficacy compared to existing datasets that lack such environmental variability.
Authors: Tomer Garber, Tom Tirer
Training deep neural networks has become a common approach for addressing image restoration problems. An alternative for training a "task-specific" network for each observation model is to use pretrained deep denoisers for imposing only the signal's prior within iterative algorithms, without additional training. Recently, a sampling-based variant of this approach has become popular with the rise of diffusion/score-based generative models. Using denoisers for general purpose restoration requires guiding the iterations to ensure agreement of the signal with the observations. In low-noise settings, guidance that is based on back-projection (BP) has been shown to be a promising strategy (used recently also under the names "pseudoinverse" or "range/null-space" guidance). However, the presence of noise in the observations hinders the gains from this approach. In this paper, we propose a novel guidance technique, based on preconditioning that allows traversing from BP-based guidance to least squares based guidance along the restoration scheme. The proposed approach is robust to noise while still having much simpler implementation than alternative methods (e.g., it does not require SVD or a large number of iterations). We use it within both an optimization scheme and a sampling-based scheme, and demonstrate its advantages over existing methods for image deblurring and super-resolution.
Authors: Miaohui Wang
Blind Image Quality Assessment (BIQA) is essential for automatically evaluating the perceptual quality of visual signals without access to the references. In this survey, we provide a comprehensive analysis and discussion of recent developments in the field of BIQA. We have covered various aspects, including hand-crafted BIQAs that focus on distortion-specific and general-purpose methods, as well as deep-learned BIQAs that employ supervised and unsupervised learning techniques. Additionally, we have explored multimodal quality assessment methods that consider interactions between visual and audio modalities, as well as visual and text modalities. Finally, we have offered insights into representative BIQA databases, including both synthetic and authentic distortions. We believe this survey provides valuable understandings into the latest developments and emerging trends for the visual quality community.
Authors: Hefei Mei, Taijin Zhao, Shiyuan Tang, Heqian Qiu, Lanxiao Wang, Minjian Zhang, Fanman Meng, Hongliang Li
Few-shot object detection (FSOD) aims to achieve object detection only using a few novel class training data. Most of the existing methods usually adopt a transfer-learning strategy to construct the novel class distribution by transferring the base class knowledge. However, this direct way easily results in confusion between the novel class and other similar categories in the decision space. To address the problem, we propose generating local reverse samples (LRSamples) in Prototype Reference Frames to adaptively adjust the center position and boundary range of the novel class distribution to learn more discriminative novel class samples for FSOD. Firstly, we propose a Center Calibration Variance Augmentation (CCVA) module, which contains the selection rule of LRSamples, the generator of LRSamples, and augmentation on the calibrated distribution centers. Specifically, we design an intra-class feature converter (IFC) as the generator of CCVA to learn the selecting rule. By transferring the knowledge of IFC from the base training to fine-tuning, the IFC generates plentiful novel samples to calibrate the novel class distribution. Moreover, we propose a Feature Density Boundary Optimization (FDBO) module to adaptively adjust the importance of samples depending on their distance from the decision boundary. It can emphasize the importance of the high-density area of the similar class (closer decision boundary area) and reduce the weight of the low-density area of the similar class (farther decision boundary area), thus optimizing a clearer decision boundary for each category. We conduct extensive experiments to demonstrate the effectiveness of our proposed method. Our method achieves consistent improvement on the Pascal VOC and MS COCO datasets based on DeFRCN and MFDC baselines.
Authors: Xiawei Li Qingyuan Xu Jing Zhang Tianyi Zhang Qian Yu Lu Sheng Dong Xu
3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging scene-level labels. However, these methods have not effectively exploited the rich geometric information (such as shape and scale) and appearance information (such as color and texture) present in RGB-D scans. Furthermore, current approaches fail to fully leverage the point affinity that can be inferred from the feature extraction network, which is crucial for learning from weak scene-level labels. Additionally, previous work overlooks the detrimental effects of the long-tailed distribution of point cloud data in weakly supervised 3D semantic segmentation. To this end, this paper proposes a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. The point affinity proposed in this paper is characterized by features from multiple modalities (e.g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution. Extensive experiments on the ScanNet and S3DIS benchmarks verify the effectiveness of our proposed method, which outperforms the state-of-the-art by ~4% to ~6% mIoU. Codes are released at https://github.com/Sunny599/AAAI24-3DWSSG-MMA.
Authors: Seunggu Kang, WonJun Moon, Euiyeon Kim, Jae-Pil Heo
Zero-Shot Object Counting (ZSOC) aims to count referred instances of arbitrary classes in a query image without human-annotated exemplars. To deal with ZSOC, preceding studies proposed a two-stage pipeline: discovering exemplars and counting. However, there remains a challenge of vulnerability to error propagation of the sequentially designed two-stage process. In this work, an one-stage baseline, Visual-Language Baseline (VLBase), exploring the implicit association of the semantic-patch embeddings of CLIP is proposed. Subsequently, the extension of VLBase to Visual-language Counter (VLCounter) is achieved by incorporating three modules devised to tailor VLBase for object counting. First, Semantic-conditioned Prompt Tuning (SPT) is introduced within the image encoder to acquire target-highlighted representations. Second, Learnable Affine Transformation (LAT) is employed to translate the semantic-patch similarity map to be appropriate for the counting task. Lastly, the layer-wisely encoded features are transferred to the decoder through Segment-aware Skip Connection (SaSC) to keep the generalization capability for unseen classes. Through extensive experiments on FSC147, CARPK, and PUCPR+, the benefits of the end-to-end framework, VLCounter, are demonstrated.
Authors: Tianxin Huang, Qingyao Liu, Xiangrui Zhao, Jun Chen, Yong Liu
As point clouds are 3D signals with permutation invariance, most existing works train their reconstruction networks by measuring shape differences with the average point-to-point distance between point clouds matched with predefined rules. However, the static matching rules may deviate from actual shape differences. Although some works propose dynamically-updated learnable structures to replace matching rules, they need more iterations to converge well. In this work, we propose a simple but effective reconstruction loss, named Learnable Chamfer Distance (LCD) by dynamically paying attention to matching distances with different weight distributions controlled with a group of learnable networks. By training with adversarial strategy, LCD learns to search defects in reconstructed results and overcomes the weaknesses of static matching rules, while the performances at low iterations can also be guaranteed by the basic matching algorithm. Experiments on multiple reconstruction networks confirm that LCD can help achieve better reconstruction performances and extract more representative representations with faster convergence and comparable training efficiency. The source codes are provided in https://github.com/Tianxinhuang/LCDNet.git.
Authors: Jiaxing Huang, Jingyi Zhang, Kai Jiang, Han Qiu, Shijian Lu
Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision model with language as task instructions, aiming to learn from a wide range of vision tasks described by language instructions a general-purpose multimodal model that can follow arbitrary instructions and thus solve arbitrary tasks specified by the user. This work aims to provide a systematic review of visual instruction tuning, covering (1) the background that presents computer vision task paradigms and the development of VIT; (2) the foundations of VIT that introduce commonly used network architectures, visual instruction tuning frameworks and objectives, and evaluation setups and tasks; (3) the commonly used datasets in visual instruction tuning and evaluation; (4) the review of existing VIT methods that categorizes them with a taxonomy according to both the studied vision task and the method design and highlights the major contributions, strengths, and shortcomings of them; (5) the comparison and discussion of VIT methods over various instruction-following benchmarks; (6) several challenges, open directions and possible future works in visual instruction tuning research.
Authors: Jia Dong, Yao Yao, Liyan Lin, Yang Dong, Jiachen Wan, Ran Peng, Chao Li, Hui Ma
Classifying hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) is a critical step in treatment selection and prognosis evaluation for patients with liver diseases. Traditional histopathological diagnosis poses challenges in this context. In this study, we introduce a novel polarization and radiomics feature fusion network, which combines polarization features obtained from Mueller matrix images of liver pathological samples with radiomics features derived from corresponding pathological images to classify HCC and ICC. Our fusion network integrates a two-tier fusion approach, comprising early feature-level fusion and late classification-level fusion. By harnessing the strengths of polarization imaging techniques and image feature-based machine learning, our proposed fusion network significantly enhances classification accuracy. Notably, even at reduced imaging resolutions, the fusion network maintains robust performance due to the additional information provided by polarization features, which may not align with human visual perception. Our experimental results underscore the potential of this fusion network as a powerful tool for computer-aided diagnosis of HCC and ICC, showcasing the benefits and prospects of integrating polarization imaging techniques into the current image-intensive digital pathological diagnosis. We aim to contribute this innovative approach to top-tier journals, offering fresh insights and valuable tools in the fields of medical imaging and cancer diagnosis. By introducing polarization imaging into liver cancer classification, we demonstrate its interdisciplinary potential in addressing challenges in medical image analysis, promising advancements in medical imaging and cancer diagnosis.
Authors: Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang
The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with parallel Feed Forward Network (FFN) experts leads to significant parameter and computational overheads that hinder its efficient deployment. In addition, the naive MoE linear router is suboptimal in assigning task-specific features to multiple experts which limits its further scalability. In this work, we propose an efficient MoE architecture with weight sharing across the experts. Inspired by the idea of linear feature modulation (FM), our architecture implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. The proposed Feature Modulated Expert (FME) serves as a building block for the novel Mixture-of-Feature-Modulation-Experts (MoFME) architecture, which can scale up the number of experts with low overhead. We further propose an Uncertainty-aware Router (UaR) to assign task-specific features to different FM modules with well-calibrated weights. This enables MoFME to effectively learn diverse expert functions for multiple tasks. The conducted experiments on the multi-deweather task show that our MoFME outperforms the baselines in the image restoration quality by 0.1-0.2 dB and achieves SOTA-compatible performance while saving more than 72% of parameters and 39% inference time over the conventional MoE counterpart. Experiments on the downstream segmentation and classification tasks further demonstrate the generalizability of MoFME to real open-world applications.
Authors: Moritz Piening, Fabian Altekrüger, Johannes Hertrich, Paul Hagemann, Andrea Walther, Gabriele Steidl
The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences. Recent advances were made by using methods from machine learning, in particular deep neural networks. Most of these methods require a huge amount of (paired) data and computer capacity to train the networks, which often may not be available. Our paper addresses the issue of learning from small data sets by taking patches of very few images into account. We focus on the combination of model-based and data-driven methods by approximating just the image prior, also known as regularizer in the variational model. We review two methodically different approaches, namely optimizing the maximum log-likelihood of the patch distribution, and penalizing Wasserstein-like discrepancies of whole empirical patch distributions. From the point of view of Bayesian inverse problems, we show how we can achieve uncertainty quantification by approximating the posterior using Langevin Monte Carlo methods. We demonstrate the power of the methods in computed tomography, image super-resolution, and inpainting. Indeed, the approach provides also high-quality results in zero-shot super-resolution, where only a low-resolution image is available. The paper is accompanied by a GitHub repository containing implementations of all methods as well as data examples so that the reader can get their own insight into the performance.
Authors: Álvaro G. Becker, Marcelo P. Cenci, Thiago L. T. da Silveira, Hugo M. Veit
The recycling of waste electrical and electronic equipment is an essential tool in allowing for a circular economy, presenting the potential for significant environmental and economic gain. However, traditional material separation techniques, based on physical and chemical processes, require substantial investment and do not apply to all cases. In this work, we investigate using an image classification neural network as a potential means to control an automated material separation process in treating smartphone waste, acting as a more efficient, less costly, and more widely applicable alternative to existing tools. We produced a dataset with 1,127 images of pyrolyzed smartphone components, which was then used to train and assess a VGG-16 image classification model. The model achieved 83.33% accuracy, lending credence to the viability of using such a neural network in material separation.
Authors: Sai Shubodh Puligilla, Mohammad Omama, Husain Zaidi, Udit Singh Parihar, Madhava Krishna
Global visual localization in LiDAR-maps, crucial for autonomous driving applications, remains largely unexplored due to the challenging issue of bridging the cross-modal heterogeneity gap. Popular multi-modal learning approach Contrastive Language-Image Pre-Training (CLIP) has popularized contrastive symmetric loss using batch construction technique by applying it to multi-modal domains of text and image. We apply this approach to the domains of 2D image and 3D LiDAR points on the task of cross-modal localization. Our method is explained as follows: A batch of N (image, LiDAR) pairs is constructed so as to predict what is the right match between N X N possible pairings across the batch by jointly training an image encoder and LiDAR encoder to learn a multi-modal embedding space. In this way, the cosine similarity between N positive pairings is maximized, whereas that between the remaining negative pairings is minimized. Finally, over the obtained similarity scores, a symmetric cross-entropy loss is optimized. To the best of our knowledge, this is the first work to apply batched loss approach to a cross-modal setting of image & LiDAR data and also to show Zero-shot transfer in a visual localization setting. We conduct extensive analyses on standard autonomous driving datasets such as KITTI and KITTI-360 datasets. Our method outperforms state-of-the-art recall@1 accuracy on the KITTI-360 dataset by 22.4%, using only perspective images, in contrast to the state-of-the-art approach, which utilizes the more informative fisheye images. Additionally, this superior performance is achieved without resorting to complex architectures. Moreover, we demonstrate the zero-shot capabilities of our model and we beat SOTA by 8% without even training on it. Furthermore, we establish the first benchmark for cross-modal localization on the KITTI dataset.
Authors: Huan Liu, Zichang Tan, Chuangchuang Tan, Yunchao Wei, Yao Zhao, Jingdong Wang
In this paper, we study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods, e.g., GANs and diffusion models. Cutting-edge solutions start to explore the benefits of pre-trained models, and mainly follow the fixed paradigm of solely training an attached classifier, e.g., combining frozen CLIP-ViT with a learnable linear layer in UniFD. However, our analysis shows that such a fixed paradigm is prone to yield detectors with insufficient learning regarding forgery representations. We attribute the key challenge to the lack of forgery adaptation, and present a novel forgery-aware adaptive transformer approach, namely FatFormer. Based on the pre-trained vision-language spaces of CLIP, FatFormer introduces two core designs for the adaption to build generalized forgery representations. First, motivated by the fact that both image and frequency analysis are essential for synthetic image detection, we develop a forgery-aware adapter to adapt image features to discern and integrate local forgery traces within image and frequency domains. Second, we find that considering the contrastive objectives between adapted image features and text prompt embeddings, a previously overlooked aspect, results in a nontrivial generalization improvement. Accordingly, we introduce language-guided alignment to supervise the forgery adaptation with image and text prompts in FatFormer. Experiments show that, by coupling these two designs, our approach tuned on 4-class ProGAN data attains a remarkable detection performance, achieving an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
Authors: Xun Guo, Mingwu Zheng, Liang Hou, Yuan Gao, Yufan Deng, Chongyang Ma, Weiming Hu, Zhengjun Zha, Haibin Huang, Pengfei Wan, Di Zhang
In the rapidly evolving domain of digital content generation, the focus has shifted from text-to-image (T2I) models to more advanced video diffusion models, notably text-to-video (T2V) and image-to-video (I2V). This paper addresses the intricate challenge posed by I2V: converting static images into dynamic, lifelike video sequences while preserving the original image fidelity. Traditional methods typically involve integrating entire images into diffusion processes or using pretrained encoders for cross attention. However, these approaches often necessitate altering the fundamental weights of T2I models, thereby restricting their reusability. We introduce a novel solution, namely I2V-Adapter, designed to overcome such limitations. Our approach preserves the structural integrity of T2I models and their inherent motion modules. The I2V-Adapter operates by processing noised video frames in parallel with the input image, utilizing a lightweight adapter module. This module acts as a bridge, efficiently linking the input to the model's self-attention mechanism, thus maintaining spatial details without requiring structural changes to the T2I model. Moreover, I2V-Adapter requires only a fraction of the parameters of conventional models and ensures compatibility with existing community-driven T2I models and controlling tools. Our experimental results demonstrate I2V-Adapter's capability to produce high-quality video outputs. This performance, coupled with its versatility and reduced need for trainable parameters, represents a substantial advancement in the field of AI-driven video generation, particularly for creative applications.
Authors: Cam Le, Lam Pham, Jasmin Lampert, Matthias Schlögl, Alexander Schindler
Knowledge about historic landslide event occurrence is important for supporting disaster risk reduction strategies. Building upon findings from 2022 Landslide4Sense Competition, we propose a deep neural network based system for landslide detection and segmentation from multisource remote sensing image input. We use a U-Net trained with Cross Entropy loss as baseline model. We then improve the U-Net baseline model by leveraging a wide range of deep learning techniques. In particular, we conduct feature engineering by generating new band data from the original bands, which helps to enhance the quality of remote sensing image input. Regarding the network architecture, we replace traditional convolutional layers in the U-Net baseline by a residual-convolutional layer. We also propose an attention layer which leverages the multi-head attention scheme. Additionally, we generate multiple output masks with three different resolutions, which creates an ensemble of three outputs in the inference process to enhance the performance. Finally, we propose a combined loss function which leverages Focal loss and IoU loss to train the network. Our experiments on the development set of the Landslide4Sense challenge achieve an F1 score and an mIoU score of 84.07 and 76.07, respectively. Our best model setup outperforms the challenge baseline and the proposed U-Net baseline, improving the F1 score/mIoU score by 6.8/7.4 and 10.5/8.8, respectively.
Authors: Siddhartha Datta, Alexander Ku, Deepak Ramachandran, Peter Anderson
Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate high-quality, diverse images with less effort. The Prompt Expansion model takes a text query as input and outputs a set of expanded text prompts that are optimized such that when passed to a text-to-image model, generates a wider variety of appealing images. We conduct a human evaluation study that shows that images generated through Prompt Expansion are more aesthetically pleasing and diverse than those generated by baseline methods. Overall, this paper presents a novel and effective approach to improving the text-to-image generation experience.
Authors: Thiago T. Santos, Kleber X. S. de Souza, João Camargo Neto, Luciano V. Koenigkan, Alécio S. Moreira, Sônia Ternes
Traditionally, sweet orange crop forecasting has involved manually counting fruits from numerous trees, which is a labor-intensive process. Automatic systems for fruit counting, based on proximal imaging, computer vision, and machine learning, have been considered a promising alternative or complement to manual counting. These systems require data association components that prevent multiple counting of the same fruit observed in different images. However, there is a lack of work evaluating the accuracy of multiple fruit counting, especially considering (i) occluded and re-entering green fruits on leafy trees, and (ii) counting ground-truth data measured in the crop field. We propose a non-invasive alternative that utilizes fruit counting from videos, implemented as a pipeline. Firstly, we employ CNNs for the detection of visible fruits. Inter-frame association techniques are then applied to track the fruits across frames. To handle occluded and re-appeared fruit, we introduce a relocalization component that employs 3-D estimation of fruit locations. Finally, a neural network regressor is utilized to estimate the total number of fruit, integrating image-based fruit counting with other tree data such as crop variety and tree size. The results demonstrate that the performance of our approach is closely tied to the quality of the field-collected videos. By ensuring that at least 30% of the fruit is accurately detected, tracked, and counted, our yield regressor achieves an impressive coefficient of determination of 0.85. To the best of our knowledge, this study represents one of the few endeavors in fruit estimation that incorporates manual fruit counting as a reference point for evaluation. We also introduce annotated datasets for multiple orange tracking (MOrangeT) and detection (OranDet), publicly available to foster the development of novel methods for image-based fruit counting.
Authors: Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite existing knowledge when learning a new task. Existing continual learning methods alleviate this problem through regularisation, parameter isolation, or rehearsal, and are typically evaluated on benchmarks consisting of a handful of tasks. We propose a novel conceptual approach to continual classification that aims to disentangle class-specific information that needs to be memorised from the class-agnostic knowledge that encapsulates generalization. We store the former in a buffer that can be easily pruned or updated when new categories arrive, while the latter is represented with a neural network that generalizes across tasks. We show that the class-agnostic network does not suffer from catastrophic forgetting and by leveraging it to perform classification, we improve accuracy on past tasks over time. In addition, our approach supports open-set classification and one-shot generalization. To test our conceptual framework, we introduce Infinite dSprites, a tool for creating continual classification and disentanglement benchmarks of arbitrary length with full control over generative factors. We show that over a sufficiently long time horizon all major types of continual learning methods break down, while our approach enables continual learning over hundreds of tasks with explicit control over memorization and forgetting.
Authors: Enes Duran, Muhammed Kocabas, Vasileios Choutas, Zicong Fan, Michael J. Black
Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing methods rely on single-image inputs, videos have useful cues to address aforementioned issues. However, existing video-based 3D hand datasets are insufficient for training feedforward models to generalize to in-the-wild scenarios. On the other hand, we have access to large human motion capture datasets which also include hand motions, e.g. AMASS. Therefore, we develop a generative motion prior specific for hands, trained on the AMASS dataset which features diverse and high-quality hand motions. This motion prior is then employed for video-based 3D hand motion estimation following a latent optimization approach. Our integration of a robust motion prior significantly enhances performance, especially in occluded scenarios. It produces stable, temporally consistent results that surpass conventional single-frame methods. We demonstrate our method's efficacy via qualitative and quantitative evaluations on the HO3D and DexYCB datasets, with special emphasis on an occlusion-focused subset of HO3D. Code is available at https://hmp.is.tue.mpg.de
Authors: Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng, Ming-Ching Chang, Li Xin
Traditional crowd counting networks suffer from information loss when feature maps are downsized through pooling layers, leading to inaccuracies in counting crowds at a distance. Existing methods often assume correct annotations during training, disregarding the impact of noisy annotations, especially in crowded scenes. Furthermore, the use of a fixed Gaussian kernel fails to account for the varying pixel distribution with respect to the camera distance. To overcome these challenges, we propose a Scale-Aware Crowd Counting Network (SACC-Net) that introduces a ``scale-aware'' architecture with error-correcting capabilities of noisy annotations. For the first time, we {\bf simultaneously} model labeling errors (mean) and scale variations (variance) by spatially-varying Gaussian distributions to produce fine-grained heat maps for crowd counting. Furthermore, the proposed adaptive Gaussian kernel variance enables the model to learn dynamically with a low-rank approximation, leading to improved convergence efficiency with comparable accuracy. The performance of SACC-Net is extensively evaluated on four public datasets: UCF-QNRF, UCF CC 50, NWPU, and ShanghaiTech A-B. Experimental results demonstrate that SACC-Net outperforms all state-of-the-art methods, validating its effectiveness in achieving superior crowd counting accuracy.
Authors: Jun Bai, Annie Jin, Madison Adams, Clifford Yang, Sheida Nabavi
Breast cancer continues to be a significant cause of mortality among women globally. Timely identification and precise diagnosis of breast abnormalities are critical for enhancing patient prognosis. In this study, we focus on improving the early detection and accurate diagnosis of breast abnormalities, which is crucial for improving patient outcomes and reducing the mortality rate of breast cancer. To address the limitations of traditional screening methods, a novel unsupervised feature correlation network was developed to predict maps indicating breast abnormal variations using longitudinal 2D mammograms. The proposed model utilizes the reconstruction process of current year and prior year mammograms to extract tissue from different areas and analyze the differences between them to identify abnormal variations that may indicate the presence of cancer. The model is equipped with a feature correlation module, an attention suppression gate, and a breast abnormality detection module that work together to improve the accuracy of the prediction. The proposed model not only provides breast abnormal variation maps, but also distinguishes between normal and cancer mammograms, making it more advanced compared to the state-of the-art baseline models. The results of the study show that the proposed model outperforms the baseline models in terms of Accuracy, Sensitivity, Specificity, Dice score, and cancer detection rate.
Authors: Rashik Shadman, M.G. Sarwar Murshed, Edward Verenich, Alvaro Velasquez, Faraz Hussain
The use of transfer learning with deep neural networks has increasingly become widespread for deploying well-tested computer vision systems to newer domains, especially those with limited datasets. We describe a transfer learning use case for a domain with a data-starved regime, having fewer than 100 labeled target samples. We evaluate the effectiveness of convolutional feature extraction and fine-tuning of overparameterized models with respect to the size of target training data, as well as their generalization performance on data with covariate shift, or out-of-distribution (OOD) data. Our experiments demonstrate that both overparameterization and feature reuse contribute to the successful application of transfer learning in training image classifiers in data-starved regimes. We provide visual explanations to support our findings and conclude that transfer learning enhances the performance of CNN architectures in data-starved regimes.
Authors: Yue Ruan, Han-Hung Lee, Yiming Zhang, Ke Zhang, Angel X. Chang
Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data. Recent work on contrastive losses for learning joint embeddings over multimodal data has been successful at tasks such as retrieval and classification. Thus far, work on joint representation learning for 3D shapes and text has focused on improving embeddings through modeling of complex attention between representations, or multi-task learning. We propose a trimodal learning scheme over text, multi-view images and 3D shape voxels, and show that with large batch contrastive learning we achieve good performance on text-to-shape retrieval without complex attention mechanisms or losses. Our experiments serve as a foundation for follow-up work on building trimodal embeddings for text-image-shape.
Authors: Hongshan Liu, Colin Aderon, Noah Wagon, Abdul Latif Bamba, Xueshen Li, Huapu Liu, Steven MacCall, Yu Gan
American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges such as crowded settings, distorted objects, and imbalanced data for identifying players, especially jersey numbers. In this work, we propose a deep learning-based player tracking system to automatically track players and index their participation per play in American football games. It is a two-stage network design to highlight areas of interest and identify jersey number information with high accuracy. First, we utilize an object detection network, a detection transformer, to tackle the player detection problem in a crowded context. Second, we identify players using jersey number recognition with a secondary convolutional neural network, then synchronize it with a game clock subsystem. Finally, the system outputs a complete log in a database for play indexing. We demonstrate the effectiveness and reliability of player tracking system by analyzing the qualitative and quantitative results on football videos. The proposed system shows great potential for implementation in and analysis of football broadcast video.
Authors: Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao, Chongyang Ma, Siyuan Pan, Pengfei Wan, Zhongyuan Wang, Huawei Shen, Xueqi Cheng
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic $-$ harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs.
Authors: Soumick Chatterjee, Hadya Yassin, Florian Dubost, Andreas Nürnberger, Oliver Speck
Deep learning models have shown their potential for several applications. However, most of the models are opaque and difficult to trust due to their complex reasoning - commonly known as the black-box problem. Some fields, such as medicine, require a high degree of transparency to accept and adopt such technologies. Consequently, creating explainable/interpretable models or applying post-hoc methods on classifiers to build trust in deep learning models are required. Moreover, deep learning methods can be used for segmentation tasks, which typically require hard-to-obtain, time-consuming manually-annotated segmentation labels for training. This paper introduces three inherently-explainable classifiers to tackle both of these problems as one. The localisation heatmaps provided by the networks -- representing the models' focus areas and being used in classification decision-making -- can be directly interpreted, without requiring any post-hoc methods to derive information for model explanation. The models are trained by using the input image and only the classification labels as ground-truth in a supervised fashion - without using any information about the location of the region of interest (i.e. the segmentation labels), making the segmentation training of the models weakly-supervised through classification labels. The final segmentation is obtained by thresholding these heatmaps. The models were employed for the task of multi-class brain tumour classification using two different datasets, resulting in the best F1-score of 0.93 for the supervised classification task while securing a median Dice score of 0.67$\pm$0.08 for the weakly-supervised segmentation task. Furthermore, the obtained accuracy on a subset of tumour-only images outperformed the state-of-the-art glioma tumour grading binary classifiers with the best model achieving 98.7\% accuracy.
Authors: Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, Junyeong Kim, Chang D. Yoo
This paper considers a network referred to as SoftGroup for accurate and scalable 3D instance segmentation. Existing state-of-the-art methods produce hard semantic predictions followed by grouping instance segmentation results. Unfortunately, errors stemming from hard decisions propagate into the grouping, resulting in poor overlap between predicted instances and ground truth and substantial false positives. To address the abovementioned problems, SoftGroup allows each point to be associated with multiple classes to mitigate the uncertainty stemming from semantic prediction. It also suppresses false positive instances by learning to categorize them as background. Regarding scalability, the existing fast methods require computational time on the order of tens of seconds on large-scale scenes, which is unsatisfactory and far from applicable for real-time. Our finding is that the $k$-Nearest Neighbor ($k$-NN) module, which serves as the prerequisite of grouping, introduces a computational bottleneck. SoftGroup is extended to resolve this computational bottleneck, referred to as SoftGroup++. The proposed SoftGroup++ reduces time complexity with octree $k$-NN and reduces search space with class-aware pyramid scaling and late devoxelization. Experimental results on various indoor and outdoor datasets demonstrate the efficacy and generality of the proposed SoftGroup and SoftGroup++. Their performances surpass the best-performing baseline by a large margin (6\% $\sim$ 16\%) in terms of AP$_{50}$. On datasets with large-scale scenes, SoftGroup++ achieves a 6$\times$ speed boost on average compared to SoftGroup. Furthermore, SoftGroup can be extended to perform object detection and panoptic segmentation with nontrivial improvements over existing methods. The source code and trained models are available at \url{https://github.com/thangvubk/SoftGroup}.
Authors: Jinpeng Hu, Zhihong Chen, Yang Liu, Xiang Wan, Tsung-Hui Chang
The impression is crucial for the referring physicians to grasp key information since it is concluded from the findings and reasoning of radiologists. To alleviate the workload of radiologists and reduce repetitive human labor in impression writing, many researchers have focused on automatic impression generation. However, recent works on this task mainly summarize the corresponding findings and pay less attention to the radiology images. In clinical, radiographs can provide more detailed valuable observations to enhance radiologists' impression writing, especially for complicated cases. Besides, each sentence in findings usually focuses on single anatomy, so they only need to be matched to corresponding anatomical regions instead of the whole image, which is beneficial for textual and visual features alignment. Therefore, we propose a novel anatomy-enhanced multimodal model to promote impression generation. In detail, we first construct a set of rules to extract anatomies and put these prompts into each sentence to highlight anatomy characteristics. Then, two separate encoders are applied to extract features from the radiograph and findings. Afterward, we utilize a contrastive learning module to align these two representations at the overall level and use a co-attention to fuse them at the sentence level with the help of anatomy-enhanced sentence representation. Finally, the decoder takes the fused information as the input to generate impressions. The experimental results on two benchmark datasets confirm the effectiveness of the proposed method, which achieves state-of-the-art results.
Authors: Erim Yanik, Steven Schwaitzberg, Gene Yang, Xavier Intes, Suvranu De
Deep Learning (DL) has achieved automatic and objective assessment of surgical skills. However, the applicability of DL models is often hampered by their substantial data requirements and confinement to specific training domains. This prevents them from transitioning to new tasks with scarce data. Therefore, domain adaptation emerges as a critical element for the practical implementation of DL in real-world scenarios. Herein, we introduce A-VBANet, a novel meta-learning model capable of delivering domain-agnostic surgical skill classification via one-shot learning. A-VBANet has been rigorously developed and tested on five diverse laparoscopic and robotic surgical simulators. Furthermore, we extend its validation to operating room (OR) videos of laparoscopic cholecystectomy. Our model successfully adapts with accuracies up to 99.5% in one-shot and 99.9% in few-shot settings for simulated tasks and 89.7% for laparoscopic cholecystectomy. This research marks the first instance of a domain-agnostic methodology for surgical skill assessment, paving the way for more precise and accessible training evaluation across diverse high-stakes environments such as real-life surgery where data is scarce.
Authors: Bo-Han Kung, Shang-Tse Chen
Randomized smoothing is currently the state-of-the-art method that provides certified robustness for deep neural networks. However, due to its excessively conservative nature, this method of incomplete verification often cannot achieve an adequate certified radius on real-world datasets. One way to obtain a larger certified radius is to use an input-specific algorithm instead of using a fixed Gaussian filter for all data points. Several methods based on this idea have been proposed, but they either suffer from high computational costs or gain marginal improvement in certified radius. In this work, we show that by exploiting the quasiconvex problem structure, we can find the optimal certified radii for most data points with slight computational overhead. This observation leads to an efficient and effective input-specific randomized smoothing algorithm. We conduct extensive experiments and empirical analysis on CIFAR-10 and ImageNet. The results show that the proposed method significantly enhances the certified radii with low computational overhead.
Authors: Jacopo Teneggi, Matthew Tivnan, J. Webster Stayman, Jeremias Sulam
Score-based generative modeling, informally referred to as diffusion models, continue to grow in popularity across several important domains and tasks. While they provide high-quality and diverse samples from empirical distributions, important questions remain on the reliability and trustworthiness of these sampling procedures for their responsible use in critical scenarios. Conformal prediction is a modern tool to construct finite-sample, distribution-free uncertainty guarantees for any black-box predictor. In this work, we focus on image-to-image regression tasks and we present a generalization of the Risk-Controlling Prediction Sets (RCPS) procedure, that we term $K$-RCPS, which allows to $(i)$ provide entrywise calibrated intervals for future samples of any diffusion model, and $(ii)$ control a certain notion of risk with respect to a ground truth image with minimal mean interval length. Differently from existing conformal risk control procedures, ours relies on a novel convex optimization approach that allows for multidimensional risk control while provably minimizing the mean interval length. We illustrate our approach on two real-world image denoising problems: on natural images of faces as well as on computed tomography (CT) scans of the abdomen, demonstrating state of the art performance.
Authors: Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng
Score-based generative models (SGMs) have recently emerged as a promising class of generative models. However, a fundamental limitation is that their sampling process is slow due to a need for many (\eg, $2000$) iterations of sequential computations. An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We assault this problem to the ill-conditioned issues of the Langevin dynamics and reverse diffusion in the sampling process. Under this insight, we propose a model-agnostic {\bf\em preconditioned diffusion sampling} (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. PDS alters the sampling process of a vanilla SGM at marginal extra computation cost, and without model retraining. Theoretically, we prove that PDS preserves the output distribution of the SGM, no risk of inducing systematical bias to the original sampling process. We further theoretically reveal a relation between the parameter of PDS and the sampling iterations,easing the parameter estimation under varying sampling iterations. Extensive experiments on various image datasets with a variety of resolutions and diversity validate that our PDS consistently accelerates off-the-shelf SGMs whilst maintaining the synthesis quality. In particular, PDS can accelerate by up to $29\times$ on more challenging high resolution (1024$\times$1024) image generation. Compared with the latest generative models (\eg, CLD-SGM, DDIM, and Analytic-DDIM), PDS can achieve the best sampling quality on CIFAR-10 at a FID score of 1.99. Our code is made publicly available to foster any further research https://github.com/fudan-zvg/PDS.
Authors: Chihcheng Hsieh, Isabel Blanco Nobre, Sandra Costa Sousa, Chun Ouyang, Margot Brereton, Jacinto C. Nascimento, Joaquim Jorge, Catarina Moreira
This study investigates the effects of including patients' clinical information on the performance of deep learning (DL) classifiers for disease location in chest X-ray images. Although current classifiers achieve high performance using chest X-ray images alone, our interviews with radiologists indicate that clinical data is highly informative and essential for interpreting images and making proper diagnoses.
In this work, we propose a novel architecture consisting of two fusion methods that enable the model to simultaneously process patients' clinical data (structured data) and chest X-rays (image data). Since these data modalities are in different dimensional spaces, we propose a spatial arrangement strategy, spatialization, to facilitate the multimodal learning process in a Mask R-CNN model. We performed an extensive experimental evaluation using MIMIC-Eye, a dataset comprising modalities: MIMIC-CXR (chest X-ray images), MIMIC IV-ED (patients' clinical data), and REFLACX (annotations of disease locations in chest X-rays).
Results show that incorporating patients' clinical data in a DL model together with the proposed fusion methods improves the disease localization in chest X-rays by 12\% in terms of Average Precision compared to a standard Mask R-CNN using only chest X-rays. Further ablation studies also emphasize the importance of multimodal DL architectures and the incorporation of patients' clinical data in disease localization. The architecture proposed in this work is publicly available to promote the scientific reproducibility of our study (https://github.com/ChihchengHsieh/multimodal-abnormalities-detection)
Authors: Yuqin Cao, Xiongkuo Min, Wei Sun, Xiaoping Zhang, Guangtao Zhai
With the explosive increase of User Generated Content (UGC), UGC video quality assessment (VQA) becomes more and more important for improving users' Quality of Experience (QoE). However, most existing UGC VQA studies only focus on the visual distortions of videos, ignoring that the user's QoE also depends on the accompanying audio signals. In this paper, we conduct the first study to address the problem of UGC audio and video quality assessment (AVQA). Specifically, we construct the first UGC AVQA database named the SJTU-UAV database, which includes 520 in-the-wild UGC audio and video (A/V) sequences, and conduct a user study to obtain the mean opinion scores of the A/V sequences. The content of the SJTU-UAV database is then analyzed from both the audio and video aspects to show the database characteristics. We also design a family of AVQA models, which fuse the popular VQA methods and audio features via support vector regressor (SVR). We validate the effectiveness of the proposed models on the three databases. The experimental results show that with the help of audio signals, the VQA models can evaluate the perceptual quality more accurately. The database will be released to facilitate further research.
Authors: Jianping Jiang, Jiahe Li, Baowen Zhang, Xiaoming Deng, Boxin Shi
Event camera shows great potential in 3D hand pose estimation, especially addressing the challenges of fast motion and high dynamic range in a low-power way. However, due to the asynchronous differential imaging mechanism, it is challenging to design event representation to encode hand motion information especially when the hands are not moving (causing motion ambiguity), and it is infeasible to fully annotate the temporally dense event stream. In this paper, we propose EvHandPose with novel hand flow representations in Event-to-Pose module for accurate hand pose estimation and alleviating the motion ambiguity issue. To solve the problem under sparse annotation, we design contrast maximization and hand-edge constraints in Pose-to-IWE (Image with Warped Events) module and formulate EvHandPose in a weakly-supervision framework. We further build EvRealHands, the first large-scale real-world event-based hand pose dataset on several challenging scenes to bridge the real-synthetic domain gap. Experiments on EvRealHands demonstrate that EvHandPose outperforms previous event-based methods under all evaluation scenes, achieves accurate and stable hand pose estimation with high temporal resolution in fast motion and strong light scenes compared with RGB-based methods, generalizes well to outdoor scenes and another type of event camera, and shows the potential for the hand gesture recognition task.
Authors: Sihwa Park, Seongjun Kim, Doeyoung Kwon, Yohan Jang, In-Seok Song, Seungjun Baek
Panoramic radiography (Panoramic X-ray, PX) is a widely used imaging modality for dental examination. However, PX only provides a flattened 2D image, lacking in a 3D view of the oral structure. In this paper, we propose NeBLa (Neural Beer-Lambert) to estimate 3D oral structures from real-world PX. NeBLa tackles full 3D reconstruction for varying subjects (patients) where each reconstruction is based only on a single panoramic image. We create an intermediate representation called simulated PX (SimPX) from 3D Cone-beam computed tomography (CBCT) data based on the Beer-Lambert law of X-ray rendering and rotational principles of PX imaging. SimPX aims at not only truthfully simulating PX, but also facilitates the reverting process back to 3D data. We propose a novel neural model based on ray tracing which exploits both global and local input features to convert SimPX to 3D output. At inference, a real PX image is translated to a SimPX-style image with semantic regularization, and the translated image is processed by generation module to produce high-quality outputs. Experiments show that NeBLa outperforms prior state-of-the-art in reconstruction tasks both quantitatively and qualitatively. Unlike prior methods, NeBLa does not require any prior information such as the shape of dental arches, nor the matched PX-CBCT dataset for training, which is difficult to obtain in clinical practice. Our code is available at https://github.com/sihwa-park/nebla.
Authors: Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, Yuxiao Dong
We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively encode human preferences. Its training is based on our systematic annotation pipeline including rating and ranking, which collects 137k expert comparisons to date. In human evaluation, ImageReward outperforms existing scoring models and metrics, making it a promising automatic metric for evaluating text-to-image synthesis. On top of it, we propose Reward Feedback Learning (ReFL), a direct tuning algorithm to optimize diffusion models against a scorer. Both automatic and human evaluation support ReFL's advantages over compared methods. All code and datasets are provided at \url{https://github.com/THUDM/ImageReward}.
Authors: Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and fine-tuning on encoded image sequences, i.e., videos. Similarly, we temporally align diffusion model upsamplers, turning them into temporally consistent video super resolution models. We focus on two relevant real-world applications: Simulation of in-the-wild driving data and creative content creation with text-to-video modeling. In particular, we validate our Video LDM on real driving videos of resolution 512 x 1024, achieving state-of-the-art performance. Furthermore, our approach can easily leverage off-the-shelf pre-trained image LDMs, as we only need to train a temporal alignment model in that case. Doing so, we turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048. We show that the temporal layers trained in this way generalize to different fine-tuned text-to-image LDMs. Utilizing this property, we show the first results for personalized text-to-video generation, opening exciting directions for future content creation. Project page: https://research.nvidia.com/labs/toronto-ai/VideoLDM/
Authors: Dvir Samuel, Rami Ben-Ari, Simon Raviv, Nir Darshan, Gal Chechik
Text-to-image diffusion models can synthesize high-quality images, but they have various limitations. Here we highlight a common failure mode of these models, namely, generating uncommon concepts and structured concepts like hand palms. We show that their limitation is partly due to the long-tail nature of their training data: web-crawled data sets are strongly unbalanced, causing models to under-represent concepts from the tail of the distribution. We characterize the effect of unbalanced training data on text-to-image models and offer a remedy. We show that rare concepts can be correctly generated by carefully selecting suitable generation seeds in the noise space, using a small reference set of images, a technique that we call SeedSelect. SeedSelect does not require retraining or finetuning the diffusion model. We assess the faithfulness, quality and diversity of SeedSelect in creating rare objects and generating complex formations like hand images, and find it consistently achieves superior performance. We further show the advantage of SeedSelect in semantic data augmentation. Generating semantically appropriate images can successfully improve performance in few-shot recognition benchmarks, for classes from the head and from the tail of the training data of diffusion models
Authors: Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences - locations in multiple images that have the same semantic meaning. Specifically, given an image, we optimize the prompt embeddings of these models for maximum attention on the regions of interest. These optimized embeddings capture semantic information about the location, which can then be transferred to another image. By doing so we obtain results on par with the strongly supervised state of the art on the PF-Willow dataset and significantly outperform (20.9% relative for the SPair-71k dataset) any existing weakly or unsupervised method on PF-Willow, CUB-200 and SPair-71k datasets.
Authors: Jingyuan Sun, Mingxiao Li, Zijiao Chen, Yunhao Zhang, Shaonan Wang, Marie-Francine Moens
Decoding visual stimuli from neural responses recorded by functional Magnetic Resonance Imaging (fMRI) presents an intriguing intersection between cognitive neuroscience and machine learning, promising advancements in understanding human visual perception and building non-invasive brain-machine interfaces. However, the task is challenging due to the noisy nature of fMRI signals and the intricate pattern of brain visual representations. To mitigate these challenges, we introduce a two-phase fMRI representation learning framework. The first phase pre-trains an fMRI feature learner with a proposed Double-contrastive Mask Auto-encoder to learn denoised representations. The second phase tunes the feature learner to attend to neural activation patterns most informative for visual reconstruction with guidance from an image auto-encoder. The optimized fMRI feature learner then conditions a latent diffusion model to reconstruct image stimuli from brain activities. Experimental results demonstrate our model's superiority in generating high-resolution and semantically accurate images, substantially exceeding previous state-of-the-art methods by 39.34% in the 50-way-top-1 semantic classification accuracy. Our research invites further exploration of the decoding task's potential and contributes to the development of non-invasive brain-machine interfaces.
Authors: Xiulong Liu, Sudipta Paul, Moitreya Chatterjee, Anoop Cherian
Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our CAVEN agent can engage in fully-bidirectional natural language conversations by producing relevant questions and interpret free-form, potentially noisy responses from the oracle based on the audio-visual context. To enable such a capability, CAVEN is equipped with: (i) a trajectory forecasting network that is grounded in audio-visual cues to produce a potential trajectory to the estimated goal, and (ii) a natural language based question generation and reasoning network to pose an interactive question to the oracle or interpret the oracle's response to produce navigation instructions. To train the interactive modules, we present a large scale dataset: AVN-Instruct, based on the Landmark-RxR dataset. To substantiate the usefulness of conversations, we present experiments on the benchmark audio-goal task using the SoundSpaces simulator under various noisy settings. Our results reveal that our fully-conversational approach leads to nearly an order-of-magnitude improvement in success rate, especially in localizing new sound sources and against methods that only use uni-directional interaction.
Authors: Kai Chen, Enze Xie, Zhe Chen, Yibo Wang, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung
Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object detection data remains an underexplored area, where not only image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential. Previous studies have utilized either copy-paste synthesis or layout-to-image (L2I) generation with specifically designed modules to encode the semantic layouts. In this paper, we propose the GeoDiffusion, a simple framework that can flexibly translate various geometric conditions into text prompts and empower pre-trained text-to-image (T2I) diffusion models for high-quality detection data generation. Unlike previous L2I methods, our GeoDiffusion is able to encode not only the bounding boxes but also extra geometric conditions such as camera views in self-driving scenes. Extensive experiments demonstrate GeoDiffusion outperforms previous L2I methods while maintaining 4x training time faster. To the best of our knowledge, this is the first work to adopt diffusion models for layout-to-image generation with geometric conditions and demonstrate that L2I-generated images can be beneficial for improving the performance of object detectors.
Authors: Yunsung Lee, Jin-Young Kim, Hyojun Go, Myeongho Jeong, Shinhyeok Oh, Seungtaek Choi
In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME). We identify the need for tailored operations at different time-steps in diffusion processes and leverage this insight to create compact yet high-performing models. MEME assigns distinct architectures to different time-step intervals, balancing convolution and self-attention operations based on observed frequency characteristics. We also introduce a soft interval assignment strategy for comprehensive training. Empirically, MEME operates 3.3 times faster than baselines while improving image generation quality (FID scores) by 0.62 (FFHQ) and 0.37 (CelebA). Though we validate the effectiveness of assigning more optimal architecture per time-step, where efficient models outperform the larger models, we argue that MEME opens a new design choice for diffusion models that can be easily applied in other scenarios, such as large multi-expert models.
Authors: Qiujie Dong, Xiaoran Gong, Rui Xu, Zixiong Wang, Shuangmin Chen, Shiqing Xin, Changhe Tu, Wenping Wang
With the rapid development of geometric deep learning techniques, many mesh-based convolutional operators have been proposed to bridge irregular mesh structures and popular backbone networks. In this paper, we show that while convolutions are helpful, a simple architecture based exclusively on multi-layer perceptrons (MLPs) is competent enough to deal with mesh classification and semantic segmentation. Our new network architecture, named Mesh-MLP, takes mesh vertices equipped with the heat kernel signature (HKS) and dihedral angles as the input, replaces the convolution module of a ResNet with Multi-layer Perceptron (MLP), and utilizes layer normalization (LN) to perform the normalization of the layers. The all-MLP architecture operates in an end-to-end fashion and does not include a pooling module. Extensive experimental results on the mesh classification/segmentation tasks validate the effectiveness of the all-MLP architecture.
Authors: Zhongbin Fang, Xiangtai Li, Xia Li, Joachim M. Buhmann, Chen Change Loy, Mengyuan Liu
With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context learning is still largely unexplored in the 3D point cloud domain. Although masked modeling has been successfully applied for in-context learning in 2D vision, directly extending it to 3D point clouds remains a formidable challenge. In the case of point clouds, the tokens themselves are the point cloud positions (coordinates) that are masked during inference. Moreover, position embedding in previous works may inadvertently introduce information leakage. To address these challenges, we introduce a novel framework, named Point-In-Context, designed especially for in-context learning in 3D point clouds, where both inputs and outputs are modeled as coordinates for each task. Additionally, we propose the Joint Sampling module, carefully designed to work in tandem with the general point sampling operator, effectively resolving the aforementioned technical issues. We conduct extensive experiments to validate the versatility and adaptability of our proposed methods in handling a wide range of tasks.
Authors: Le Zhang, Rabiul Awal, Aishwarya Agrawal
Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation. However, the compositional reasoning abilities of existing VLMs remains subpar. The root of this limitation lies in the inadequate alignment between the images and captions in the pretraining datasets. Additionally, the current contrastive learning objective fails to focus on fine-grained grounding components like relations, actions, and attributes, resulting in "bag-of-words" representations. We introduce a simple and effective method to improve compositional reasoning in VLMs. Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. Our approach does not require specific annotations and does not incur extra parameters. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines across five vision-language compositional benchmarks. We open-source our code at https://github.com/lezhang7/Enhance-FineGrained.
Authors: Elysia Q. Smyers, Sydney M. Katz, Anthony L. Corso, Mykel J. Kochenderfer
Designing robust machine learning systems remains an open problem, and there is a need for benchmark problems that cover both environmental changes and evaluation on a downstream task. In this work, we introduce AVOIDDS, a realistic object detection benchmark for the vision-based aircraft detect-and-avoid problem. We provide a labeled dataset consisting of 72,000 photorealistic images of intruder aircraft with various lighting conditions, weather conditions, relative geometries, and geographic locations. We also provide an interface that evaluates trained models on slices of this dataset to identify changes in performance with respect to changing environmental conditions. Finally, we implement a fully-integrated, closed-loop simulator of the vision-based detect-and-avoid problem to evaluate trained models with respect to the downstream collision avoidance task. This benchmark will enable further research in the design of robust machine learning systems for use in safety-critical applications. The AVOIDDS dataset and code are publicly available at https://purl.stanford.edu/hj293cv5980 and https://github.com/sisl/VisionBasedAircraftDAA respectively.
Authors: Apratim Bhattacharyya, Sunny Panchal, Mingu Lee, Reza Pourreza, Pulkit Madan, Roland Memisevic
Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in which model predictions need to be grounded in fine-grained low-level details, such as object motions and object interactions. In this work, we propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, and tracking, to endow the model with the required low-level visual capabilities. We show that a two-stream video encoder with spatiotemporal attention is effective at capturing the required static and motion-based cues in the video. By leveraging the LM's ability to perform the low-level surrogate tasks, we can cast reasoning in videos as the three-step process of Look, Remember, Reason wherein visual information is extracted using low-level visual skills step-by-step and then integrated to arrive at a final answer. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, and Something-Else datasets. Our approach is trainable end-to-end and surpasses state-of-the-art task-specific methods across these tasks by a large margin.
Authors: Bo Zhao, Boya Wu, Muyang He, Tiejun Huang
Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive performance of visual understanding and reasoning, their limits are still largely under-explored due to the scarcity of high-quality instruction tuning data. To push the limits of multimodal capability, we Scale up Visual Instruction Tuning (SVIT) by constructing a dataset of 4.2 million visual instruction tuning data including 1.6M conversation question-answer (QA) pairs, 1.6M complex reasoning QA pairs, 1.0M referring QA pairs and 106K detailed image descriptions. Besides the volume, the proposed dataset is also featured by the high quality and rich diversity, which is generated by prompting GPT-4 with the abundant manual annotations of images. We also propose a new data recipe to select subset with better diversity and balance, which evokes model's superior capabilities. Extensive experiments verify that SVIT-v1.5, trained on the proposed dataset, outperforms state-of-the-art Multimodal Large Language Models on popular benchmarks. The data and code are publicly available at https://github.com/BAAI-DCAI/Visual-Instruction-Tuning.
Authors: Naoki Nishikawa, Yuichi Ike, Kenji Yamanishi
Machine learning for point clouds has been attracting much attention, with many applications in various fields, such as shape recognition and material science. For enhancing the accuracy of such machine learning methods, it is often effective to incorporate global topological features, which are typically extracted by persistent homology. In the calculation of persistent homology for a point cloud, we choose a filtration for the point cloud, an increasing sequence of spaces. Since the performance of machine learning methods combined with persistent homology is highly affected by the choice of a filtration, we need to tune it depending on data and tasks. In this paper, we propose a framework that learns a filtration adaptively with the use of neural networks. In order to make the resulting persistent homology isometry-invariant, we develop a neural network architecture with such invariance. Additionally, we show a theoretical result on a finite-dimensional approximation of filtration functions, which justifies the proposed network architecture. Experimental results demonstrated the efficacy of our framework in several classification tasks.
Authors: Zhihan Gao, Xingjian Shi, Boran Han, Hao Wang, Xiaoyong Jin, Danielle Maddix, Yi Zhu, Mu Li, Yuyang Wang
Earth system forecasting has traditionally relied on complex physical models that are computationally expensive and require significant domain expertise. In the past decade, the unprecedented increase in spatiotemporal Earth observation data has enabled data-driven forecasting models using deep learning techniques. These models have shown promise for diverse Earth system forecasting tasks but either struggle with handling uncertainty or neglect domain-specific prior knowledge, resulting in averaging possible futures to blurred forecasts or generating physically implausible predictions. To address these limitations, we propose a two-stage pipeline for probabilistic spatiotemporal forecasting: 1) We develop PreDiff, a conditional latent diffusion model capable of probabilistic forecasts. 2) We incorporate an explicit knowledge alignment mechanism to align forecasts with domain-specific physical constraints. This is achieved by estimating the deviation from imposed constraints at each denoising step and adjusting the transition distribution accordingly. We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset. Specifically, we impose the law of conservation of energy in N-body MNIST and anticipated precipitation intensity in SEVIR. Experiments demonstrate the effectiveness of PreDiff in handling uncertainty, incorporating domain-specific prior knowledge, and generating forecasts that exhibit high operational utility.
Authors: Yanda Li, Chi Zhang, Gang Yu, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and textual modalities effectively while comprehending human instructions. Current methodologies often rely on annotations derived from benchmark datasets to construct image-dialogue datasets for training purposes, akin to instruction tuning in LLMs. However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models. In an effort to mitigate these limitations, we propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models to yield a diverse and controllable dataset with varied image content. Additionally, datasets can be arbitrarily scaled. This not only provides greater flexibility compared to existing methodologies but also significantly enhances several model capabilities. Our research includes comprehensive experiments conducted on various datasets. The results emphasize substantial enhancements in more than ten commonly assessed capabilities. Additionally, our model achieves state-of-the-art results across multiple widely recognized multimodal benchmarks.
Authors: Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common objects due to extensive training datasets, they lack specific domain knowledge and have a weaker understanding of localized details within objects, which hinders their effectiveness in the Industrial Anomaly Detection (IAD) task. On the other hand, most existing IAD methods only provide anomaly scores and necessitate the manual setting of thresholds to distinguish between normal and abnormal samples, which restricts their practical implementation. In this paper, we explore the utilization of LVLM to address the IAD problem and propose AnomalyGPT, a novel IAD approach based on LVLM. We generate training data by simulating anomalous images and producing corresponding textual descriptions for each image. We also employ an image decoder to provide fine-grained semantic and design a prompt learner to fine-tune the LVLM using prompt embeddings. Our AnomalyGPT eliminates the need for manual threshold adjustments, thus directly assesses the presence and locations of anomalies. Additionally, AnomalyGPT supports multi-turn dialogues and exhibits impressive few-shot in-context learning capabilities. With only one normal shot, AnomalyGPT achieves the state-of-the-art performance with an accuracy of 86.1%, an image-level AUC of 94.1%, and a pixel-level AUC of 95.3% on the MVTec-AD dataset. Code is available at https://github.com/CASIA-IVA-Lab/AnomalyGPT.
Authors: Daniel LeJeune, Sina Alemohammad
In order to better understand feature learning in neural networks, we propose a framework for understanding linear models in tangent feature space where the features are allowed to be transformed during training. We consider linear transformations of features, resulting in a joint optimization over parameters and transformations with a bilinear interpolation constraint. We show that this optimization problem has an equivalent linearly constrained optimization with structured regularization that encourages approximately low rank solutions. Specializing to neural network structure, we gain insights into how the features and thus the kernel function change, providing additional nuance to the phenomenon of kernel alignment when the target function is poorly represented using tangent features. In addition to verifying our theoretical observations in real neural networks on a simple regression problem, we empirically show that an adaptive feature implementation of tangent feature classification has an order of magnitude lower sample complexity than the fixed tangent feature model on MNIST and CIFAR-10.
Authors: Renqi Chen, Jingjing Luo, Fan Nian, Yuhui Cen, Yiheng Peng, Zekuan Yu
Accurate medical image segmentation especially for echocardiographic images with unmissable noise requires elaborate network design. Compared with manual design, Neural Architecture Search (NAS) realizes better segmentation results due to larger search space and automatic optimization, but most of the existing methods are weak in layer-wise feature aggregation and adopt a ``strong encoder, weak decoder" structure, insufficient to handle global relationships and local details. To resolve these issues, we propose a novel semi-supervised hybrid NAS network for accurate medical image segmentation termed SSHNN. In SSHNN, we creatively use convolution operation in layer-wise feature fusion instead of normalized scalars to avoid losing details, making NAS a stronger encoder. Moreover, Transformers are introduced for the compensation of global context and U-shaped decoder is designed to efficiently connect global context with local features. Specifically, we implement a semi-supervised algorithm Mean-Teacher to overcome the limited volume problem of labeled medical image dataset. Extensive experiments on CAMUS echocardiography dataset demonstrate that SSHNN outperforms state-of-the-art approaches and realizes accurate segmentation. Code will be made publicly available.
Authors: Abhijit Ramesh, Anantha Nandanan, Nikhil Boggavarapu, Priya Nair MD, Gilad Gressel
Pancreatic cancer is a lethal form of cancer that significantly contributes to cancer-related deaths worldwide. Early detection is essential to improve patient prognosis and survival rates. Despite advances in medical imaging techniques, pancreatic cancer remains a challenging disease to detect. Endoscopic ultrasound (EUS) is the most effective diagnostic tool for detecting pancreatic cancer. However, it requires expert interpretation of complex ultrasound images to complete a reliable patient scan. To obtain complete imaging of the pancreas, practitioners must learn to guide the endoscope into multiple "EUS stations" (anatomical locations), which provide different views of the pancreas. This is a difficult skill to learn, involving over 225 proctored procedures with the support of an experienced doctor. We build an AI-assisted tool that utilizes deep learning techniques to identify these stations of the stomach in real time during EUS procedures. This computer-assisted diagnostic (CAD) will help train doctors more efficiently. Historically, the challenge faced in developing such a tool has been the amount of retrospective labeling required by trained clinicians. To solve this, we developed an open-source user-friendly labeling web app that streamlines the process of annotating stations during the EUS procedure with minimal effort from the clinicians. Our research shows that employing only 43 procedures with no hyperparameter fine-tuning obtained a balanced accuracy of 89%, comparable to the current state of the art. In addition, we employ Grad-CAM, a visualization technology that provides clinicians with interpretable and explainable visualizations.
Authors: Zhenbo Song, Xianghui Ze, Jianfeng Lu, Yujiao Shi
This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of dense pixel-wise flow fields in pairs of ground and satellite images to calculate the camera pose. Our approach differs from existing methods by constructing the feature metric at the pixel level, enabling full-image supervision for learning distinctive geometric configurations and visual appearances across views. Specifically, our method employs two distinct convolution networks for ground and satellite feature extraction. Then, we project the ground feature map to the bird's eye view (BEV) using a fixed camera height assumption to achieve preliminary geometric alignment. To further establish content association between the BEV and satellite features, we introduce a residual convolution block to refine the projected BEV feature. Optical flow estimation is performed on the refined BEV feature map and the satellite feature map using flow decoder networks based on RAFT. After obtaining dense flow correspondences, we apply the least square method to filter matching inliers and regress the ground camera pose. Extensive experiments demonstrate significant improvements compared to state-of-the-art methods. Notably, our approach reduces the median localization error by 89%, 19%, 80% and 35% on the KITTI, Ford multi-AV, VIGOR and Oxford RobotCar datasets, respectively.
Authors: Nicholas Konz, Charles Godfrey, Madelyn Shapiro, Jonathan Tu, Henry Kvinge, Davis Brown
By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data. As having the right (or wrong) concepts is critical to trustworthy machine learning systems, it is natural to ask which inputs from the model's original training set were most important for learning a concept at a given layer. To answer this, we combine data attribution methods with methods for probing the concepts learned by a model. Training network and probe ensembles for two concept datasets on a range of network layers, we use the recently developed TRAK method for large-scale data attribution. We find some evidence for convergence, where removing the 10,000 top attributing images for a concept and retraining the model does not change the location of the concept in the network nor the probing sparsity of the concept. This suggests that rather than being highly dependent on a few specific examples, the features that inform the development of a concept are spread in a more diffuse manner across its exemplars, implying robustness in concept formation.
Authors: Zhiwen Fan, Panwang Pan, Peihao Wang, Yifan Jiang, Hanwen Jiang, Dejia Xu, Zehao Zhu, Dilin Wang, Zhangyang Wang
In the field of novel-view synthesis, the necessity of knowing camera poses (e.g., via Structure from Motion) before rendering has been a common practice. However, the consistent acquisition of accurate camera poses remains elusive, and errors in pose extraction can adversely impact the view synthesis process. To address this challenge, we introduce PF-GRT, a new Pose-Free framework for Generalizable Rendering Transformer, eliminating the need for pre-computed camera poses and instead leveraging feature-matching learned directly from data. PF-GRT is parameterized using a local relative coordinate system, where one of the source images is set as the origin. An OmniView Transformer is designed for fusing multi-view cues under the pose-free setting, where unposed-view fusion and origin-centric aggregation are performed. The 3D point feature along target ray is sampled by projecting onto the selected origin plane. The final pixel intensities are modulated and decoded using another Transformer. PF-GRT demonstrates an impressive ability to generalize to new scenes that were not encountered during the training phase, without the need of pre-computing camera poses. Our experiments with zero-shot rendering on the LLFF, RealEstate-10k, Shiny, and Blender datasets reveal that it produces superior quality in generating photo-realistic images. Moreover, it demonstrates robustness against noise in test camera poses. Code is available at https://zhiwenfan.github.io/PF-GRT/.
Authors: Zhenglin Huang, Xianan Bao, Na Zhang, Qingqi Zhang, Xiaomei Tu, Biao Wu, Xi Yang
Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on clean data but also robustness when data distributions shift. While prior methods have proposed that there is a trade-off between accuracy and robustness, we propose IPMix, a simple data augmentation approach to improve robustness without hurting clean accuracy. IPMix integrates three levels of data augmentation (image-level, patch-level, and pixel-level) into a coherent and label-preserving technique to increase the diversity of training data with limited computational overhead. To further improve the robustness, IPMix introduces structural complexity at different levels to generate more diverse images and adopts the random mixing method for multi-scale information fusion. Experiments demonstrate that IPMix outperforms state-of-the-art corruption robustness on CIFAR-C and ImageNet-C. In addition, we show that IPMix also significantly improves the other safety measures, including robustness to adversarial perturbations, calibration, prediction consistency, and anomaly detection, achieving state-of-the-art or comparable results on several benchmarks, including ImageNet-R, ImageNet-A, and ImageNet-O.
Authors: Denis Mbey Akola, Gianni Franchi
This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty. We propose training one Region Proposal Network(RPN) and multiple Fast R-CNN prediction heads is all you need to build a robust deep ensemble network for estimating uncertainty in object detection. We present this approach and provide experiments to show that this approach is much faster than the naive method of fully training all $n$ models in an ensemble. We also estimate the uncertainty by measuring this ensemble model's Expected Calibration Error (ECE). We then further compare the performance of this model with that of Gaussian YOLOv3, a variant of YOLOv3 that models uncertainty using predicted bounding box coordinates. The source code is released at \url{https://github.com/Akola-Mbey-Denis/EfficientEnsemble}
Authors: Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen, Yongheng Wang, Huajun Chen, Ningyu Zhang
In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the editing process. To facilitate research in this area, we construct a new benchmark, dubbed MMEdit, for editing multimodal LLMs and establishing a suite of innovative metrics for evaluation. We conduct comprehensive experiments involving various model editing baselines and analyze the impact of editing different components for multimodal LLMs. Empirically, we notice that previous baselines can implement editing multimodal LLMs to some extent, but the effect is still barely satisfactory, indicating the potential difficulty of this task. We hope that our work can provide the NLP community with insights. Code and dataset are available in https://github.com/zjunlp/EasyEdit.
Authors: Wangyu Wu, Tianhong Dai, Xiaowei Huang, Fei Ma, Jimin Xiao
Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to cost-effectiveness. Recently, Vision Transformer (ViT) based methods without class activation map (CAM) have shown greater capability in generating reliable pseudo labels than previous methods using CAM. However, the current ViT-based methods utilize max pooling to select the patch with the highest prediction score to map the patch-level classification to the image-level one, which may affect the quality of pseudo labels due to the inaccurate classification of the patches. In this paper, we introduce a novel ViT-based WSSS method named top-K pooling with patch contrastive learning (TKP-PCL), which employs a top-K pooling layer to alleviate the limitations of previous max pooling selection. A patch contrastive error (PCE) is also proposed to enhance the patch embeddings to further improve the final results. The experimental results show that our approach is very efficient and outperforms other state-of-the-art WSSS methods on the PASCAL VOC 2012 dataset.
Authors: Uri Stern, Daniel Shwartz, Daphna Weinshall
Deep neural networks have become the method of choice for solving many classification tasks, largely because they can fit very complex functions defined over raw data. The downside of such powerful learners is the danger of overfit. In this paper, we introduce a novel ensemble classifier for deep networks that effectively overcomes overfitting by combining models generated at specific intermediate epochs during training. Our method allows for the incorporation of useful knowledge obtained by the models during the overfitting phase without deterioration of the general performance, which is usually missed when early stopping is used. To motivate this approach, we begin with the theoretical analysis of a regression model, whose prediction -- that the variance among classifiers increases when overfit occurs -- is demonstrated empirically in deep networks in common use. Guided by these results, we construct a new ensemble-based prediction method, where the prediction is determined by the class that attains the most consensual prediction throughout the training epochs. Using multiple image and text classification datasets, we show that when regular ensembles suffer from overfit, our method eliminates the harmful reduction in generalization due to overfit, and often even surpasses the performance obtained by early stopping. Our method is easy to implement and can be integrated with any training scheme and architecture, without additional prior knowledge beyond the training set. It is thus a practical and useful tool to overcome overfit. Code is available at https://github.com/uristern123/United-We-Stand-Using-Epoch-wise-Agreement-of-Ensembles-to-Combat-Overfit.
Authors: Maomao Li, Ge Yuan, Cairong Wang, Zhian Liu, Yong Zhang, Yongwei Nie, Jue Wang, Dong Xu
This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed "editing for swapping" (E4S). The traditional face swapping methods rely on global feature extraction and often fail to preserve the source identity. In contrast, our framework proposes a Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. Specifically, our E4S performs face swapping in the latent space of a pretrained StyleGAN, where a multi-scale mask-guided encoder is applied to project the texture of each facial component into regional style codes and a mask-guided injection module then manipulates feature maps with the style codes. Based on this disentanglement, face swapping can be simplified as style and mask swapping. Besides, since reconstructing the source face in the target image may lead to disharmony lighting, we propose to train a re-coloring network to make the swapped face maintain the lighting condition on the target face. Further, to deal with the potential mismatch area during mask exchange, we designed a face inpainting network as post-processing. The extensive comparisons with state-of-the-art methods demonstrate that our E4S outperforms existing methods in preserving texture, shape, and lighting. Our implementation is available at https://github.com/e4s2023/E4S2023.
Authors: Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs - by guaranteeing robustness of the majority vote when randomly adding noise before classification. Yet, certifying robustness on such complex data via randomized smoothing is challenging when adversaries do not arbitrarily perturb entire objects (e.g. images) but only a subset of their entities (e.g. pixels). As a solution, we introduce hierarchical randomized smoothing: We partially smooth objects by adding random noise only on a randomly selected subset of their entities. By adding noise in a more targeted manner than existing methods we obtain stronger robustness guarantees while maintaining high accuracy. We initialize hierarchical smoothing using different noising distributions, yielding novel robustness certificates for discrete and continuous domains. We experimentally demonstrate the importance of hierarchical smoothing in image and node classification, where it yields superior robustness-accuracy trade-offs. Overall, hierarchical smoothing is an important contribution towards models that are both - certifiably robust to perturbations and accurate.
Authors: Srijan Das, Tanmay Jain, Dominick Reilly, Pranav Balaji, Soumyajit Karmakar, Shyam Marjit, Xiang Li, Abhijit Das, Michael S. Ryoo
Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training ViTs with self-supervised learning (SSL) and fine-tuning sequentially. However, we observe that jointly optimizing ViTs for the primary task and a Self-Supervised Auxiliary Task (SSAT) is surprisingly beneficial when the amount of training data is limited. We explore the appropriate SSL tasks that can be optimized alongside the primary task, the training schemes for these tasks, and the data scale at which they can be most effective. Our findings reveal that SSAT is a powerful technique that enables ViTs to leverage the unique characteristics of both the self-supervised and primary tasks, achieving better performance than typical ViTs pre-training with SSL and fine-tuning sequentially. Our experiments, conducted on 10 datasets, demonstrate that SSAT significantly improves ViT performance while reducing carbon footprint. We also confirm the effectiveness of SSAT in the video domain for deepfake detection, showcasing its generalizability. Our code is available at https://github.com/dominickrei/Limited-data-vits.
Authors: Jinjin Xu, Liwu Xu, Yuzhe Yang, Xiang Li, Yanchun Xie, Yi-Jie Huang, Yaqian Li
Recent advances such as LLaVA and Mini-GPT4 have successfully integrated visual information into LLMs, yielding inspiring outcomes and giving rise to a new generation of multi-modal LLMs, or MLLMs. Nevertheless, these methods struggle with hallucinations and the mutual interference between tasks. To tackle these problems, we propose an efficient and accurate approach to adapt to downstream tasks by utilizing LLM as a bridge to connect multiple expert models, namely u-LLaVA. Firstly, we incorporate the modality alignment module and multi-task modules into LLM. Then, we reorganize or rebuild multi-type public datasets to enable efficient modality alignment and instruction following. Finally, task-specific information is extracted from the trained LLM and provided to different modules for solving downstream tasks. The overall framework is simple, effective, and achieves state-of-the-art performance across multiple benchmarks. We also release our model, the generated data, and the code base publicly available at https://github.com/OPPOMKLab/u-LLaVA.
Authors: Pranav Singh, Raviteja Chukkapalli, Shravan Chaudhari, Luoyao Chen, Mei Chen, Jinqian Pan, Craig Smuda, Jacopo Cirrone
Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages the advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Remarkably, we observed that self-supervised learning with only 10% of the annotation surpassed the performance of full annotation in the classification of most datasets. Similarly, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods with 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods.
Authors: Jiageng Zhong, Ming Li, Yinliang Chen, Zihang Wei, Fan Yang, Haoran Shen
For intelligent quadcopter UAVs, a robust and reliable autonomous planning system is crucial. Most current trajectory planning methods for UAVs are suitable for static environments but struggle to handle dynamic obstacles, which can pose challenges and even dangers to flight. To address this issue, this paper proposes a vision-based planning system that combines tracking and trajectory prediction of dynamic obstacles to achieve efficient and reliable autonomous flight. We use a lightweight object detection algorithm to identify dynamic obstacles and then use Kalman Filtering to track and estimate their motion states. During the planning phase, we not only consider static obstacles but also account for the potential movements of dynamic obstacles. For trajectory generation, we use a B-spline-based trajectory search algorithm, which is further optimized with various constraints to enhance safety and alignment with the UAV's motion characteristics. We conduct experiments in both simulation and real-world environments, and the results indicate that our approach can successfully detect and avoid obstacles in dynamic environments in real-time, offering greater reliability compared to existing approaches. Furthermore, with the advancements in Natural Language Processing (NLP) technology demonstrating exceptional zero-shot generalization capabilities, more user-friendly human-machine interactions have become feasible, and this study also explores the integration of autonomous planning systems with Large Language Models (LLMs).
Authors: Quazi Mishkatul Alam, Bilel Tarchoun, Ihsen Alouani, Nael Abu-Ghazaleh
The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling. Deformable vision transformers significantly reduce the quadratic complexity of attention modeling by using sparse attention structures, enabling them to incorporate features across different scales and be used in large-scale applications, such as multi-view vision systems. Recent work has demonstrated adversarial attacks against conventional vision transformers; we show that these attacks do not transfer to deformable transformers due to their sparse attention structure. Specifically, attention in deformable transformers is modeled using pointers to the most relevant other tokens. In this work, we contribute for the first time adversarial attacks that manipulate the attention of deformable transformers, redirecting it to focus on irrelevant parts of the image. We also develop new collaborative attacks where a source patch manipulates attention to point to a target patch, which contains the adversarial noise to fool the model. In our experiments, we observe that altering less than 1% of the patched area in the input field results in a complete drop to 0% AP in single-view object detection using MS COCO and a 0% MODA in multi-view object detection using Wildtrack.
Authors: Niv Cohen, Issar Tzachor, Yedid Hoshen
This paper proposes set features for detecting anomalies in samples that consist of unusual combinations of normal elements. Many leading methods discover anomalies by detecting an unusual part of a sample. For example, state-of-the-art segmentation-based approaches, first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as anomalous if it contains anomalous elements. However, such approaches do not extend well to scenarios where the anomalies are expressed by an unusual combination of normal elements. In this paper, we overcome this limitation by proposing set features that model each sample by the distribution of its elements. We compute the anomaly score of each sample using a simple density estimation method, using fixed features. Our approach outperforms the previous state-of-the-art in image-level logical anomaly detection and sequence-level time series anomaly detection.
Authors: Xingqun Qi, Jiahao Pan, Peng Li, Ruibin Yuan, Xiaowei Chi, Mengfei Li, Wenhan Luo, Wei Xue, Shanghang Zhang, Qifeng Liu, Yike Guo
Generating vivid and emotional 3D co-speech gestures is crucial for virtual avatar animation in human-machine interaction applications. While the existing methods enable generating the gestures to follow a single emotion label, they overlook that long gesture sequence modeling with emotion transition is more practical in real scenes. In addition, the lack of large-scale available datasets with emotional transition speech and corresponding 3D human gestures also limits the addressing of this task. To fulfill this goal, we first incorporate the ChatGPT-4 and an audio inpainting approach to construct the high-fidelity emotion transition human speeches. Considering obtaining the realistic 3D pose annotations corresponding to the dynamically inpainted emotion transition audio is extremely difficult, we propose a novel weakly supervised training strategy to encourage authority gesture transitions. Specifically, to enhance the coordination of transition gestures w.r.t different emotional ones, we model the temporal association representation between two different emotional gesture sequences as style guidance and infuse it into the transition generation. We further devise an emotion mixture mechanism that provides weak supervision based on a learnable mixed emotion label for transition gestures. Last, we present a keyframe sampler to supply effective initial posture cues in long sequences, enabling us to generate diverse gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models constructed by adapting single emotion-conditioned counterparts on our newly defined emotion transition task and datasets. Our code and dataset will be released on the project page: https://xingqunqi-lab.github.io/Emo-Transition/.
Authors: Ting Liu, Yue Hu, Wansen Wu, Youkai Wang, Kai Xu, Quanjun Yin
Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of them are trained on web-crawled general-purpose datasets, which incurs a considerable domain gap when used for VLN tasks. To address the problem, we propose a novel and model-agnostic domain-aware prompt learning (DAP) framework. For equipping the pretrained models with specific object-level and scene-level cross-modal alignment in VLN tasks, DAP applies a low-cost prompt tuning paradigm to learn soft visual prompts for extracting in-domain image semantics. Specifically, we first generate a set of in-domain image-text pairs with the help of the CLIP model. Then we introduce soft visual prompts in the input space of the visual encoder in a pretrained model. DAP injects in-domain visual knowledge into the visual encoder of the pretrained model in an efficient way. Experimental results on both R2R and REVERIE show the superiority of DAP compared to existing state-of-the-art methods.
Authors: Xiuhong Lin, Changjie Qiu, Zhipeng Cai, Siqi Shen, Yu Zang, Weiquan Liu, Xuesheng Bian, Matthias Müller, Cheng Wang
Event cameras have emerged as a promising vision sensor in recent years due to their unparalleled temporal resolution and dynamic range. While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior work studies 2D-3D registration for event cameras. To this end, we propose E2PNet, the first learning-based method for event-to-point cloud registration. The core of E2PNet is a novel feature representation network called Event-Points-to-Tensor (EP2T), which encodes event data into a 2D grid-shaped feature tensor. This grid-shaped feature enables matured RGB-based frameworks to be easily used for event-to-point cloud registration, without changing hyper-parameters and the training procedure. EP2T treats the event input as spatio-temporal point clouds. Unlike standard 3D learning architectures that treat all dimensions of point clouds equally, the novel sampling and information aggregation modules in EP2T are designed to handle the inhomogeneity of the spatial and temporal dimensions. Experiments on the MVSEC and VECtor datasets demonstrate the superiority of E2PNet over hand-crafted and other learning-based methods. Compared to RGB-based registration, E2PNet is more robust to extreme illumination or fast motion due to the use of event data. Beyond 2D-3D registration, we also show the potential of EP2T for other vision tasks such as flow estimation, event-to-image reconstruction and object recognition. The source code can be found at: https://github.com/Xmu-qcj/E2PNet.
Authors: Yiwei Ma, Yijun Fan, Jiayi Ji, Haowei Wang, Xiaoshuai Sun, Guannan Jiang, Annan Shu, Rongrong Ji
In recent times, automatic text-to-3D content creation has made significant progress, driven by the development of pretrained 2D diffusion models. Existing text-to-3D methods typically optimize the 3D representation to ensure that the rendered image aligns well with the given text, as evaluated by the pretrained 2D diffusion model. Nevertheless, a substantial domain gap exists between 2D images and 3D assets, primarily attributed to variations in camera-related attributes and the exclusive presence of foreground objects. Consequently, employing 2D diffusion models directly for optimizing 3D representations may lead to suboptimal outcomes. To address this issue, we present X-Dreamer, a novel approach for high-quality text-to-3D content creation that effectively bridges the gap between text-to-2D and text-to-3D synthesis. The key components of X-Dreamer are two innovative designs: Camera-Guided Low-Rank Adaptation (CG-LoRA) and Attention-Mask Alignment (AMA) Loss. CG-LoRA dynamically incorporates camera information into the pretrained diffusion models by employing camera-dependent generation for trainable parameters. This integration enhances the alignment between the generated 3D assets and the camera's perspective. AMA loss guides the attention map of the pretrained diffusion model using the binary mask of the 3D object, prioritizing the creation of the foreground object. This module ensures that the model focuses on generating accurate and detailed foreground objects. Extensive evaluations demonstrate the effectiveness of our proposed method compared to existing text-to-3D approaches. Our project webpage: https://xmu-xiaoma666.github.io/Projects/X-Dreamer/ .
Authors: Jie Wang, Jiu-Cheng Xie, Xianyan Li, Feng Xu, Chi-Man Pun, Hao Gao
Previous head avatar methods have primarily relied on fixed-shape scene primitives, lacking a balance between geometric topology, texture details, and computational efficiency. Some hybrid neural network methods (e.g., planes and voxels) gained advantages in fast rendering, but they all used axis-aligned mappings to extract features explicitly, leading to issues of axis-aligned bias and feature dilution. We present GaussianHead, which utilizes deformable 3D Gaussians as building blocks for the head avatars. We propose a novel methodology where the core Gaussians designated for rendering undergo dynamic diffusion before being mapped onto a factor plane to acquire canonical sub-factors. Through our factor blending strategy, the canonical features for the core Gaussians used in rendering are obtained. This approach deviates from the previous practice of utilizing axis-aligned mappings, especially improving the representation capability of subtle structures such as teeth, wrinkles, hair, and even facial pores. In comparison to state-of-the-art methods, our unique primitive selection and factor decomposition in GaussianHead deliver superior visual results while maintaining rendering performance (0.1 seconds per frame). Code will released for research.
Authors: Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang
Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, they did not explore 3D and vision-language tasks for human-centric and required task-specific finetuning. These limitations restrict their application to more downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat diverse human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. Comprehensive evaluations of Hulk on 12 benchmarks covering 8 human-centric tasks demonstrate the superiority of our proposed method, achieving state-of-the-art performance in 11 benchmarks. The code will be available on https://github.com/OpenGVLab/HumanBench.
Authors: Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao, Xi Peng
All-in-one aims to solve various tasks of image restoration in a single model. To this end, we present a feasible way of exploiting the image priors captured by the pretrained diffusion model, through addressing the two challenges, i.e., degradation modeling and diffusion guidance. The former aims to simulate the process of the clean image degenerated by the unknown degradations, and the latter aims at guiding the diffusion model to generate the desired clean image. With the motivations, we propose a zero-shot framework for all-in-one image restoration, termed ZeroAIR, which alternatively performs the test-time degradation modeling (TDM) and the three-stage diffusion guidance (TDG) at each timestep of the reverse sampling. To be specific, TDM exploits the diffusion priors to learn a degradation model from a given degraded image, and TDG divides the timesteps into three stages for taking full advantages of the varying diffusion priors. Thanks to their degradation-agnostic property, all-in-one restoration could be achieved in a zero-shot way. Through extensive experiments, we show that our ZeroAIR achieves comparable even better performance than those task-specific methods. The code will be available on Github.
Authors: Alessandro Farace di Villaforesta, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò
To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explained Networks to provide global explanations for Graph Neural Networks. We demonstrate this using a generally applicable graph construction and classification pipeline, involving panoptic segmentation with HoVer-Net and cancer prediction with Graph Convolution Networks. By training on H&E slides of breast cancer, we show promising results in offering explainable and trustworthy AI tools for clinicians.
Authors: Mohammed Baharoon, Waseem Qureshi, Jiahong Ouyang, Yanwu Xu, Abdulrhman Aljouie, Wei Peng
The integration of deep learning systems into healthcare has been hindered by the resource-intensive process of data annotation and the inability of these systems to generalize to different data distributions. Foundation models, which are models pre-trained on large datasets, have emerged as a solution to reduce reliance on annotated data and enhance model generalizability and robustness. DINOv2 is an open-source foundation model pre-trained with self-supervised learning on 142 million curated natural images that exhibits promising capabilities across various vision tasks. Nevertheless, a critical question remains unanswered regarding DINOv2's adaptability to radiological imaging, and whether its features are sufficiently general to benefit radiology image analysis. Therefore, this study comprehensively evaluates DINOv2 for radiology, conducting over 100 experiments across diverse modalities (X-ray, CT, and MRI). To measure the effectiveness and generalizability of DINOv2's feature representations, we analyze the model across medical image analysis tasks including disease classification and organ segmentation on both 2D and 3D images, and under different settings like kNN, few-shot learning, linear-probing, end-to-end fine-tuning, and parameter-efficient fine-tuning. Comparative analyses with established supervised, self-supervised, and weakly-supervised models reveal DINOv2's superior performance and cross-task generalizability. The findings contribute insights to potential avenues for optimizing pre-training strategies for medical imaging and enhancing the broader understanding of DINOv2's role in bridging the gap between natural and radiological image analysis. Our code is available at https://github.com/MohammedSB/DINOv2ForRadiology
Authors: Xin Li, Yeqi Bai, Pinlong Cai, Licheng Wen, Daocheng Fu, Bo Zhang, Xuemeng Yang, Xinyu Cai, Tao Ma, Jianfei Guo, Xing Gao, Min Dou, Yikang Li, Botian Shi, Yong Liu, Liang He, Yu Qiao
This paper explores the emerging knowledge-driven autonomous driving technologies. Our investigation highlights the limitations of current autonomous driving systems, in particular their sensitivity to data bias, difficulty in handling long-tail scenarios, and lack of interpretability. Conversely, knowledge-driven methods with the abilities of cognition, generalization and life-long learning emerge as a promising way to overcome these challenges. This paper delves into the essence of knowledge-driven autonomous driving and examines its core components: dataset \& benchmark, environment, and driver agent. By leveraging large language models, world models, neural rendering, and other advanced artificial intelligence techniques, these components collectively contribute to a more holistic, adaptive, and intelligent autonomous driving system. The paper systematically organizes and reviews previous research efforts in this area, and provides insights and guidance for future research and practical applications of autonomous driving. We will continually share the latest updates on cutting-edge developments in knowledge-driven autonomous driving along with the relevant valuable open-source resources at: \url{https://github.com/PJLab-ADG/awesome-knowledge-driven-AD}.
Authors: Zechuan Zhang, Zongxin Yang, Yi Yang
Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline.SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios. Project page https://river-zhang.github.io/SIFU-projectpage/ .
Authors: Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov
A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. In pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework.
Code: https://github.com/NVlabs/RADIO
Authors: Rahul Venkatesh, Honglin Chen, Kevin Feigelis, Daniel M. Bear, Khaled Jedoui, Klemen Kotar, Felix Binder, Wanhee Lee, Sherry Liu, Kevin A. Smith, Judith E. Fan, Daniel L. K. Yamins
The ability to understand physical dynamics is essential to learning agents acting in the world. This paper presents Counterfactual World Modeling (CWM), a candidate pure vision foundational model for physical dynamics understanding. CWM consists of three basic concepts. First, we propose a simple and powerful temporally-factored masking policy for masked prediction of video data, which encourages the model to learn disentangled representations of scene appearance and dynamics. Second, as a result of the factoring, CWM is capable of generating counterfactual next-frame predictions by manipulating a few patch embeddings to exert meaningful control over scene dynamics. Third, the counterfactual modeling capability enables the design of counterfactual queries to extract vision structures similar to keypoints, optical flows, and segmentations, which are useful for dynamics understanding. We show that zero-shot readouts of these structures extracted by the counterfactual queries attain competitive performance to prior methods on real-world datasets. Finally, we demonstrate that CWM achieves state-of-the-art performance on the challenging Physion benchmark for evaluating physical dynamics understanding.
Authors: Ranjan Sapkota, Dawood Ahmed, Manoj Karkee
Instance segmentation, an important image processing operation for automation in agriculture, is used to precisely delineate individual objects of interest within images, which provides foundational information for various automated or robotic tasks such as selective harvesting and precision pruning. This study compares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learning models for instance segmentation under varying orchard conditions across two datasets. Dataset 1, collected in dormant season, includes images of dormant apple trees, which were used to train multi-object segmentation models delineating tree branches and trunks. Dataset 2, collected in the early growing season, includes images of apple tree canopies with green foliage and immature (green) apples (also called fruitlet), which were used to train single-object segmentation models delineating only immature green apples. The results showed that YOLOv8 performed better than Mask R-CNN, achieving good precision and near-perfect recall across both datasets at a confidence threshold of 0.5. Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recall of 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of 0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieved a precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-class scenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, the inference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset 1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 ms and 12.8 ms achieved by Mask R-CNN's, respectively.
Authors: Wenting Chen, Linlin Shen, Xiang Li, 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: Liangchen Song, Liangliang Cao, Jiatao Gu, Yifan Jiang, Junsong Yuan, Hao Tang
The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption of 3D content editing is its time-intensive processing. This challenge arises from the iterative and refining steps required to achieve consistent 3D outputs from 2D image-based generative models. Recent state-of-the-art methods typically require optimization time ranging from tens of minutes to several hours to edit a 3D scene using a single GPU. In this work, we propose that by incorporating correspondence regularization into diffusion models, the process of 3D editing can be significantly accelerated. This approach is inspired by the notion that the estimated samples during diffusion should be multiview-consistent during the diffusion generation process. By leveraging this multiview consistency, we can edit 3D content at a much faster speed. In most scenarios, our proposed technique brings a 10$\times$ speed-up compared to the baseline method and completes the editing of a 3D scene in 2 minutes with comparable quality.
Authors: Huy Le, Tung Kieu, Anh Nguyen, Ngan Le
Text-video retrieval, a prominent sub-field within the domain of multimodal information retrieval, has witnessed remarkable growth in recent years. However, existing methods assume video scenes are consistent with unbiased descriptions. These limitations fail to align with real-world scenarios since 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 framework via vision-language models through open-vocabulary knowledge designed to tackle the challenge of handling different writing styles in video descriptions. WAVER capitalizes on the open-vocabulary properties that lie 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 task while handling writing-style variations.
Authors: Nikita Starodubcev, Artem Fedorov, Artem Babenko, Dmitry Baranchuk
Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage. In this work, we investigate the relative quality of samples produced by the teacher text-to-image diffusion model and its distilled student version. As our main empirical finding, we discover that a noticeable portion of student samples exhibit superior fidelity compared to the teacher ones, despite the ``approximate'' nature of the student. Based on this finding, we propose an adaptive collaboration between student and teacher diffusion models for effective text-to-image synthesis. Specifically, the distilled model produces the initial sample, and then an oracle decides whether it needs further improvements with a slow teacher model. Extensive experiments demonstrate that the designed pipeline surpasses state-of-the-art text-to-image alternatives for various inference budgets in terms of human preference. Furthermore, the proposed approach can be naturally used in popular applications such as text-guided image editing and controllable generation.
Authors: Decheng Liu, Xijun Wang, Chunlei Peng, Nannan Wang, Ruiming Hu, Xinbo Gao
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods still can't achieve satisfactory performance because of low transferability and high detectability. In this paper, we propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space, which utilizes strong inpainting capabilities of the latent diffusion model to generate realistic adversarial images. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness. Extensive qualitative and quantitative experiments on the public FFHQ and CelebA-HQ datasets prove the proposed method achieves superior performance compared with the state-of-the-art methods without an extra generative model training process. The source code is available at https://github.com/kopper-xdu/Adv-Diffusion.
Authors: Junwu Zhang, Zhenyu Tang, Yatian Pang, Xinhua Cheng, Peng Jin, Yida Wei, Munan Ning, Li Yuan
Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoothed textures, as well as the slow generation speed. To address these deficiencies, we present Repaint123 to alleviate multi-view bias as well as texture degradation and speed up the generation process. The core idea is to combine the powerful image generation capability of the 2D diffusion model and the texture alignment ability of the repainting strategy for generating high-quality multi-view images with consistency. We further propose visibility-aware adaptive repainting strength for overlap regions to enhance the generated image quality in the repainting process. The generated high-quality and multi-view consistent images enable the use of simple Mean Square Error (MSE) loss for fast 3D content generation. We conduct extensive experiments and show that our method has a superior ability to generate high-quality 3D content with multi-view consistency and fine textures in 2 minutes from scratch. Our project page is available at https://pku-yuangroup.github.io/repaint123/.
Authors: Qinying Liu, Kecheng Zheng, Wei Wu, Zhan Tong, Yu Liu, Wei Chen, Zilei Wang, Yujun Shen
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an attribute-specified object. In this work, we propose an embarrassingly simple approach to better align image and text features with no need of additional data formats other than image-text pairs. Concretely, given an image and its paired text, we manage to parse objects (e.g., cat) and attributes (e.g., black) from the description, which are highly likely to exist in the image. It is noteworthy that the parsing pipeline is fully automatic and thus enjoys good scalability. With these parsed semantics as supervision signals, we can complement the commonly used image-text contrastive loss with the multi-tag classification loss. Extensive experimental results on a broad suite of semantic segmentation datasets substantiate the average 3.65\% improvement of our framework over existing alternatives. Furthermore, the visualization results indicate that attribute supervision makes vision-language models accurately localize attribute-specified objects. Project page and code can be found at https://qinying-liu.github.io/Tag-Align.
Authors: Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Zihan Song, Yuwei Zhou, Wenwu Zhu
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task requiring the model to precisely locate the start and end timestamps of temporal moments in videos that match the given textual queries, still remains unclear and unexplored in literature. To fill the gap, in this paper, we propose the LLM4VG benchmark, which systematically evaluates the performance of different LLMs on video grounding tasks. Based on our proposed LLM4VG, we design extensive experiments to examine two groups of video LLM models on video grounding: (i) the video LLMs trained on the text-video pairs (denoted as VidLLM), and (ii) the LLMs combined with pretrained visual description models such as the video/image captioning model. We propose prompt methods to integrate the instruction of VG and description from different kinds of generators, including caption-based generators for direct visual description and VQA-based generators for information enhancement. We also provide comprehensive comparisons of various VidLLMs and explore the influence of different choices of visual models, LLMs, prompt designs, etc, as well. Our experimental evaluations lead to two conclusions: (i) the existing VidLLMs are still far away from achieving satisfactory video grounding performance, and more time-related video tasks should be included to further fine-tune these models, and (ii) the combination of LLMs and visual models shows preliminary abilities for video grounding with considerable potential for improvement by resorting to more reliable models and further guidance of prompt instructions.
Authors: Yiqi Lin, Conghui He, Alex Jinpeng Wang, Bin Wang, Weijia Li, Mike Zheng Shou
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to 'Parrot' the visual text embedded within images while disregarding the authentic visual semantics. We uncover that in the most popular image-text dataset LAION-2B, the captions also densely parrot (spell) the text embedded in images. Our analysis shows that around 50% of images are embedded with visual text content, and 90% of their captions more or less parrot the visual text. Based on such observation, we thoroughly inspect the different released versions of CLIP models and verify that the visual text is the dominant factor in measuring the LAION-style image-text similarity for these models. To examine whether these parrot captions shape the text spotting bias, we train a series of CLIP models with LAION subsets curated by different parrot-caption-oriented criteria. We show that training with parrot captions easily shapes such bias but harms the expected visual-language representation learning in CLIP models. This suggests that it is urgent to revisit either the design of CLIP-like models or the existing image-text dataset curation pipeline built on CLIP score filtering.
Authors: Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, Jifeng Dai
The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. It has powerful visual capabilities and can be a good alternative to the ViT-22B. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL.
Authors: Johann Ostmeyer, Ludovica Schaerf, Pavel Buividovich, Tessa Charles, Eric Postma, Carina Popovici
Previous research has shown that Artificial Intelligence is capable of distinguishing between authentic paintings by a given artist and human-made forgeries with remarkable accuracy, provided sufficient training. However, with the limited amount of existing known forgeries, augmentation methods for forgery detection are highly desirable. In this work, we examine the potential of incorporating synthetic artworks into training datasets to enhance the performance of forgery detection. Our investigation focuses on paintings by Vincent van Gogh, for which we release the first dataset specialized for forgery detection. To reinforce our results, we conduct the same analyses on the artists Amedeo Modigliani and Raphael. We train a classifier to distinguish original artworks from forgeries. For this, we use human-made forgeries and imitations in the style of well-known artists and augment our training sets with images in a similar style generated by Stable Diffusion and StyleGAN. We find that the additional synthetic forgeries consistently improve the detection of human-made forgeries. In addition, we find that, in line with previous research, the inclusion of synthetic forgeries in the training also enables the detection of AI-generated forgeries, especially if created using a similar generator.
Authors: Jinchao Zhu, Yuxuan Wang, Xiaobing Tu, Siyuan Pan, Pengfei Wan, Gao Huang
The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model. Although there have been some attempts to reduce sampling steps, model distillation, and network quantization, these previous methods generally retain the original network architecture. Billion scale parameters and high computing requirements make the research of model architecture adjustment scarce. In this work, we first explore the computational redundancy part of the network, and then prune the redundancy blocks of the model and maintain the network performance through a progressive incubation strategy. Secondly, in order to maintaining the model performance, we add cross-layer multi-expert conditional convolution (CLME-Condconv) to the block pruning part to inherit the original convolution parameters. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part. Finally, we use semantic-aware supervision (SAS) to align the outputs of the teacher model and student model at the semantic level. Experiments show that this method can effectively train a lightweight model close to the performance of the original SD model, and effectively improve the model speed under limited resources. Experiments show that the proposed method can effectively train a light-weight model close to the performance of the original SD model, and effectively improve the model speed under limited resources. After acceleration, the UNet part of the model is 22% faster and the overall speed is 19% faster.
Authors: Chen Hou, Guoqiang Wei, Zhibo Chen
Diffusion models have attained remarkable success in the domains of image generation and editing. It is widely recognized that employing larger inversion and denoising steps in diffusion model leads to improved image reconstruction quality. However, the editing performance of diffusion models tends to be no more satisfactory even with increasing denoising steps. The deficiency in editing could be attributed to the conditional Markovian property of the editing process, where errors accumulate throughout denoising steps. To tackle this challenge, we first propose an innovative framework where a rectifier module is incorporated to modulate diffusion model weights with residual features, thereby providing compensatory information to bridge the fidelity gap. Furthermore, we introduce a novel learning paradigm aimed at minimizing error propagation during the editing process, which trains the editing procedure in a manner similar to denoising score-matching. Extensive experiments demonstrate that our proposed framework and training strategy achieve high-fidelity reconstruction and editing results across various levels of denoising steps, meanwhile exhibits exceptional performance in terms of both quantitative metric and qualitative assessments. Moreover, we explore our model's generalization through several applications like image-to-image translation and out-of-domain image editing.
Authors: Jing Wang, Jinagyun Li, Chen Chen, Yisi Zhang, Haoran Shen, Tianxiang Zhang
The Few-Shot Segmentation (FSS) aims to accomplish the novel class segmentation task with a few annotated images. Current FSS research based on meta-learning focus on designing a complex interaction mechanism between the query and support feature. However, unlike humans who can rapidly learn new things from limited samples, the existing approach relies solely on fixed feature matching to tackle new tasks, lacking adaptability. In this paper, we propose a novel framework based on the adapter mechanism, namely Adaptive FSS, which can efficiently adapt the existing FSS model to the novel classes. In detail, we design the Prototype Adaptive Module (PAM), which utilizes accurate category information provided by the support set to derive class prototypes, enhancing class-specific information in the multi-stage representation. In addition, our approach is compatible with in diverse FSS methods with different backbones by simply inserting PAM between the layers of the encoder. Experiments demonstrate that our method effectively improves the performance of the FSS models (e.g., MSANet, HDMNet, FPTrans, and DCAMA) and achieve new state-of-the-art (SOTA) results (i.e., 72.4\% and 79.1\% mIoU on PASCAL-5$^i$ 1-shot and 5-shot settings, 52.7\% and 60.0\% mIoU on COCO-20$^i$ 1-shot and 5-shot settings). Our code can be available at https://github.com/jingw193/AdaptiveFSS.
Authors: Zeqiang Wei, Kai Jin, Xiuzhuang Zhou
Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. Eliminating heterogeneity between different modalities to enhance semantic consistency is the key challenge of this task. The current Vision-Language Pretraining (VLP) models, with cross-modal contrastive learning and masked reconstruction as joint training tasks, can effectively enhance the performance of cross-modal retrieval. This framework typically employs dual-stream inputs, using unmasked data for cross-modal contrastive learning and masked data for reconstruction. However, due to task competition and information interference caused by significant differences between the inputs of the two proxy tasks, the effectiveness of representation learning for intra-modal and cross-modal features is limited. In this paper, we propose an efficient VLP framework named Masked Contrastive and Reconstruction (MCR), which takes masked data as the sole input for both tasks. This enhances task connections, reducing information interference and competition between them, while also substantially decreasing the required GPU memory and training time. Moreover, we introduce a new modality alignment strategy named Mapping before Aggregation (MbA). Unlike previous methods, MbA maps different modalities to a common feature space before conducting local feature aggregation, thereby reducing the loss of fine-grained semantic information necessary for improved modality alignment. Qualitative and quantitative experiments conducted on the MIMIC-CXR dataset validate the effectiveness of our approach, demonstrating state-of-the-art performance in medical cross-modal retrieval tasks.
Authors: Jaehyuk Jang, Yooseung Wang, Changick Kim
Recently, multimodal prompting, which introduces learnable missing-aware prompts for all missing modality cases, has exhibited impressive performance. However, it encounters two critical issues: 1) The number of prompts grows exponentially as the number of modalities increases; and 2) It lacks robustness in scenarios with different missing modality settings between training and inference. In this paper, we propose a simple yet effective prompt design to address these challenges. Instead of using missing-aware prompts, we utilize prompts as modality-specific tokens, enabling them to capture the unique characteristics of each modality. Furthermore, our prompt design leverages orthogonality between prompts as a key element to learn distinct information across different modalities and promote diversity in the learned representations. Extensive experiments demonstrate that our prompt design enhances both performance and robustness while reducing the number of prompts.
Authors: Qiaoyu Zheng, Weike Zhao, Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie
In this study, we aim to investigate the problem of large-scale, large-vocabulary disease classification for radiologic images, which can be formulated as a multi-modal, multi-anatomy, multi-label, long-tailed classification. Our main contributions are three folds: (i), on dataset construction, we build up an academically accessible, large-scale diagnostic dataset that encompasses 5568 disorders linked with 930 unique ICD-10-CM codes, containing 39,026 cases (192,675 scans). (ii), on model design, we present a novel architecture that enables to process arbitrary number of input scans, from various imaging modalities, which is trained with knowledge enhancement to leverage the rich domain knowledge; (iii), on evaluation, we initialize a new benchmark for multi-modal multi-anatomy long-tailed diagnosis. Our method shows superior results on it. Additionally, our final model serves as a pre-trained model, and can be finetuned to benefit diagnosis on various external datasets.
Authors: Rony Abecidan (CRIStAL, CNRS), Vincent Itier (CRIStAL, IMT Nord Europe, CNRS), Jérémie Boulanger (CRIStAL, CNRS), Patrick Bas (CRIStAL, CNRS), Tomáš Pevný (CTU)
Within an operational framework, covers used by a steganographer are likely to come from different sensors and different processing pipelines than the ones used by researchers for training their steganalysis models. Thus, a performance gap is unavoidable when it comes to out-of-distributions covers, an extremely frequent scenario called Cover Source Mismatch (CSM). Here, we explore a grid of processing pipelines to study the origins of CSM, to better understand it, and to better tackle it. A set-covering greedy algorithm is used to select representative pipelines minimizing the maximum regret between the representative and the pipelines within the set. Our main contribution is a methodology for generating relevant bases able to tackle operational CSM. Experimental validation highlights that, for a given number of training samples, our set covering selection is a better strategy than selecting random pipelines or using all the available pipelines. Our analysis also shows that parameters as denoising, sharpening, and downsampling are very important to foster diversity. Finally, different benchmarks for classical and wild databases show the good generalization property of the extracted databases. Additional resources are available at github.com/RonyAbecidan/HolisticSteganalysisWithSetCovering.
Authors: Rachid Aliradi, Abdealmalik Ouamane, Abdeslam Amrane
the paper presents a new method color MS-BSIF learning and MS-LBP for the kinship verification is the machine's ability to identify the genetic and blood the relationship and its degree between the facial images of humans. Facial verification of kinship refers to the task of training a machine to recognize the blood relationship between a pair of faces parent and non-parent (verification) based on features extracted from facial images, and determining the exact type or degree of this genetic relationship. We use the LBP and color BSIF learning features for the comparison and the TXQDA method for dimensionality reduction and data classification. We let's test the kinship facial verification application is namely the kinface Cornell database. This system improves the robustness of learning while controlling efficiency. The experimental results obtained and compared to other methods have proven the reliability of our framework and surpass the performance of other state-of-the-art techniques.