Authors: Zeyu Tang, Xiaodan Xing, Guang Yang
This study aims to develop and evaluate an innovative simulation algorithm for generating thick-slice CT images that closely resemble actual images in the AAPM-Mayo's 2016 Low Dose CT Grand Challenge dataset. The proposed method was evaluated using Peak Signal-to-Noise Ratio (PSNR) and Root Mean Square Error (RMSE) metrics, with the hypothesis that our simulation would produce images more congruent with their real counterparts. Our proposed method demonstrated substantial enhancements in terms of both PSNR and RMSE over other simulation methods. The highest PSNR values were obtained with the proposed method, yielding 49.7369 $\pm$ 2.5223 and 48.5801 $\pm$ 7.3271 for D45 and B30 reconstruction kernels, respectively. The proposed method also registered the lowest RMSE with values of 0.0068 $\pm$ 0.0020 and 0.0108 $\pm$ 0.0099 for D45 and B30, respectively, indicating a distribution more closely aligned with the authentic thick-slice image. Further validation of the proposed simulation algorithm was conducted using the TCIA LDCT-and-Projection-data dataset. The generated images were then leveraged to train four distinct super-resolution (SR) models, which were subsequently evaluated using the real thick-slice images from the 2016 Low Dose CT Grand Challenge dataset. When trained with data produced by our novel algorithm, all four SR models exhibited enhanced performance.
Authors: Jingmeng Li, Hui Wei
Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence. This type of image, which consists of a set of discrete black speckles (speckles), is called an emerging image. Not everyone can find the dog in Dalmatian dog, and among those who can, the time spent varies greatly. Although Gestalt theory summarizes perceptual organization into several principles, it remains ambiguous how these principles affect the perception of emerging images. This study, therefore, designed three psychological experiments to explore the factors that influence the perception of emerging images. In the first, we found that the density of speckles in the local area and the arrangements of some key speckles played a key role in the perception of an emerging case. We set parameters in the algorithm to characterize these two factors. We then automatically generated diversified emerging-test images (ETIs) through the algorithm and verified their effectiveness in two subsequent experiments.
Authors: Max Graf, Mathieu Barthet
Hand tracking is a critical component of natural user interactions in extended reality (XR) environments, including extended reality musical instruments (XRMIs). However, self-occlusion remains a significant challenge for vision-based hand tracking systems, leading to inaccurate results and degraded user experiences. In this paper, we propose a multimodal hand tracking system that combines vision-based hand tracking with surface electromyography (sEMG) data for finger joint angle estimation. We validate the effectiveness of our system through a series of hand pose tasks designed to cover a wide range of gestures, including those prone to self-occlusion. By comparing the performance of our multimodal system to a baseline vision-based tracking method, we demonstrate that our multimodal approach significantly improves tracking accuracy for several finger joints prone to self-occlusion. These findings suggest that our system has the potential to enhance XR experiences by providing more accurate and robust hand tracking, even in the presence of self-occlusion.
Authors: Guanlin Li, Guowen Xu, Tianwei Zhang
In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventional adversarial training on balanced datasets, this process falls into the dilemma of generating uneven adversarial examples (AEs) and an unbalanced feature embedding space, causing the resulting model to exhibit low robustness and accuracy on tail data. To combat that, we propose a new adversarial training framework -- Re-balancing Adversarial Training (REAT). This framework consists of two components: (1) a new training strategy inspired by the term effective number to guide the model to generate more balanced and informative AEs; (2) a carefully constructed penalty function to force a satisfactory feature space. Evaluation results on different datasets and model structures prove that REAT can effectively enhance the model's robustness and preserve the model's clean accuracy. The code can be found in https://github.com/GuanlinLee/REAT.
Authors: Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu
The primal sketch is a fundamental representation in Marr's vision theory, which allows for parsimonious image-level processing from 2D to 2.5D perception. This paper takes a further step by computing 3D primal sketch of wireframes from a set of images with known camera poses, in which we take the 2D wireframes in multi-view images as the basis to compute 3D wireframes in a volumetric rendering formulation. In our method, we first propose a NEural Attraction (NEAT) Fields that parameterizes the 3D line segments with coordinate Multi-Layer Perceptrons (MLPs), enabling us to learn the 3D line segments from 2D observation without incurring any explicit feature correspondences across views. We then present a novel Global Junction Perceiving (GJP) module to perceive meaningful 3D junctions from the NEAT Fields of 3D line segments by optimizing a randomly initialized high-dimensional latent array and a lightweight decoding MLP. Benefitting from our explicit modeling of 3D junctions, we finally compute the primal sketch of 3D wireframes by attracting the queried 3D line segments to the 3D junctions, significantly simplifying the computation paradigm of 3D wireframe parsing. In experiments, we evaluate our approach on the DTU and BlendedMVS datasets with promising performance obtained. As far as we know, our method is the first approach to achieve high-fidelity 3D wireframe parsing without requiring explicit matching.
Authors: Dang Thanh Vu, Vo Hoang Trong, Yu Gwang-Hyun, Kim Jin-Young
This study introduces "shortcut routing," a novel routing mechanism in capsule networks that addresses computational inefficiencies by directly activating global capsules from local capsules, eliminating intermediate layers. An attention-based approach with fuzzy coefficients is also explored for improved efficiency. Experimental results on Mnist, smallnorb, and affNist datasets show comparable classification performance, achieving accuracies of 99.52%, 93.91%, and 89.02% respectively. The proposed fuzzy-based and attention-based routing methods significantly reduce the number of calculations by 1.42 and 2.5 times compared to EM routing, highlighting their computational advantages in capsule networks. These findings contribute to the advancement of efficient and accurate hierarchical pattern representation models.
Authors: Yifei Shi, Junhua Xi, Dewen Hu, Zhiping Cai, Kai Xu
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.
Authors: Shouwei Ruan, Yinpeng Dong, Hang Su, Jianteng Peng, Ning Chen, Xingxing Wei
Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. As most models process images in the perspective view, it is challenging to impose invariance to 3D viewpoint changes based only on 2D inputs. Motivated by the success of adversarial training in promoting model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve viewpoint robustness of common image classifiers. By regarding viewpoint transformation as an attack, VIAT is formulated as a minimax optimization problem, where the inner maximization characterizes diverse adversarial viewpoints by learning a Gaussian mixture distribution based on a new attack GMVFool, while the outer minimization trains a viewpoint-invariant classifier by minimizing the expected loss over the worst-case adversarial viewpoint distributions. To further improve the generalization performance, a distribution sharing strategy is introduced leveraging the transferability of adversarial viewpoints across objects. Experiments validate the effectiveness of VIAT in improving the viewpoint robustness of various image classifiers based on the diversity of adversarial viewpoints generated by GMVFool.
Authors: Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju
Face recognition from image sets acquired under unregulated and uncontrolled settings, such as at large distances, low resolutions, varying viewpoints, illumination, pose, and atmospheric conditions, is challenging. Face feature aggregation, which involves aggregating a set of N feature representations present in a template into a single global representation, plays a pivotal role in such recognition systems. Existing works in traditional face feature aggregation either utilize metadata or high-dimensional intermediate feature representations to estimate feature quality for aggregation. However, generating high-quality metadata or style information is not feasible for extremely low-resolution faces captured in long-range and high altitude settings. To overcome these limitations, we propose a feature distribution conditioning approach called CoNAN for template aggregation. Specifically, our method aims to learn a context vector conditioned over the distribution information of the incoming feature set, which is utilized to weigh the features based on their estimated informativeness. The proposed method produces state-of-the-art results on long-range unconstrained face recognition datasets such as BTS, and DroneSURF, validating the advantages of such an aggregation strategy.
Authors: Subba Reddy Oota, Manish Gupta, Raju S. Bapi, Gael Jobard, Frederic Alexandre, Xavier Hinaut
How does the brain represent different modes of information? Can we design a system that automatically understands what the user is thinking? Such questions can be answered by studying brain recordings like functional magnetic resonance imaging (fMRI). As a first step, the neuroscience community has contributed several large cognitive neuroscience datasets related to passive reading/listening/viewing of concept words, narratives, pictures and movies. Encoding and decoding models using these datasets have also been proposed in the past two decades. These models serve as additional tools for basic research in cognitive science and neuroscience. Encoding models aim at generating fMRI brain representations given a stimulus automatically. They have several practical applications in evaluating and diagnosing neurological conditions and thus also help design therapies for brain damage. Decoding models solve the inverse problem of reconstructing the stimuli given the fMRI. They are useful for designing brain-machine or brain-computer interfaces. Inspired by the effectiveness of deep learning models for natural language processing, computer vision, and speech, recently several neural encoding and decoding models have been proposed. In this survey, we will first discuss popular representations of language, vision and speech stimuli, and present a summary of neuroscience datasets. Further, we will review popular deep learning based encoding and decoding architectures and note their benefits and limitations. Finally, we will conclude with a brief summary and discussion about future trends. Given the large amount of recently published work in the `computational cognitive neuroscience' community, we believe that this survey nicely organizes the plethora of work and presents it as a coherent story.
Authors: Jisong Kim, Minjae Seong, Geonho Bang, Dongsuk Kum, Jun Won Choi
While LiDAR sensors have been succesfully applied to 3D object detection, the affordability of radar and camera sensors has led to a growing interest in fusiong radars and cameras for 3D object detection. However, previous radar-camera fusion models have not been able to fully utilize radar information in that initial 3D proposals were generated based on the camera features only and the instance-level fusion is subsequently conducted. In this paper, we propose radar-camera multi-level fusion (RCM-Fusion), which fuses radar and camera modalities at both the feature-level and instance-level to fully utilize radar information. At the feature-level, we propose a Radar Guided BEV Encoder which utilizes radar Bird's-Eye-View (BEV) features to transform image features into precise BEV representations and then adaptively combines the radar and camera BEV features. At the instance-level, we propose a Radar Grid Point Refinement module that reduces localization error by considering the characteristics of the radar point clouds. The experiments conducted on the public nuScenes dataset demonstrate that our proposed RCM-Fusion offers 11.8% performance gain in nuScenes detection score (NDS) over the camera-only baseline model and achieves state-of-the-art performaces among radar-camera fusion methods in the nuScenes 3D object detection benchmark. Code will be made publicly available.
Authors: Raiyan Rahman, Christopher Indris, Tianxiao Zhang, Kaidong Li, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
Aphid infestations can cause extensive damage to wheat and sorghum fields and spread plant viruses, resulting in significant yield losses in agriculture. To address this issue, farmers often rely on chemical pesticides, which are inefficiently applied over large areas of fields. As a result, a considerable amount of pesticide is wasted on areas without pests, while inadequate amounts are applied to areas with severe infestations. The paper focuses on the urgent need for an intelligent autonomous system that can locate and spray infestations within complex crop canopies, reducing pesticide use and environmental impact. We have collected and labeled a large aphid image dataset in the field, and propose the use of real-time semantic segmentation models to segment clusters of aphids. A multiscale dataset is generated to allow for learning the clusters at different scales. We compare the segmentation speeds and accuracy of four state-of-the-art real-time semantic segmentation models on the aphid cluster dataset, benchmarking them against nonreal-time models. The study results show the effectiveness of a real-time solution, which can reduce inefficient pesticide use and increase crop yields, paving the way towards an autonomous pest detection system.
Authors: Shixiong Zhang, Jiao Li, Lu Yang
Image synthesis has attracted emerging research interests in academic and industry communities. Deep learning technologies especially the generative models greatly inspired controllable image synthesis approaches and applications, which aim to generate particular visual contents with latent prompts. In order to further investigate low-level controllable image synthesis problem which is crucial for fine image rendering and editing tasks, we present a survey of some recent works on 3D controllable image synthesis using deep learning. We first introduce the datasets and evaluation indicators for 3D controllable image synthesis. Then, we review the state-of-the-art research for geometrically controllable image synthesis in two aspects: 1) Viewpoint/pose-controllable image synthesis; 2) Structure/shape-controllable image synthesis. Furthermore, the photometrically controllable image synthesis approaches are also reviewed for 3D re-lighting researches. While the emphasis is on 3D controllable image synthesis algorithms, the related applications, products and resources are also briefly summarized for practitioners.
Authors: Daniel Braun, Rita Borgo, Max Sondag, Tatiana von Landesberger
We introduce two novel visualization designs to support practitioners in performing identification and discrimination tasks on large value ranges (i.e., several orders of magnitude) in time-series data: (1) The order of magnitude horizon graph, which extends the classic horizon graph; and (2) the order of magnitude line chart, which adapts the log-line chart. These new visualization designs visualize large value ranges by explicitly splitting the mantissa m and exponent e of a value v = m * 10e . We evaluate our novel designs against the most relevant state-of-the-art visualizations in an empirical user study. It focuses on four main tasks commonly employed in the analysis of time-series and large value ranges visualization: identification, discrimination, estimation, and trend detection. For each task we analyse error, confidence, and response time. The new order of magnitude horizon graph performs better or equal to all other designs in identification, discrimination, and estimation tasks. Only for trend detection tasks, the more traditional horizon graphs reported better performance. Our results are domain-independent, only requiring time-series data with large value ranges.
Authors: Chaofeng Chen, Wei Liu, Xiao Tan, Kwan-Yee K. Wong
The performance of face photo-sketch translation has improved a lot thanks to deep neural networks. GAN based methods trained on paired images can produce high-quality results under laboratory settings. Such paired datasets are, however, often very small and lack diversity. Meanwhile, Cycle-GANs trained with unpaired photo-sketch datasets suffer from the \emph{steganography} phenomenon, which makes them not effective to face photos in the wild. In this paper, we introduce a semi-supervised approach with a noise-injection strategy, named Semi-Cycle-GAN (SCG), to tackle these problems. For the first problem, we propose a {\em pseudo sketch feature} representation for each input photo composed from a small reference set of photo-sketch pairs, and use the resulting {\em pseudo pairs} to supervise a photo-to-sketch generator $G_{p2s}$. The outputs of $G_{p2s}$ can in turn help to train a sketch-to-photo generator $G_{s2p}$ in a self-supervised manner. This allows us to train $G_{p2s}$ and $G_{s2p}$ using a small reference set of photo-sketch pairs together with a large face photo dataset (without ground-truth sketches). For the second problem, we show that the simple noise-injection strategy works well to alleviate the \emph{steganography} effect in SCG and helps to produce more reasonable sketch-to-photo results with less overfitting than fully supervised approaches. Experiments show that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.
Authors: Matthias Wödlinger, Jan Kotera, Manuel Keglevic, Jan Xu, Robert Sablatnig
In this paper, we present ECSIC, a novel learned method for stereo image compression. Our proposed method compresses the left and right images in a joint manner by exploiting the mutual information between the images of the stereo image pair using a novel stereo cross attention (SCA) module and two stereo context modules. The SCA module performs cross-attention restricted to the corresponding epipolar lines of the two images and processes them in parallel. The stereo context modules improve the entropy estimation of the second encoded image by using the first image as a context. We conduct an extensive ablation study demonstrating the effectiveness of the proposed modules and a comprehensive quantitative and qualitative comparison with existing methods. ECSIC achieves state-of-the-art performance among stereo image compression models on the two popular stereo image datasets Cityscapes and InStereo2k while allowing for fast encoding and decoding, making it highly practical for real-time applications.
Authors: Cesar A. Sierra-Franco, Jan Hurtado, Victor de A. Thomaz, Leonardo C. da Cruz, Santiago V. Silva, Alberto B. Raposo
Mammography images are widely used to detect non-palpable breast lesions or nodules, preventing cancer and providing the opportunity to plan interventions when necessary. The identification of some structures of interest is essential to make a diagnosis and evaluate image adequacy. Thus, computer-aided detection systems can be helpful in assisting medical interpretation by automatically segmenting these landmark structures. In this paper, we propose a deep learning-based framework for the segmentation of the nipple, the pectoral muscle, the fibroglandular tissue, and the fatty tissue on standard-view mammography images. We introduce a large private segmentation dataset and extensive experiments considering different deep-learning model architectures. Our experiments demonstrate accurate segmentation performance on variate and challenging cases, showing that this framework can be integrated into clinical practice.
Authors: Vinayak Gupta, Srikanta Bedathur
Human beings always engage in a vast range of activities and tasks that demonstrate their ability to adapt to different scenarios. Any human activity can be represented as a temporal sequence of actions performed to achieve a certain goal. Unlike the time series datasets extracted from electronics or machines, these action sequences are highly disparate in their nature -- the time to finish a sequence of actions can vary between different persons. Therefore, understanding the dynamics of these sequences is essential for many downstream tasks such as activity length prediction, goal prediction, next action recommendation, etc. Existing neural network-based approaches that learn a continuous-time activity sequence (or CTAS) are limited to the presence of only visual data or are designed specifically for a particular task, i.e., limited to next action or goal prediction. In this paper, we present ProActive, a neural marked temporal point process (MTPP) framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems -- next action prediction, sequence-goal prediction, and end-to-end sequence generation. Specifically, we utilize a self-attention module with temporal normalizing flows to model the influence and the inter-arrival times between actions in a sequence. In addition, we propose a novel addition over the ProActive model that can handle variations in the order of actions, i.e., different methods of achieving a given goal. We demonstrate that this variant can learn the order in which the person or actor prefers to do their actions. Extensive experiments on sequences derived from three activity recognition datasets show the significant accuracy boost of ProActive over the state-of-the-art in terms of action and goal prediction, and the first-ever application of end-to-end action sequence generation.
Authors: Lizhao Liu, Zhuangwei Zhuang, Shangxin Huang, Xunlong Xiao, Tianhang Xiang, Cen Chen, Jingdong Wang, Mingkui Tan
We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with extremely sparse annotated points, it is very difficult to extract both contextual and object information for scene understanding such as semantic segmentation. Motivated by masked modeling (e.g., MAE) in image and video representation learning, we seek to endow the power of masked modeling to learn contextual information from sparsely-annotated points. However, directly applying MAE to 3D point clouds with sparse annotations may fail to work. First, it is nontrivial to effectively mask out the informative visual context from 3D point clouds. Second, how to fully exploit the sparse annotations for context modeling remains an open question. In this paper, we propose a simple yet effective Contextual Point Cloud Modeling (CPCM) method that consists of two parts: a region-wise masking (RegionMask) strategy and a contextual masked training (CMT) method. Specifically, RegionMask masks the point cloud continuously in geometric space to construct a meaningful masked prediction task for subsequent context learning. CMT disentangles the learning of supervised segmentation and unsupervised masked context prediction for effectively learning the very limited labeled points and mass unlabeled points, respectively. Extensive experiments on the widely-tested ScanNet V2 and S3DIS benchmarks demonstrate the superiority of CPCM over the state-of-the-art.
Authors: Ioannis Sarridis, Jochen Spangenberg, Olga Papadopoulou, Symeon Papadopoulos
Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This paper presents a user study, involving 107 participants, predominantly journalists and human rights investigators, that explores the capability of Artificial Intelligence (AI)-based image filters to potentially mitigate the emotional impact of viewing such disturbing content. We tested five different filter styles, both traditional (Blurring and Partial Blurring) and AI-based (Drawing, Colored Drawing, and Painting), and measured their effectiveness in terms of conveying image information while reducing emotional distress. Our findings suggest that the AI-based Drawing style filter demonstrates the best performance, offering a promising solution for reducing negative feelings (-30.38%) while preserving the interpretability of the image (97.19%). Despite the requirement for many professionals to eventually inspect the original images, participants suggested potential strategies for integrating AI filters into their workflow, such as using AI filters as an initial, preparatory step before viewing the original image. Overall, this paper contributes to the development of a more ethically considerate and effective visual environment for professionals routinely engaging with potentially disturbing imagery.
Authors: Thao Nguyen, Samir Yitzhak Gadre, Gabriel Ilharco, Sewoong Oh, Ludwig Schmidt
Massive web datasets play a key role in the success of large vision-language models like CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to reduce noise often come at the expense of data diversity. Our work focuses on caption quality as one major source of noise, and studies how generated captions can increase the utility of web-scraped datapoints with nondescript text. Through exploring different mixing strategies for raw and generated captions, we outperform the best filtering method proposed by the DataComp benchmark by 2% on ImageNet and 4% on average across 38 tasks, given a candidate pool of 128M image-text pairs. Our best approach is also 2x better at Flickr and MS-COCO retrieval. We then analyze what makes synthetic captions an effective source of text supervision. In experimenting with different image captioning models, we also demonstrate that the performance of a model on standard image captioning benchmarks (e.g., NoCaps CIDEr) is not a reliable indicator of the utility of the captions it generates for multimodal training. Finally, our experiments with using generated captions at DataComp's large scale (1.28B image-text pairs) offer insights into the limitations of synthetic text, as well as the importance of image curation with increasing training data quantity.
Authors: Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel
The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos. Webpage: https://diffusion-tokenflow.github.io/
Authors: Rui Wang, Sophokles Ktistakis, Siwei Zhang, Mirko Meboldt, Quentin Lohmeyer
The surgical usage of Mixed Reality (MR) has received growing attention in areas such as surgical navigation systems, skill assessment, and robot-assisted surgeries. For such applications, pose estimation for hand and surgical instruments from an egocentric perspective is a fundamental task and has been studied extensively in the computer vision field in recent years. However, the development of this field has been impeded by a lack of datasets, especially in the surgical field, where bloody gloves and reflective metallic tools make it hard to obtain 3D pose annotations for hands and objects using conventional methods. To address this issue, we propose POV-Surgery, a large-scale, synthetic, egocentric dataset focusing on pose estimation for hands with different surgical gloves and three orthopedic surgical instruments, namely scalpel, friem, and diskplacer. Our dataset consists of 53 sequences and 88,329 frames, featuring high-resolution RGB-D video streams with activity annotations, accurate 3D and 2D annotations for hand-object pose, and 2D hand-object segmentation masks. We fine-tune the current SOTA methods on POV-Surgery and further show the generalizability when applying to real-life cases with surgical gloves and tools by extensive evaluations. The code and the dataset are publicly available at batfacewayne.github.io/POV_Surgery_io/.
Authors: Meike Nauta, Johannes H. Hegeman, Jeroen Geerdink, Jörg Schlötterer, Maurice van Keulen, Christin Seifert
Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated diagnosis support on real-world medical imaging data. PIP-Net learns human-understandable prototypical image parts and we evaluate its accuracy and interpretability for fracture detection and skin cancer diagnosis. We find that PIP-Net's decision making process is in line with medical classification standards, while only provided with image-level class labels. Because of PIP-Net's unsupervised pretraining of prototypes, data quality problems such as undesired text in an X-ray or labelling errors can be easily identified. Additionally, we are the first to show that humans can manually correct the reasoning of PIP-Net by directly disabling undesired prototypes. We conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.
Authors: Ethan Shen, Scotty Singh, Bhavesh Kumar
Multi-modal tasks involving vision and language in deep learning continue to rise in popularity and are leading to the development of newer models that can generalize beyond the extent of their training data. The current models lack temporal generalization which enables models to adapt to changes in future data. This paper discusses a viable approach to creating an advanced Visual Question Answering (VQA) model which can produce successful results on temporal generalization. We propose a new data set, GenVQA, utilizing images and captions from the VQAv2 and MS-COCO dataset to generate new images through stable diffusion. This augmented dataset is then used to test a combination of seven baseline and cutting edge VQA models. Performance evaluation focuses on questions mirroring the original VQAv2 dataset, with the answers having been adjusted to the new images. This paper's purpose is to investigate the robustness of several successful VQA models to assess their performance on future data distributions. Model architectures are analyzed to identify common stylistic choices that improve generalization under temporal distribution shifts. This research highlights the importance of creating a large-scale future shifted dataset. This data can enhance the robustness of VQA models, allowing their future peers to have improved ability to adapt to temporal distribution shifts.
Authors: Shahin Atakishiyev, Mohammad Salameh, Housam Babiker, Randy Goebel
The end-to-end learning ability of self-driving vehicles has achieved significant milestones over the last decade owing to rapid advances in deep learning and computer vision algorithms. However, as autonomous driving technology is a safety-critical application of artificial intelligence (AI), road accidents and established regulatory principles necessitate the need for the explainability of intelligent action choices for self-driving vehicles. To facilitate interpretability of decision-making in autonomous driving, we present a Visual Question Answering (VQA) framework, which explains driving actions with question-answering-based causal reasoning. To do so, we first collect driving videos in a simulation environment using reinforcement learning (RL) and extract consecutive frames from this log data uniformly for five selected action categories. Further, we manually annotate the extracted frames using question-answer pairs as justifications for the actions chosen in each scenario. Finally, we evaluate the correctness of the VQA-predicted answers for actions on unseen driving scenes. The empirical results suggest that the VQA mechanism can provide support to interpret real-time decisions of autonomous vehicles and help enhance overall driving safety.
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 control 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: Chen Li, Xiaoling Hu, Chao Chen
Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this paper, we propose the first confidence estimation method for a semi-supervised setting, when most training labels are unavailable. We stipulate that even with limited training labels, we can still reasonably approximate the confidence of model on unlabeled samples by inspecting the prediction consistency through the training process. We use training consistency as a surrogate function and propose a consistency ranking loss for confidence estimation. On both image classification and segmentation tasks, our method achieves state-of-the-art performances in confidence estimation. Furthermore, we show the benefit of the proposed method through a downstream active learning task. The code is available at https://github.com/TopoXLab/consistency-ranking-loss
Authors: Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott C. Lowe, Jaclyn T.A. McKeown, Chris C.Y. Ho, Joschka McLeod, Yi-Yun C Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel X. Chang, Graham W. Taylor, Paul Fieguth
In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-Insect Dataset. Each record is taxonomically classified by an expert, and also has associated genetic information including raw nucleotide barcode sequences and assigned barcode index numbers, which are genetically-based proxies for species classification. This paper presents a curated million-image dataset, primarily to train computer-vision models capable of providing image-based taxonomic assessment, however, the dataset also presents compelling characteristics, the study of which would be of interest to the broader machine learning community. Driven by the biological nature inherent to the dataset, a characteristic long-tailed class-imbalance distribution is exhibited. Furthermore, taxonomic labelling is a hierarchical classification scheme, presenting a highly fine-grained classification problem at lower levels. Beyond spurring interest in biodiversity research within the machine learning community, progress on creating an image-based taxonomic classifier will also further the ultimate goal of all BIOSCAN research: to lay the foundation for a comprehensive survey of global biodiversity. This paper introduces the dataset and explores the classification task through the implementation and analysis of a baseline classifier.
Authors: Junaid Ahmed Ghauri, Eric Müller-Budack, Ralph Ewerth
Due to the swift growth of patent applications each year, information and multimedia retrieval approaches that facilitate patent exploration and retrieval are of utmost importance. Different types of visualizations (e.g., graphs, technical drawings) and perspectives (e.g., side view, perspective) are used to visualize details of innovations in patents. The classification of these images enables a more efficient search and allows for further analysis. So far, datasets for image type classification miss some important visualization types for patents. Furthermore, related work does not make use of recent deep learning approaches including transformers. In this paper, we adopt state-of-the-art deep learning methods for the classification of visualization types and perspectives in patent images. We extend the CLEF-IP dataset for image type classification in patents to ten classes and provide manual ground truth annotations. In addition, we derive a set of hierarchical classes from a dataset that provides weakly-labeled data for image perspectives. Experimental results have demonstrated the feasibility of the proposed approaches. Source code, models, and dataset will be made publicly available.
Authors: S Suryavardan, Shreyash Mishra, Megha Chakraborty, Parth Patwa, Anku Rani, Aman Chadha, Aishwarya Reganti, Amitava Das, Amit Sheth, Manoj Chinnakotla, Asif Ekbal, Srijan Kumar
With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent. The detrimental impact of fake news emphasizes the need for research focused on automating the detection of false information and verifying its accuracy. In this work, we present the outcome of the Factify 2 shared task, which provides a multi-modal fact verification and satire news dataset, as part of the DeFactify 2 workshop at AAAI'23. The data calls for a comparison based approach to the task by pairing social media claims with supporting documents, with both text and image, divided into 5 classes based on multi-modal relations. In the second iteration of this task we had over 60 participants and 9 final test-set submissions. The best performances came from the use of DeBERTa for text and Swinv2 and CLIP for image. The highest F1 score averaged for all five classes was 81.82%.
Authors: Yize Cheng, Wenbin Hu, Minhao Cheng
Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. However, it was also discovered that DNNs are vulnerable to multiple kinds of attacks, including Backdoor Attacks. Through the attack, the attacker manages to embed a hidden backdoor into the DNN such that the model behaves normally on benign data samples, but makes attacker-specified judgments given the occurrence of a predefined trigger. Although numerous backdoor attacks have been experimented on image classification, backdoor attacks on object detection tasks have not been properly investigated and explored. As object detection has been adopted as an important module in multiple security-sensitive applications such as autonomous driving, backdoor attacks on object detection could pose even more severe threats. Inspired by the inherent property of deep learning-based object detectors, we propose a simple yet effective backdoor attack method against object detection without modifying the ground truth annotations, specifically focusing on the object disappearance attack and object generation attack. Extensive experiments and ablation studies prove the effectiveness of our attack on two benchmark object detection datasets, PASCAL VOC07+12 and MSCOCO, on which we achieve an attack success rate of more than 92% with a poison rate of only 5%.
Authors: James Chapman, Bohan Chen, Zheng Tan, Jeff Calder, Kevin Miller, Andrea L. Bertozzi
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximally improving the underlying classifier's performance. Recent gains have been made using sequential active learning for synthetic aperture radar (SAR) data arXiv:2204.00005. In each iteration, sequential active learning selects a query set of size one while batch active learning selects a query set of multiple datapoints. While batch active learning methods exhibit greater efficiency, the challenge lies in maintaining model accuracy relative to sequential active learning methods. We developed a novel, two-part approach for batch active learning: Dijkstra's Annulus Core-Set (DAC) for core-set generation and LocalMax for batch sampling. The batch active learning process that combines DAC and LocalMax achieves nearly identical accuracy as sequential active learning but is more efficient, proportional to the batch size. As an application, a pipeline is built based on transfer learning feature embedding, graph learning, DAC, and LocalMax to classify the FUSAR-Ship and OpenSARShip datasets. Our pipeline outperforms the state-of-the-art CNN-based methods.
Authors: Guangzhi Wang, Yangyang Guo, Mohan Kankanhalli
Human-Object Interaction Detection is a crucial aspect of human-centric scene understanding, with important applications in various domains. Despite recent progress in this field, recognizing subtle and detailed interactions remains challenging. Existing methods try to use human-related clues to alleviate the difficulty, but rely heavily on external annotations or knowledge, limiting their practical applicability in real-world scenarios. In this work, we propose a novel Part Semantic Network (PSN) to solve this problem. The core of PSN is a Conditional Part Attention (CPA) mechanism, where human features are taken as keys and values, and the object feature is used as query for the computation in a cross-attention mechanism. In this way, our model learns to automatically focus on the most informative human parts conditioned on the involved object, generating more semantically meaningful features for interaction recognition. Additionally, we propose an Occluded Part Extrapolation (OPE) strategy to facilitate interaction recognition under occluded scenarios, which teaches the model to extrapolate detailed features from partially occluded ones. Our method consistently outperforms prior approaches on the V-COCO and HICO-DET datasets, without external data or extra annotations. Additional ablation studies validate the effectiveness of each component of our proposed method.
Authors: Tareq Babaqi, Manar Jaradat, Ayse Erdem Yildirim, Saif H. Al-Nimer, Daehan Won
Eye is the essential sense organ for vision function. Due to the fact that certain eye disorders might result in vision loss, it is essential to diagnose and treat eye diseases early on. By identifying common eye illnesses and performing an eye check, eye care providers can safeguard patients against vision loss or blindness. Convolutional neural networks (CNN) and transfer learning were employed in this study to discriminate between a normal eye and one with diabetic retinopathy, cataract, or glaucoma disease. Using transfer learning for multi-class classification, high accuracy was achieved at 94% while the traditional CNN achieved 84% rate.
Authors: Neha Kalibhat, Shweta Bhardwaj, Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi
We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vision-language model like CLIP. Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts that closely describe the target feature. FALCON also applies contrastive interpretation using lowly activating (counterfactual) images, to eliminate spurious concepts. Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20% of the representation space can be explained by individual features. We show that features in larger spaces become more interpretable when studied in groups and can be explained with high-order scoring concepts through FALCON. We discuss how extracted concepts can be used to explain and debug failures in downstream tasks. Finally, we present a technique to transfer concepts from one (explainable) representation space to another unseen representation space by learning a simple linear transformation.
Authors: Subhashis Suara, Aayush Jha, Pratik Sinha, Arif Ahmed Sekh
Explainable Deep Learning has gained significant attention in the field of artificial intelligence (AI), particularly in domains such as medical imaging, where accurate and interpretable machine learning models are crucial for effective diagnosis and treatment planning. Grad-CAM is a baseline that highlights the most critical regions of an image used in a deep learning model's decision-making process, increasing interpretability and trust in the results. It is applied in many computer vision (CV) tasks such as classification and explanation. This study explores the principles of Explainable Deep Learning and its relevance to medical imaging, discusses various explainability techniques and their limitations, and examines medical imaging applications of Grad-CAM. The findings highlight the potential of Explainable Deep Learning and Grad-CAM in improving the accuracy and interpretability of deep learning models in medical imaging. The code is available in (will be available).
Authors: Minghui Chen, Meirui Jiang, Qi Dou, Zehua Wang, Xiaoxiao Li
Cross-silo federated learning (FL) enables the development of machine learning models on datasets distributed across data centers such as hospitals and clinical research laboratories. However, recent research has found that current FL algorithms face a trade-off between local and global performance when confronted with distribution shifts. Specifically, personalized FL methods have a tendency to overfit to local data, leading to a sharp valley in the local model and inhibiting its ability to generalize to out-of-distribution data. In this paper, we propose a novel federated model soup method (i.e., selective interpolation of model parameters) to optimize the trade-off between local and global performance. Specifically, during the federated training phase, each client maintains its own global model pool by monitoring the performance of the interpolated model between the local and global models. This allows us to alleviate overfitting and seek flat minima, which can significantly improve the model's generalization performance. We evaluate our method on retinal and pathological image classification tasks, and our proposed method achieves significant improvements for out-of-distribution generalization. Our code is available at https://github.com/ubc-tea/FedSoup.
Authors: Josh Myers-Dean, Yifei Fan, Brian Price, Wilson Chan, Danna Gurari
Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation. Our work addresses limitations of existing methods: they either only support one gesture type for marking an image (e.g., either clicks or scribbles) or require knowledge of the gesture type being employed, and require specifying whether marked regions should be included versus excluded in the final segmentation. We instead propose a simplified interactive segmentation task where a user only must mark an image, where the input can be of any gesture type without specifying the gesture type. We support this new task by introducing the first interactive segmentation dataset with multiple gesture types as well as a new evaluation metric capable of holistically evaluating interactive segmentation algorithms. We then analyze numerous interactive segmentation algorithms, including ones adapted for our novel task. While we observe promising performance overall, we also highlight areas for future improvement. To facilitate further extensions of this work, we publicly share our new dataset at https://github.com/joshmyersdean/dig.
Authors: Yuanhao Gong
Training and deploying the large language models requires a large mount of computational resource because the language models contain billions of parameters and the text has thousands of tokens. Another problem is that the large language models are static. They are fixed after the training process. To tackle these issues, in this paper, we propose to train and deploy the dynamic large language model on blockchains, which have high computation performance and are distributed across a network of computers. A blockchain is a secure, decentralized, and transparent system that allows for the creation of a tamper-proof ledger for transactions without the need for intermediaries. The dynamic large language models can continuously learn from the user input after the training process. Our method provides a new way to develop the large language models and also sheds a light on the next generation artificial intelligence systems.
Authors: Peijie Dong, Lujun Li, Zimian Wei, Xin Niu, Zhiliang Tian, Hengyue Pan
Mixed-Precision Quantization~(MQ) can achieve a competitive accuracy-complexity trade-off for models. Conventional training-based search methods require time-consuming candidate training to search optimized per-layer bit-width configurations in MQ. Recently, some training-free approaches have presented various MQ proxies and significantly improve search efficiency. However, the correlation between these proxies and quantization accuracy is poorly understood. To address the gap, we first build the MQ-Bench-101, which involves different bit configurations and quantization results. Then, we observe that the existing training-free proxies perform weak correlations on the MQ-Bench-101. To efficiently seek superior proxies, we develop an automatic search of proxies framework for MQ via evolving algorithms. In particular, we devise an elaborate search space involving the existing proxies and perform an evolution search to discover the best correlated MQ proxy. We proposed a diversity-prompting selection strategy and compatibility screening protocol to avoid premature convergence and improve search efficiency. In this way, our Evolving proxies for Mixed-precision Quantization~(EMQ) framework allows the auto-generation of proxies without heavy tuning and expert knowledge. Extensive experiments on ImageNet with various ResNet and MobileNet families demonstrate that our EMQ obtains superior performance than state-of-the-art mixed-precision methods at a significantly reduced cost. The code will be released.
Authors: Qi Zhang, Sipeng Zheng, Qin Jin
Temporal video grounding (TVG) aims to retrieve the time interval of a language query from an untrimmed video. A significant challenge in TVG is the low "Semantic Noise Ratio (SNR)", which results in worse performance with lower SNR. Prior works have addressed this challenge using sophisticated techniques. In this paper, we propose a no-frills TVG model that consists of two core modules, namely multi-scale neighboring attention and zoom-in boundary detection. The multi-scale neighboring attention restricts each video token to only aggregate visual contexts from its neighbor, enabling the extraction of the most distinguishing information with multi-scale feature hierarchies from high-ratio noises. The zoom-in boundary detection then focuses on local-wise discrimination of the selected top candidates for fine-grained grounding adjustment. With an end-to-end training strategy, our model achieves competitive performance on different TVG benchmarks, while also having the advantage of faster inference speed and lighter model parameters, thanks to its lightweight architecture.
Authors: Yu Qiao, Huy Q. Le, Choong Seon Hong
As a distributed machine learning technique, federated learning (FL) requires clients to collaboratively train a shared model with an edge server without leaking their local data. However, the heterogeneous data distribution among clients often leads to a decrease in model performance. To tackle this issue, this paper introduces a prototype-based regularization strategy to address the heterogeneity in the data distribution. Specifically, the regularization process involves the server aggregating local prototypes from distributed clients to generate a global prototype, which is then sent back to the individual clients to guide their local training. The experimental results on MNIST and Fashion-MNIST show that our proposal achieves improvements of 3.3% and 8.9% in average test accuracy, respectively, compared to the most popular baseline FedAvg. Furthermore, our approach has a fast convergence rate in heterogeneous settings.
Authors: Hugo Latapie, Kristinn R. Thorisson, Shan Yu, Vahagn Petrosyan, Patrick Hammer, Pei Wang, Brandon Kynoch, Hanning Chen, Tangrui Li
Traditional computer vision models often require extensive manual effort for data acquisition and validation, particularly when detecting subtle behavioral nuances or events. The difficulty in distinguishing routine behaviors from potential risks in real-world applications, like differentiating routine shopping from potential shoplifting, further complicates the process.
We present Ethosight, a novel zero-shot computer vision algorithm. Ethosight eradicates the need for pre-existing symbolic knowledge, initiating from a clean slate based on user requirements and semantic knowledge of interest. Using localized label affinity calculations and a reasoning-guided iterative learning loop, Ethosight infers scene details and iteratively refines the label set. Reasoning mechanisms can be derived from large language models like GPT4, symbolic reasoners like OpenNARS, or hybrid systems.
Ethosight further capitalizes on the capabilities of a pre-trained multi-modal model, ImageBind, generating accurate semantic knowledge of images within a few cycles. It successfully captures both explicit and nuanced elements efficiently. We also introduce the implementation of Korzybski's "time-binding" concept in machines, which allows for generational learning and knowledge sharing across deployments.
Our evaluations demonstrate Ethosight's efficacy across 40 complex use cases. It has exhibited an exceptional ability to discern new areas of interest, consistently generating high-affinity scores within the top five labels from a set of a thousand. Tests conducted across diverse environments attest to Ethosight's robust performance. Detailed results and case studies within the main body of this paper and an appendix underscore a promising trajectory towards enhancing the adaptability and resilience of computer vision models in detecting and extracting subtle and nuanced behaviors.
Authors: Dejia Xu, Xingqian Xu, Wenyan Cong, Humphrey Shi, Zhangyang Wang
Have you ever imagined how it would look if we placed new objects into paintings? For example, what would it look like if we placed a basketball into Claude Monet's ``Water Lilies, Evening Effect''? We propose Reference-based Painterly Inpainting, a novel task that crosses the wild reference domain gap and implants novel objects into artworks. Although previous works have examined reference-based inpainting, they are not designed for large domain discrepancies between the target and the reference, such as inpainting an artistic image using a photorealistic reference. This paper proposes a novel diffusion framework, dubbed RefPaint, to ``inpaint more wildly'' by taking such references with large domain gaps. Built with an image-conditioned diffusion model, we introduce a ladder-side branch and a masked fusion mechanism to work with the inpainting mask. By decomposing the CLIP image embeddings at inference time, one can manipulate the strength of semantic and style information with ease. Experiments demonstrate that our proposed RefPaint framework produces significantly better results than existing methods. Our method enables creative painterly image inpainting with reference objects that would otherwise be difficult to achieve. Project page: https://vita-group.github.io/RefPaint/
Authors: Ziwei Wang, Timothy Molloy, Pieter van Goor, Robert Mahony
Event-based cameras have become increasingly popular for tracking fast-moving objects due to their high temporal resolution, low latency, and high dynamic range. In this paper, we propose a novel algorithm for tracking event blobs using raw events asynchronously in real time. We introduce the concept of an event blob as a spatio-temporal likelihood of event occurrence where the conditional spatial likelihood is blob-like. Many real-world objects generate event blob data, for example, flickering LEDs such as car headlights or any small foreground object moving against a static or slowly varying background. The proposed algorithm uses a nearest neighbour classifier with a dynamic threshold criteria for data association coupled with a Kalman filter to track the event blob state. Our algorithm achieves highly accurate tracking and event blob shape estimation even under challenging lighting conditions and high-speed motions. The microsecond time resolution achieved means that the filter output can be used to derive secondary information such as time-to-contact or range estimation, that will enable applications to real-world problems such as collision avoidance in autonomous driving.
Authors: Dongyun Lin, Yi Cheng, Aiyuan Guo, Shangbo Mao, Yiqun Li
To address 3D object retrieval, substantial efforts have been made to generate highly discriminative descriptors of 3D objects represented by a single modality, e.g., voxels, point clouds or multi-view images. It is promising to leverage the complementary information from multi-modality representations of 3D objects to further improve retrieval performance. However, multi-modality 3D object retrieval is rarely developed and analyzed on large-scale datasets. In this paper, we propose self-and-cross attention based aggregation of point cloud and multi-view images (SCA-PVNet) for 3D object retrieval. With deep features extracted from point clouds and multi-view images, we design two types of feature aggregation modules, namely the In-Modality Aggregation Module (IMAM) and the Cross-Modality Aggregation Module (CMAM), for effective feature fusion. IMAM leverages a self-attention mechanism to aggregate multi-view features while CMAM exploits a cross-attention mechanism to interact point cloud features with multi-view features. The final descriptor of a 3D object for object retrieval can be obtained via concatenating the aggregated features from both modules. Extensive experiments and analysis are conducted on three datasets, ranging from small to large scale, to show the superiority of the proposed SCA-PVNet over the state-of-the-art methods.
Authors: Ajay Jaiswal, Xingguang Zhang, Stanley H. Chan, Zhangyang Wang
Image distortion by atmospheric turbulence is a stochastic degradation, which is a critical problem in long-range optical imaging systems. A number of research has been conducted during the past decades, including model-based and emerging deep-learning solutions with the help of synthetic data. Although fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions recently, the training of such models only relies on the synthetic data and ground truth pairs. This paper proposes the Physics-integrated Restoration Network (PiRN) to bring the physics-based simulator directly into the training process to help the network to disentangle the stochasticity from the degradation and the underlying image. Furthermore, to overcome the ``average effect" introduced by deterministic models and the domain gap between the synthetic and real-world degradation, we further introduce PiRN with Stochastic Refinement (PiRN-SR) to boost its perceptual quality. Overall, our PiRN and PiRN-SR improve the generalization to real-world unknown turbulence conditions and provide a state-of-the-art restoration in both pixel-wise accuracy and perceptual quality. Our codes are available at \url{https://github.com/VITA-Group/PiRN}.
Authors: Weihang Ran, Wei Yuan, Xiaodan Shi, Zipei Fan, Ryosuke Shibasaki
Building outline extracted from high-resolution aerial images can be used in various application fields such as change detection and disaster assessment. However, traditional CNN model cannot recognize contours very precisely from original images. In this paper, we proposed a CNN and Transformer based model together with active contour model to deal with this problem. We also designed a triple-branch decoder structure to handle different features generated by encoder. Experiment results show that our model outperforms other baseline model on two datasets, achieving 91.1% mIoU on Vaihingen and 83.8% on Bing huts.
Authors: Mang Ye, Xiuwen Fang, Bo Du, Pong C. Yuen, Dacheng Tao
Federated learning (FL) has drawn increasing attention owing to its potential use in large-scale industrial applications. Existing federated learning works mainly focus on model homogeneous settings. However, practical federated learning typically faces the heterogeneity of data distributions, model architectures, network environments, and hardware devices among participant clients. Heterogeneous Federated Learning (HFL) is much more challenging, and corresponding solutions are diverse and complex. Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential. In this survey, we firstly summarize the various research challenges in HFL from five aspects: statistical heterogeneity, model heterogeneity, communication heterogeneity, device heterogeneity, and additional challenges. In addition, recent advances in HFL are reviewed and a new taxonomy of existing HFL methods is proposed with an in-depth analysis of their pros and cons. We classify existing methods from three different levels according to the HFL procedure: data-level, model-level, and server-level. Finally, several critical and promising future research directions in HFL are discussed, which may facilitate further developments in this field. A periodically updated collection on HFL is available at https://github.com/marswhu/HFL_Survey.
Authors: Jifei Miao, Kit Ian Kou
In recent years, tensor networks have emerged as powerful tools for solving large-scale optimization problems. One of the most promising tensor networks is the tensor ring (TR) decomposition, which achieves circular dimensional permutation invariance in the model through the utilization of the trace operation and equitable treatment of the latent cores. On the other hand, more recently, quaternions have gained significant attention and have been widely utilized in color image processing tasks due to their effectiveness in encoding color pixels. Therefore, in this paper, we propose the quaternion tensor ring (QTR) decomposition, which inherits the powerful and generalized representation abilities of the TR decomposition while leveraging the advantages of quaternions for color pixel representation. In addition to providing the definition of QTR decomposition and an algorithm for learning the QTR format, this paper also proposes a low-rank quaternion tensor completion (LRQTC) model and its algorithm for color image inpainting based on the QTR decomposition. Finally, extensive experiments on color image inpainting demonstrate that the proposed QTLRC method is highly competitive.
Authors: Kun Li, Dan Guo, Guoliang Chen, Xinge Peng, Meng Wang
In this paper, we briefly introduce the solution of our team HFUT-VUT for the Micros-gesture Classification in the MiGA challenge at IJCAI 2023. The micro-gesture classification task aims at recognizing the action category of a given video based on the skeleton data. For this task, we propose a 3D-CNNs-based micro-gesture recognition network, which incorporates a skeletal and semantic embedding loss to improve action classification performance. Finally, we rank 1st in the Micro-gesture Classification Challenge, surpassing the second-place team in terms of Top-1 accuracy by 1.10%.
Authors: Suncheng Xiang, Cang Liu, Sijia Du, Dahong Qian
Colonoscopic Polyp Re-Identification aims to match a specific polyp in a large gallery with different cameras and views, which plays a key role for the prevention and treatment of colorectal cancer in the computer-aided diagnosis. However, traditional methods mainly focus on the visual representation learning, while neglect to explore the potential of semantic features during training, which may easily leads to poor generalization capability when adapted the pretrained model into the new scenarios. To relieve this dilemma, we propose a simple but effective training method named VT-ReID, which can remarkably enrich the representation of polyp videos with the interchange of high-level semantic information. Moreover, we elaborately design a novel clustering mechanism to introduce prior knowledge from textual data, which leverages contrastive learning to promote better separation from abundant unlabeled text data. To the best of our knowledge, this is the first attempt to employ the visual-text feature with clustering mechanism for the colonoscopic polyp re-identification. Empirical results show that our method significantly outperforms current state-of-the art methods with a clear margin.
Authors: Mathuran Kandeepan (ALSOC), Clara Ciocan (ALSOC), Adrien Cassagne (ALSOC), Lionel Lacassagne (ALSOC)
This article presents the methods used to parallelize a new computer vision application. The system is able to automatically detect meteor from non-stabilized cameras and noisy video sequences. The application is designed to be embedded in weather balloons or for airborne observation campaigns. Thus, the final target is a low power system-on-chip (< 10 Watts) while the software needs to compute a stream of frames in real-time (> 25 frames per second). For this, first the application is split in a tasks graph, then different parallelization techniques are applied. Experiment results demonstrate the efficiency of the parallelization methods. For instance, on the Raspberry Pi 4 and on a HD video sequence, the processing chain reaches 42 frames per second while it only consumes 6 Watts.
Authors: Mohan Zhou, Yalong Bai, Wei Zhang, Ting Yao, Tiejun Zhao, Tao Mei
A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis method development. Existing quantitative evaluations often fail to capture the full complexity of human preference, as they only consider limited evaluation dimensions. Qualitative evaluations and user studies offer a solution but are time-consuming and labor-intensive. This limitation hinders the advancement of conversational head generation algorithms and systems. In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions. PS can serve as a quantitative evaluation without the need for human annotation. Experimental results validate the superiority of Preference Score in aligning with human perception, and also demonstrates robustness and generalizability to unseen data, making it a valuable tool for advancing conversation head generation. We expect this metric could facilitate new advances in conversational head generation.
Authors: Ke Zhu, Yin-Yin He, Jianxin Wu
Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often conceptually complicated. This paper proposes a novel and highly effective QAT method, quantized feature distillation (QFD). QFD first trains a quantized (or binarized) representation as the teacher, then quantize the network using knowledge distillation (KD). Quantitative results show that QFD is more flexible and effective (i.e., quantization friendly) than previous quantization methods. QFD surpasses existing methods by a noticeable margin on not only image classification but also object detection, albeit being much simpler. Furthermore, QFD quantizes ViT and Swin-Transformer on MS-COCO detection and segmentation, which verifies its potential in real world deployment. To the best of our knowledge, this is the first time that vision transformers have been quantized in object detection and image segmentation tasks.
Authors: Qichao Ying, Jiaxin Liu, Sheng Li, Haisheng Xu, Zhenxing Qian, Xinpeng Zhang
The widespread use of face retouching filters on short-video platforms has raised concerns about the authenticity of digital appearances and the impact of deceptive advertising. To address these issues, there is a pressing need to develop advanced face retouching techniques. However, the lack of large-scale and fine-grained face retouching datasets has been a major obstacle to progress in this field. In this paper, we introduce RetouchingFFHQ, a large-scale and fine-grained face retouching dataset that contains over half a million conditionally-retouched images. RetouchingFFHQ stands out from previous datasets due to its large scale, high quality, fine-grainedness, and customization. By including four typical types of face retouching operations and different retouching levels, we extend the binary face retouching detection into a fine-grained, multi-retouching type, and multi-retouching level estimation problem. Additionally, we propose a Multi-granularity Attention Module (MAM) as a plugin for CNN backbones for enhanced cross-scale representation learning. Extensive experiments using different baselines as well as our proposed method on RetouchingFFHQ show decent performance on face retouching detection. With the proposed new dataset, we believe there is great potential for future work to tackle the challenging problem of real-world fine-grained face retouching detection.
Authors: Haoyuan Wang, Xiaogang Xu, Ke Xu, Rynson WH. Lau
Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene. However, images photographed from a low-light scene can hardly be used to train a NeRF model to produce high-quality results, due to their low pixel intensities, heavy noise, and color distortion. Combining existing low-light image enhancement methods with NeRF methods also does not work well due to the view inconsistency caused by the individual 2D enhancement process. In this paper, we propose a novel approach, called Low-Light NeRF (or LLNeRF), to enhance the scene representation and synthesize normal-light novel views directly from sRGB low-light images in an unsupervised manner. The core of our approach is a decomposition of radiance field learning, which allows us to enhance the illumination, reduce noise and correct the distorted colors jointly with the NeRF optimization process. Our method is able to produce novel view images with proper lighting and vivid colors and details, given a collection of camera-finished low dynamic range (8-bits/channel) images from a low-light scene. Experiments demonstrate that our method outperforms existing low-light enhancement methods and NeRF methods.
Authors: Haechang Lee, Dongwon Park, Wongi Jeong, Kijeong Kim, Hyunwoo Je, Dongil Ryu, Se Young Chun
As the physical size of recent CMOS image sensors (CIS) gets smaller, the latest mobile cameras are adopting unique non-Bayer color filter array (CFA) patterns (e.g., Quad, Nona, QxQ), which consist of homogeneous color units with adjacent pixels. These non-Bayer sensors are superior to conventional Bayer CFA thanks to their changeable pixel-bin sizes for different light conditions but may introduce visual artifacts during demosaicing due to their inherent pixel pattern structures and sensor hardware characteristics. Previous demosaicing methods have primarily focused on Bayer CFA, necessitating distinct reconstruction methods for non-Bayer patterned CIS with various CFA modes under different lighting conditions. In this work, we propose an efficient unified demosaicing method that can be applied to both conventional Bayer RAW and various non-Bayer CFAs' RAW data in different operation modes. Our Knowledge Learning-based demosaicing model for Adaptive Patterns, namely KLAP, utilizes CFA-adaptive filters for only 1% key filters in the network for each CFA, but still manages to effectively demosaic all the CFAs, yielding comparable performance to the large-scale models. Furthermore, by employing meta-learning during inference (KLAP-M), our model is able to eliminate unknown sensor-generic artifacts in real RAW data, effectively bridging the gap between synthetic images and real sensor RAW. Our KLAP and KLAP-M methods achieved state-of-the-art demosaicing performance in both synthetic and real RAW data of Bayer and non-Bayer CFAs.
Authors: Rebecca Leygonie (LIPADE), Sylvain Lobry (LIPADE)), Laurent Wendling (LIPADE)
We wish to define the limits of a classical classification model based on deep learning when applied to abstract images, which do not represent visually identifiable objects.QR codes (Quick Response codes) fall into this category of abstract images: one bit corresponding to one encoded character, QR codes were not designed to be decoded manually. To understand the limitations of a deep learning-based model for abstract image classification, we train an image classification model on QR codes generated from information obtained when reading a health pass. We compare a classification model with a classical (deterministic) decoding method in the presence of noise. This study allows us to conclude that a model based on deep learning can be relevant for the understanding of abstract images.
Authors: Yinghui Xing, Dexuan Kong, Shizhou Zhang, Geng Chen, Lingyan Ran, Peng Wang, Yanning Zhang
Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify camouflaged objects with complete and fine details, while the boundary can not be well located for the lack of object-related semantics. In this paper, we propose a novel ``pre-train, adapt and detect" paradigm to detect camouflaged objects. By introducing a large pre-trained model, abundant knowledge learned from massive multi-modal data can be directly transferred to COD. A lightweight parallel adapter is inserted to adjust the features suitable for the downstream COD task. Extensive experiments on four challenging benchmark datasets demonstrate that our method outperforms existing state-of-the-art COD models by large margins. Moreover, we design a multi-task learning scheme for tuning the adapter to exploit the shareable knowledge across different semantic classes. Comprehensive experimental results showed that the generalization ability of our model can be substantially improved with multi-task adapter initialization on source tasks and multi-task adaptation on target tasks.
Authors: Jaekyun Ko, Sanghwan Lee
Recently, denoising methods based on supervised learning have exhibited promising performance. However, their reliance on external datasets containing noisy-clean image pairs restricts their applicability. To address this limitation, researchers have focused on training denoising networks using solely a set of noisy inputs. To improve the feasibility of denoising procedures, in this study, we proposed a single-image self-supervised learning method in which only the noisy input image is used for network training. Gated convolution was used for feature extraction and no-reference image quality assessment was used for guiding the training process. Moreover, the proposed method sampled instances from the input image dataset using Bernoulli sampling with a certain dropout rate for training. The corresponding result was produced by averaging the generated predictions from various instances of the trained network with dropouts. The experimental results indicated that the proposed method achieved state-of-the-art denoising performance on both synthetic and real-world datasets. This highlights the effectiveness and practicality of our method as a potential solution for various noise removal tasks.
Authors: Zhimiao Yu, Tiancheng Lin, Yi Xu
Improving the feature representation ability is the foundation of many whole slide pathological image (WSIs) tasks. Recent works have achieved great success in pathological-specific self-supervised learning (SSL). However, most of them only focus on learning patch-level representations, thus there is still a gap between pretext and slide-level downstream tasks, e.g., subtyping, grading and staging. Aiming towards slide-level representations, we propose Slide-Level Prototypical Distillation (SLPD) to explore intra- and inter-slide semantic structures for context modeling on WSIs. Specifically, we iteratively perform intra-slide clustering for the regions (4096x4096 patches) within each WSI to yield the prototypes and encourage the region representations to be closer to the assigned prototypes. By representing each slide with its prototypes, we further select similar slides by the set distance of prototypes and assign the regions by cross-slide prototypes for distillation. SLPD achieves state-of-the-art results on multiple slide-level benchmarks and demonstrates that representation learning of semantic structures of slides can make a suitable proxy task for WSI analysis. Code will be available at https://github.com/Carboxy/SLPD.
Authors: Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio, Josef Bigun
The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method for verifying users due to the prevalence of cameras in mobile devices and their integration into everyday applications. The rapid advancement of deep Convolutional Neural Networks (CNNs) has led to numerous face verification architectures. However, these models are often large and impractical for mobile applications, reaching sizes of hundreds of megabytes with millions of parameters. We address this issue by developing SqueezerFaceNet, a light face recognition network which less than 1M parameters. This is achieved by applying a network pruning method based on Taylor scores, where filters with small importance scores are removed iteratively. Starting from an already small network (of 1.24M) based on SqueezeNet, we show that it can be further reduced (up to 40%) without an appreciable loss in performance. To the best of our knowledge, we are the first to evaluate network pruning methods for the task of face recognition.
Authors: Sahar Almahfouz Nasser, Nihar Gupte, Amit Sethi
Retinal image matching plays a crucial role in monitoring disease progression and treatment response. However, datasets with matched keypoints between temporally separated pairs of images are not available in abundance to train transformer-based model. We propose a novel approach based on reverse knowledge distillation to train large models with limited data while preventing overfitting. Firstly, we propose architectural modifications to a CNN-based semi-supervised method called SuperRetina that help us improve its results on a publicly available dataset. Then, we train a computationally heavier model based on a vision transformer encoder using the lighter CNN-based model, which is counter-intuitive in the field knowledge-distillation research where training lighter models based on heavier ones is the norm. Surprisingly, such reverse knowledge distillation improves generalization even further. Our experiments suggest that high-dimensional fitting in representation space may prevent overfitting unlike training directly to match the final output. We also provide a public dataset with annotations for retinal image keypoint detection and matching to help the research community develop algorithms for retinal image applications.
Authors: Quang Huy Che, Dinh Phuc Nguyen, Minh Quan Pham, Duc Khai Lam
Semantic segmentation is a common task in autonomous driving to understand the surrounding environment. Driveable Area Segmentation and Lane Detection are particularly important for safe and efficient navigation on the road. However, original semantic segmentation models are computationally expensive and require high-end hardware, which is not feasible for embedded systems in autonomous vehicles. This paper proposes a lightweight model for the driveable area and lane line segmentation. TwinLiteNet is designed cheaply but achieves accurate and efficient segmentation results. We evaluate TwinLiteNet on the BDD100K dataset and compare it with modern models. Experimental results show that our TwinLiteNet performs similarly to existing approaches, requiring significantly fewer computational resources. Specifically, TwinLiteNet achieves a mIoU score of 91.3% for the Drivable Area task and 31.08% IoU for the Lane Detection task with only 0.4 million parameters and achieves 415 FPS on GPU RTX A5000. Furthermore, TwinLiteNet can run in real-time on embedded devices with limited computing power, especially since it achieves 60FPS on Jetson Xavier NX, making it an ideal solution for self-driving vehicles. Code is available: url{https://github.com/chequanghuy/TwinLiteNet}.
Authors: Jiachun Pan, Hanshu Yan, Jun Hao Liew, Vincent Y. F. Tan, Jiashi Feng
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims to address the challenge of DPM customization when the only available supervision is a differentiable metric defined on the generated contents. Since the sampling procedure of DPMs involves recursive calls to the denoising UNet, na\"ive gradient backpropagation requires storing the intermediate states of all iterations, resulting in extremely high memory consumption. To overcome this issue, we propose a novel method AdjointDPM, which first generates new samples from diffusion models by solving the corresponding probability-flow ODEs. It then uses the adjoint sensitivity method to backpropagate the gradients of the loss to the models' parameters (including conditioning signals, network weights, and initial noises) by solving another augmented ODE. To reduce numerical errors in both the forward generation and gradient backpropagation processes, we further reparameterize the probability-flow ODE and augmented ODE as simple non-stiff ODEs using exponential integration. Finally, we demonstrate the effectiveness of AdjointDPM on three interesting tasks: converting visual effects into identification text embeddings, finetuning DPMs for specific types of stylization, and optimizing initial noise to generate adversarial samples for security auditing.
Authors: Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden
Self-supervised monocular depth estimation (SS-MDE) has the potential to scale to vast quantities of data. Unfortunately, existing approaches limit themselves to the automotive domain, resulting in models incapable of generalizing to complex environments such as natural or indoor settings.
To address this, we propose a large-scale SlowTV dataset curated from YouTube, containing an order of magnitude more data than existing automotive datasets. SlowTV contains 1.7M images from a rich diversity of environments, such as worldwide seasonal hiking, scenic driving and scuba diving. Using this dataset, we train an SS-MDE model that provides zero-shot generalization to a large collection of indoor/outdoor datasets. The resulting model outperforms all existing SSL approaches and closes the gap on supervised SoTA, despite using a more efficient architecture.
We additionally introduce a collection of best-practices to further maximize performance and zero-shot generalization. This includes 1) aspect ratio augmentation, 2) camera intrinsic estimation, 3) support frame randomization and 4) flexible motion estimation. Code is available at https://github.com/jspenmar/slowtv_monodepth.
Authors: Md Abdul Kadir, Hasan Md Tusfiqur Alam, Daniel Sonntag
Active learning algorithms have become increasingly popular for training models with limited data. However, selecting data for annotation remains a challenging problem due to the limited information available on unseen data. To address this issue, we propose EdgeAL, which utilizes the edge information of unseen images as {\it a priori} information for measuring uncertainty. The uncertainty is quantified by analyzing the divergence and entropy in model predictions across edges. This measure is then used to select superpixels for annotation. We demonstrate the effectiveness of EdgeAL on multi-class Optical Coherence Tomography (OCT) segmentation tasks, where we achieved a 99% dice score while reducing the annotation label cost to 12%, 2.3%, and 3%, respectively, on three publicly available datasets (Duke, AROI, and UMN). The source code is available at \url{https://github.com/Mak-Ta-Reque/EdgeAL}
Authors: Tianlei Wang, Dekang Liu, Wandong Zhang, Jiuwen Cao
One-class classification (OCC) aims to train a classifier only with the target class data and attracts great attention for its strong applicability in real-world application. Despite a lot of advances have been made in OCC, it still lacks the effective OCC loss functions for deep learning. In this paper, a novel logarithmic barrier function based OCC loss (LBL) that assigns large gradients to the margin samples and thus derives more compact hypersphere, is first proposed by approximating the OCC objective smoothly. But the optimization of LBL may be instability especially when samples lie on the boundary leading to the infinity loss. To address this issue, then, a unilateral relaxation Sigmoid function is introduced into LBL and a novel OCC loss named LBLSig is proposed. The LBLSig can be seen as the fusion of the mean square error (MSE) and the cross entropy (CE) and the optimization of LBLSig is smoother owing to the unilateral relaxation Sigmoid function. The effectiveness of the proposed LBL and LBLSig is experimentally demonstrated in comparisons with several state-of-the-art OCC algorithms on different network structures. The source code can be found at https://github.com/ML-HDU/LBL_LBLSig.
Authors: Anindya Mondal, Sauradip Nag, Joaquin M Prada, Xiatian Zhu, Anjan Dutta
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome model design complexity and high maintenance costs. Moreover, they often focus on learning the visual modality alone and single-label classification whilst neglecting other available information sources (e.g., class name text) and the concurrent occurrence of multiple actions. To overcome these limitations, we propose a new approach called 'actor-agnostic multi-modal multi-label action recognition,' which offers a unified solution for various types of actors, including humans and animals. We further formulate a novel Multi-modal Semantic Query Network (MSQNet) model in a transformer-based object detection framework (e.g., DETR), characterized by leveraging visual and textual modalities to represent the action classes better. The elimination of actor-specific model designs is a key advantage, as it removes the need for actor pose estimation altogether. Extensive experiments on five publicly available benchmarks show that our MSQNet consistently outperforms the prior arts of actor-specific alternatives on human and animal single- and multi-label action recognition tasks by up to 50%. Code will be released at https://github.com/mondalanindya/MSQNet.
Authors: Ankur Sikarwar, Mengmi Zhang
Working memory (WM), a fundamental cognitive process facilitating the temporary storage, integration, manipulation, and retrieval of information, plays a vital role in reasoning and decision-making tasks. Robust benchmark datasets that capture the multifaceted nature of WM are crucial for the effective development and evaluation of AI WM models. Here, we introduce a comprehensive Working Memory (WorM) benchmark dataset for this purpose. WorM comprises 10 tasks and a total of 1 million trials, assessing 4 functionalities, 3 domains, and 11 behavioral and neural characteristics of WM. We jointly trained and tested state-of-the-art recurrent neural networks and transformers on all these tasks. We also include human behavioral benchmarks as an upper bound for comparison. Our results suggest that AI models replicate some characteristics of WM in the brain, most notably primacy and recency effects, and neural clusters and correlates specialized for different domains and functionalities of WM. In the experiments, we also reveal some limitations in existing models to approximate human behavior. This dataset serves as a valuable resource for communities in cognitive psychology, neuroscience, and AI, offering a standardized framework to compare and enhance WM models, investigate WM's neural underpinnings, and develop WM models with human-like capabilities. Our source code and data are available at https://github.com/ZhangLab-DeepNeuroCogLab/WorM.
Authors: Fan Lu, Yan Xu, Guang Chen, Hongsheng Li, Kwan-Yee Lin, Changjun Jiang
Neural Radiance Fields (NeRFs) have achieved great success in the past few years. However, most current methods still require intensive resources due to ray marching-based rendering. To construct urban-level radiance fields efficiently, we design Deformable Neural Mesh Primitive~(DNMP), and propose to parameterize the entire scene with such primitives. The DNMP is a flexible and compact neural variant of classic mesh representation, which enjoys both the efficiency of rasterization-based rendering and the powerful neural representation capability for photo-realistic image synthesis. Specifically, a DNMP consists of a set of connected deformable mesh vertices with paired vertex features to parameterize the geometry and radiance information of a local area. To constrain the degree of freedom for optimization and lower the storage budgets, we enforce the shape of each primitive to be decoded from a relatively low-dimensional latent space. The rendering colors are decoded from the vertex features (interpolated with rasterization) by a view-dependent MLP. The DNMP provides a new paradigm for urban-level scene representation with appealing properties: $(1)$ High-quality rendering. Our method achieves leading performance for novel view synthesis in urban scenarios. $(2)$ Low computational costs. Our representation enables fast rendering (2.07ms/1k pixels) and low peak memory usage (110MB/1k pixels). We also present a lightweight version that can run 33$\times$ faster than vanilla NeRFs, and comparable to the highly-optimized Instant-NGP (0.61 vs 0.71ms/1k pixels). Project page: \href{https://dnmp.github.io/}{https://dnmp.github.io/}.
Authors: Maxim Bonnaerens, Joni Dambre
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the complexity of transformer models is quadratic with respect to the number of input tokens. Therefore techniques that reduce the number of input tokens that need to be processed have been proposed. This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. LTMP uses learned threshold masking modules that dynamically determine which tokens to merge and which to prune. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task. Our results demonstrate that LTMP achieves state-of-the-art accuracy across reduction rates while requiring only a single fine-tuning epoch, which is an order of magnitude faster than previous methods. Code is available at https://github.com/Mxbonn/ltmp .
Authors: Yuhang Lu, Qi Jiang, Runnan Chen, Yuenan Hou, Xinge Zhu, Yuexin Ma
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels to unseen classes without labels. They typically align visual features with semantic features obtained from word embedding by the supervision of seen classes' annotations. However, point cloud contains limited information to fully match with semantic features. In fact, the rich appearance information of images is a natural complement to the textureless point cloud, which is not well explored in previous literature. Motivated by this, we propose a novel multi-modal zero-shot learning method to better utilize the complementary information of point clouds and images for more accurate visual-semantic alignment. Extensive experiments are performed in two popular benchmarks, i.e., SemanticKITTI and nuScenes, and our method outperforms current SOTA methods with 52% and 49% improvement on average for unseen class mIoU, respectively.
Authors: Jianan Liu, Qiuchi Zhao, Weiyi Xiong, Tao Huang, Qing-Long Han, Bing Zhu
The 4D Millimeter wave (mmWave) radar is a promising technology for vehicle sensing due to its cost-effectiveness and operability in adverse weather conditions. However, the adoption of this technology has been hindered by sparsity and noise issues in radar point cloud data. This paper introduces spatial multi-representation fusion (SMURF), a novel approach to 3D object detection using a single 4D imaging radar. SMURF leverages multiple representations of radar detection points, including pillarization and density features of a multi-dimensional Gaussian mixture distribution through kernel density estimation (KDE). KDE effectively mitigates measurement inaccuracy caused by limited angular resolution and multi-path propagation of radar signals. Additionally, KDE helps alleviate point cloud sparsity by capturing density features. Experimental evaluations on View-of-Delft (VoD) and TJ4DRadSet datasets demonstrate the effectiveness and generalization ability of SMURF, outperforming recently proposed 4D imaging radar-based single-representation models. Moreover, while using 4D imaging radar only, SMURF still achieves comparable performance to the state-of-the-art 4D imaging radar and camera fusion-based method, with an increase of 1.22% in the mean average precision on bird's-eye view of TJ4DRadSet dataset and 1.32% in the 3D mean average precision on the entire annotated area of VoD dataset. Our proposed method demonstrates impressive inference time and addresses the challenges of real-time detection, with the inference time no more than 0.05 seconds for most scans on both datasets. This research highlights the benefits of 4D mmWave radar and is a strong benchmark for subsequent works regarding 3D object detection with 4D imaging radar.
Authors: Ondrej Bohdal, Da Li, Timothy Hospedales
Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data. However, the adaptation process still takes a considerable amount of time and is predominantly based on optimization that relies on back-propagation. In this work we present a simple feed-forward approach that challenges the need for back-propagation based adaptation. Our approach is based on computing prototypes of classes under the domain shift using a pre-trained model. It achieves strong improvements in accuracy compared to the pre-trained model and requires only a small fraction of time of existing domain adaptation methods.
Authors: Zijiao Yang, Arjun Majumdar, Stefan Lee
To be successful, Vision-and-Language Navigation (VLN) agents must be able to ground instructions to actions based on their surroundings. In this work, we develop a methodology to study agent behavior on a skill-specific basis -- examining how well existing agents ground instructions about stopping, turning, and moving towards specified objects or rooms. Our approach is based on generating skill-specific interventions and measuring changes in agent predictions. We present a detailed case study analyzing the behavior of a recent agent and then compare multiple agents in terms of skill-specific competency scores. This analysis suggests that biases from training have lasting effects on agent behavior and that existing models are able to ground simple referring expressions. Our comparisons between models show that skill-specific scores correlate with improvements in overall VLN task performance.
Authors: João Santos, Triet Tran, Oliver Rippel
Few-shot anomaly detection (AD) is an emerging sub-field of general AD, and tries to distinguish between normal and anomalous data using only few selected samples. While newly proposed few-shot AD methods do compare against pre-existing algorithms developed for the full-shot domain as baselines, they do not dedicatedly optimize them for the few-shot setting. It thus remains unclear if the performance of such pre-existing algorithms can be further improved. We address said question in this work. Specifically, we present a study on the AD/anomaly segmentation (AS) performance of PatchCore, the current state-of-the-art full-shot AD/AS algorithm, in both the few-shot and the many-shot settings. We hypothesize that further performance improvements can be realized by (I) optimizing its various hyperparameters, and by (II) transferring techniques known to improve few-shot supervised learning to the AD domain. Exhaustive experiments on the public VisA and MVTec AD datasets reveal that (I) significant performance improvements can be realized by optimizing hyperparameters such as the underlying feature extractor, and that (II) image-level augmentations can, but are not guaranteed, to improve performance. Based on these findings, we achieve a new state of the art in few-shot AD on VisA, further demonstrating the merit of adapting pre-existing AD/AS methods to the few-shot setting. Last, we identify the investigation of feature extractors with a strong inductive bias as a potential future research direction for (few-shot) AD/AS.
Authors: Stella Bounareli, Christos Tzelepis, Vasileios Argyriou, Ioannis Patras, Georgios Tzimiropoulos
In this paper, we present our method for neural face reenactment, called HyperReenact, that aims to generate realistic talking head images of a source identity, driven by a target facial pose. Existing state-of-the-art face reenactment methods train controllable generative models that learn to synthesize realistic facial images, yet producing reenacted faces that are prone to significant visual artifacts, especially under the challenging condition of extreme head pose changes, or requiring expensive few-shot fine-tuning to better preserve the source identity characteristics. We propose to address these limitations by leveraging the photorealistic generation ability and the disentangled properties of a pretrained StyleGAN2 generator, by first inverting the real images into its latent space and then using a hypernetwork to perform: (i) refinement of the source identity characteristics and (ii) facial pose re-targeting, eliminating this way the dependence on external editing methods that typically produce artifacts. Our method operates under the one-shot setting (i.e., using a single source frame) and allows for cross-subject reenactment, without requiring any subject-specific fine-tuning. We compare our method both quantitatively and qualitatively against several state-of-the-art techniques on the standard benchmarks of VoxCeleb1 and VoxCeleb2, demonstrating the superiority of our approach in producing artifact-free images, exhibiting remarkable robustness even under extreme head pose changes. We make the code and the pretrained models publicly available at: https://github.com/StelaBou/HyperReenact .
Authors: Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Wanli Ouyang, Xiangyu Yue
Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input data from various modalities are mapped into a shared token space, allowing a subsequent encoder with frozen parameters to extract high-level semantic features of the input data. Composed of three main components: a unified data tokenizer, a modality-shared encoder, and task-specific heads for downstream tasks, Meta-Transformer is the first framework to perform unified learning across 12 modalities with unpaired data. Experiments on different benchmarks reveal that Meta-Transformer can handle a wide range of tasks including fundamental perception (text, image, point cloud, audio, video), practical application (X-Ray, infrared, hyperspectral, and IMU), and data mining (graph, tabular, and time-series). Meta-Transformer indicates a promising future for developing unified multimodal intelligence with transformers. Code will be available at https://github.com/invictus717/MetaTransformer
Authors: Xilei Zhu, Huiyu Duan, Yuqin Cao, Yuxin Zhu, Yucheng Zhu, Jing Liu, Li Chen, Xiongkuo Min, Guangtao Zhai
Omnidirectional videos (ODVs) play an increasingly important role in the application fields of medical, education, advertising, tourism, etc. Assessing the quality of ODVs is significant for service-providers to improve the user's Quality of Experience (QoE). However, most existing quality assessment studies for ODVs only focus on the visual distortions of videos, while ignoring that the overall QoE also depends on the accompanying audio signals. In this paper, we first establish a large-scale audio-visual quality assessment dataset for omnidirectional videos, which includes 375 distorted omnidirectional audio-visual (A/V) sequences generated from 15 high-quality pristine omnidirectional A/V contents, and the corresponding perceptual audio-visual quality scores. Then, we design three baseline methods for full-reference omnidirectional audio-visual quality assessment (OAVQA), which combine existing state-of-the-art single-mode audio and video QA models via multimodal fusion strategies. We validate the effectiveness of the A/V multimodal fusion method for OAVQA on our dataset, which provides a new benchmark for omnidirectional QoE evaluation. Our dataset is available at https://github.com/iamazxl/OAVQA.
Authors: Jinheng Xie, Yuexiang Li, Yawen Huang, Haozhe Liu, Wentian Zhang, Yefeng Zheng, Mike Zheng Shou
Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works have explored using other modalities as conditions, considerable paired data, e.g., box/mask-image pairs, and fine-tuning time are required for nurturing models. As such paired data is time-consuming and labor-intensive to acquire and restricted to a closed set, this potentially becomes the bottleneck for applications in an open world. This paper focuses on the simplest form of user-provided conditions, e.g., box or scribble. To mitigate the aforementioned problem, we propose a training-free method to control objects and contexts in the synthesized images adhering to the given spatial conditions. Specifically, three spatial constraints, i.e., Inner-Box, Outer-Box, and Corner Constraints, are designed and seamlessly integrated into the denoising step of diffusion models, requiring no additional training and massive annotated layout data. Extensive results show that the proposed constraints can control what and where to present in the images while retaining the ability of the Stable Diffusion model to synthesize with high fidelity and diverse concept coverage. The code is publicly available at https://github.com/Sierkinhane/BoxDiff.
Authors: Wei Cong, Yang Cong, Jiahua Dong, Gan Sun, Henghui Ding
Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and background shift since they 1) treat all previous classes equally without considering different forgetting paces caused by imbalanced gradient back-propagation; 2) lack strong semantic guidance between classes. To tackle the above challenges, in this paper, we propose a Gradient-Semantic Compensation (GSC) model, which surmounts incremental semantic segmentation from both gradient and semantic perspectives. Specifically, to address catastrophic forgetting from the gradient aspect, we develop a step-aware gradient compensation that can balance forgetting paces of previously seen classes via re-weighting gradient backpropagation. Meanwhile, we propose a soft-sharp semantic relation distillation to distill consistent inter-class semantic relations via soft labels for alleviating catastrophic forgetting from the semantic aspect. In addition, we develop a prototypical pseudo re-labeling that provides strong semantic guidance to mitigate background shift. It produces high-quality pseudo labels for old classes in the background by measuring distances between pixels and class-wise prototypes. Extensive experiments on three public datasets, i.e., Pascal VOC 2012, ADE20K, and Cityscapes, demonstrate the effectiveness of our proposed GSC model.
Authors: Jianpeng Zhang, Xianghua Ye, Jianfeng Zhang, Yuxing Tang, Minfeng Xu, Jianfei Guo, Xin Chen, Zaiyi Liu, Jingren Zhou, Le Lu, Ling Zhang
Lung cancer is a leading cause of death worldwide and early screening is critical for improving survival outcomes. In clinical practice, the contextual structure of nodules and the accumulated experience of radiologists are the two core elements related to the accuracy of identification of benign and malignant nodules. Contextual information provides comprehensive information about nodules such as location, shape, and peripheral vessels, and experienced radiologists can search for clues from previous cases as a reference to enrich the basis of decision-making. In this paper, we propose a radiologist-inspired method to simulate the diagnostic process of radiologists, which is composed of context parsing and prototype recalling modules. The context parsing module first segments the context structure of nodules and then aggregates contextual information for a more comprehensive understanding of the nodule. The prototype recalling module utilizes prototype-based learning to condense previously learned cases as prototypes for comparative analysis, which is updated online in a momentum way during training. Building on the two modules, our method leverages both the intrinsic characteristics of the nodules and the external knowledge accumulated from other nodules to achieve a sound diagnosis. To meet the needs of both low-dose and noncontrast screening, we collect a large-scale dataset of 12,852 and 4,029 nodules from low-dose and noncontrast CTs respectively, each with pathology- or follow-up-confirmed labels. Experiments on several datasets demonstrate that our method achieves advanced screening performance on both low-dose and noncontrast scenarios.
Authors: Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn
Recently, different methods have been proposed to address the inconsistency issue of DDIM inversion to enable image editing, such as EDICT [36] and Null-text inversion [22]. However, the above methods introduce considerable computational overhead. In this paper, we propose a new technique, named bi-directional integration approximation (BDIA), to perform exact diffusion inversion with neglible computational overhead. Suppose we would like to estimate the next diffusion state $\boldsymbol{z}_{i-1}$ at timestep $t_i$ with the historical information $(i,\boldsymbol{z}_i)$ and $(i+1,\boldsymbol{z}_{i+1})$. We first obtain the estimated Gaussian noise $\hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i)$, and then apply the DDIM update procedure twice for approximating the ODE integration over the next time-slot $[t_i, t_{i-1}]$ in the forward manner and the previous time-slot $[t_i, t_{t+1}]$ in the backward manner. The DDIM step for the previous time-slot is used to refine the integration approximation made earlier when computing $\boldsymbol{z}_i$. One nice property with BDIA-DDIM is that the update expression for $\boldsymbol{z}_{i-1}$ is a linear combination of $(\boldsymbol{z}_{i+1}, \boldsymbol{z}_i, \hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i))$. This allows for exact backward computation of $\boldsymbol{z}_{i+1}$ given $(\boldsymbol{z}_i, \boldsymbol{z}_{i-1})$, thus leading to exact diffusion inversion. Experiments on both image reconstruction and image editing were conducted, confirming our statement.
BDIA can also be applied to improve the performance of other ODE solvers in addition to DDIM. In our work, it is found that applying BDIA to the EDM sampling procedure produces slightly better FID score over CIFAR10.
Authors: Ondrej Bohdal, Da Li, Timothy Hospedales
Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under the domain shift and making predictions according to the prototype closest to the vector with predicted class probabilities. The proposed adaptation procedure is fast, comes almost for free in terms of computational resources and leads to considerable performance improvements. We demonstrate the benefits of such label calibration on the highly-practical synthetic-to-real semantic segmentation problem.
Authors: Reyhaneh Rahimi, Ardeshir Ebtehaj, Ali Behrangi, Jackson Tan
This paper presents a deep learning architecture for nowcasting of precipitation almost globally every 30 min with a 4-hour lead time. The architecture fuses a U-Net and a convolutional long short-term memory (LSTM) neural network and is trained using data from the Integrated MultisatellitE Retrievals for GPM (IMERG) and a few key precipitation drivers from the Global Forecast System (GFS). The impacts of different training loss functions, including the mean-squared error (regression) and the focal-loss (classification), on the quality of precipitation nowcasts are studied. The results indicate that the regression network performs well in capturing light precipitation (below 1.6 mm/hr), but the classification network can outperform the regression network for nowcasting of precipitation extremes (>8 mm/hr), in terms of the critical success index (CSI).. Using the Wasserstein distance, it is shown that the predicted precipitation by the classification network has a closer class probability distribution to the IMERG than the regression network. It is uncovered that the inclusion of the physical variables can improve precipitation nowcasting, especially at longer lead times in both networks. Taking IMERG as a relative reference, a multi-scale analysis in terms of fractions skill score (FSS), shows that the nowcasting machine remains skillful (FSS > 0.5) at the resolution of 10 km compared to 50 km for GFS. For precipitation rates greater than 4~mm/hr, only the classification network remains FSS-skillful on scales greater than 50 km within a 2-hour lead time.
Authors: Wei Cong, Yang Cong, Gan Sun, Yuyang Liu, Jiahua Dong
Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual learner will be degraded without distinguishing the contributions of previously learned tasks; 2) the computational cost will be greatly increased with the number of tasks, since most existing algorithms need to regularize all previous tasks when learning new tasks. To address the above challenges, we propose a self-paced Weight Consolidation (spWC) framework to attain robust continual learning via evaluating the discriminative contributions of previous tasks. To be specific, we develop a self-paced regularization to reflect the priorities of past tasks via measuring difficulty based on key performance indicator (i.e., accuracy). When encountering a new task, all previous tasks are sorted from "difficult" to "easy" based on the priorities. Then the parameters of the new continual learner will be learned via selectively maintaining the knowledge amongst more difficult past tasks, which could well overcome catastrophic forgetting with less computational cost. We adopt an alternative convex search to iteratively update the model parameters and priority weights in the bi-convex formulation. The proposed spWC framework is plug-and-play, which is applicable to most continual learning algorithms (e.g., EWC, MAS and RCIL) in different directions (e.g., classification and segmentation). Experimental results on several public benchmark datasets demonstrate that our proposed framework can effectively improve performance when compared with other popular continual learning algorithms.
Authors: Zhenghui Zhao, Lixiang Ru, Chen Wu
Weakly-supervised change detection (WSCD) aims to detect pixel-level changes with only image-level annotations. Owing to its label efficiency, WSCD is drawing increasing attention recently. However, current WSCD methods often encounter the challenge of change missing and fabricating, i.e., the inconsistency between image-level annotations and pixel-level predictions. Specifically, change missing refer to the situation that the WSCD model fails to predict any changed pixels, even though the image-level label indicates changed, and vice versa for change fabricating. To address this challenge, in this work, we leverage global-scale and local-scale priors in WSCD and propose two components: a Dilated Prior (DP) decoder and a Label Gated (LG) constraint. The DP decoder decodes samples with the changed image-level label, skips samples with the unchanged label, and replaces them with an all-unchanged pixel-level label. The LG constraint is derived from the correspondence between changed representations and image-level labels, penalizing the model when it mispredicts the change status. Additionally, we develop TransWCD, a simple yet powerful transformer-based model, showcasing the potential of weakly-supervised learning in change detection. By integrating the DP decoder and LG constraint into TransWCD, we form TransWCD-DL. Our proposed TransWCD and TransWCD-DL achieve significant +6.33% and +9.55% F1 score improvements over the state-of-the-art methods on the WHU-CD dataset, respectively. Some performance metrics even exceed several fully-supervised change detection (FSCD) competitors. Code will be available at https://github.com/zhenghuizhao/TransWCD.
Authors: Kaede Shiohara, Xingchao Yang, Takafumi Taketomi
The great advancements of generative adversarial networks and face recognition models in computer vision have made it possible to swap identities on images from single sources. Although a lot of studies seems to have proposed almost satisfactory solutions, we notice previous methods still suffer from an identity-attribute entanglement that causes undesired attributes swapping because widely used identity encoders, eg, ArcFace, have some crucial attribute biases owing to their pretraining on face recognition tasks. To address this issue, we design BlendFace, a novel identity encoder for face-swapping. The key idea behind BlendFace is training face recognition models on blended images whose attributes are replaced with those of another mitigates inter-personal biases such as hairsyles. BlendFace feeds disentangled identity features into generators and guides generators properly as an identity loss function. Extensive experiments demonstrate that BlendFace improves the identity-attribute disentanglement in face-swapping models, maintaining a comparable quantitative performance to previous methods.
Authors: Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
Emerging large-scale text-to-image generative models, e.g., Stable Diffusion (SD), have exhibited overwhelming results with high fidelity. Despite the magnificent progress, current state-of-the-art models still struggle to generate images fully adhering to the input prompt. Prior work, Attend & Excite, has introduced the concept of Generative Semantic Nursing (GSN), aiming to optimize cross-attention during inference time to better incorporate the semantics. It demonstrates promising results in generating simple prompts, e.g., ``a cat and a dog''. However, its efficacy declines when dealing with more complex prompts, and it does not explicitly address the problem of improper attribute binding. To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind. We introduce two novel loss objectives for GSN: a novel attendance loss and a binding loss. Our approach stands out in its ability to faithfully synthesize desired objects with improved attribute alignment from complex prompts and exhibits superior performance across multiple evaluation benchmarks. More videos and updates can be found on the project page \url{https://sites.google.com/view/divide-and-bind}.
Authors: Ashish Singh, Prateek Agarwal, Zixuan Huang, Arpita Singh, Tong Yu, Sungchul Kim, Victor Bursztyn, Nikos Vlassis, Ryan A. Rossi
Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness [15] leading to generated captions being misaligned with reader preferences. To enable the generation of high-quality figure captions, we introduce FigCaps-HF a new framework for figure-caption generation that can incorporate domain expert feedback in generating captions optimized for reader preferences. Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences. We demonstrate the effectiveness of our simple learning framework by improving performance over standard fine-tuning across different types of models. In particular, when using BLIP as the base model, our RLHF framework achieves a mean gain of 35.7%, 16.9%, and 9% in ROUGE, BLEU, and Meteor, respectively. Finally, we release a large-scale benchmark dataset with human feedback on figure-caption pairs to enable further evaluation and development of RLHF techniques for this problem.
Authors: Ken Mori, Kai Storms, Steven Peters
Having efficient testing strategies is a core challenge that needs to be overcome for the release of automated driving. This necessitates clear requirements as well as suitable methods for testing. In this work, the requirements for perception modules are considered with respect to relevance. The concept of relevance currently remains insufficiently defined and specified. In this paper, we propose a novel methodology to overcome this challenge by exemplary application to collision safety in the highway domain. Using this general system and use case specification, a corresponding concept for relevance is derived. Irrelevant objects are thus defined as objects which do not limit the set of safe actions available to the ego vehicle under consideration of all uncertainties. As an initial step, the use case is decomposed into functional scenarios with respect to collision relevance. For each functional scenario, possible actions of both the ego vehicle and any other dynamic object are formalized as equations. This set of possible actions is constrained by traffic rules, yielding relevance criteria. As a result, we present a conservative estimation which dynamic objects are relevant for perception and need to be considered for a complete evaluation. The estimation provides requirements which are applicable for offline testing and validation of perception components. A visualization is presented for examples from the highD dataset, showing the plausibility of the results. Finally, a possibility for a future validation of the presented relevance concept is outlined.
The popularity of point cloud deep models for safety-critical purposes has increased, but the reliability and security of these models can be compromised by intentional or naturally occurring point cloud noise. To combat this issue, we present a novel point cloud outlier removal method called PointCVaR, which empowers standard-trained models to eliminate additional outliers and restore the data. Our approach begins by conducting attribution analysis to determine the influence of each point on the model output, which we refer to as point risk. We then optimize the process of filtering high-risk points using Conditional Value at Risk (CVaR) as the objective. The rationale for this approach is based on the observation that noise points in point clouds tend to cluster in the tail of the risk distribution, with a low frequency but a high level of risk, resulting in significant interference with classification results. Despite requiring no additional training effort, our method produces exceptional results in various removal-and-classification experiments for noisy point clouds, which are corrupted by random noise, adversarial noise, and backdoor trigger noise. Impressively, it achieves 87% accuracy in defense against the backdoor attack by removing triggers. Overall, the proposed PointCVaR effectively eliminates noise points and enhances point cloud classification, making it a promising plug-in module for various models in different scenarios.
Authors: Rongzheng Bian, Yumeng Xue, Liang Zhou, Jian Zhang, Baoquan Chen, Daniel Weiskopf, Yunhai Wang
We propose a visualization method to understand the effect of multidimensional projection on local subspaces, using implicit function differentiation. Here, we understand the local subspace as the multidimensional local neighborhood of data points. Existing methods focus on the projection of multidimensional data points, and the neighborhood information is ignored. Our method is able to analyze the shape and directional information of the local subspace to gain more insights into the global structure of the data through the perception of local structures. Local subspaces are fitted by multidimensional ellipses that are spanned by basis vectors. An accurate and efficient vector transformation method is proposed based on analytical differentiation of multidimensional projections formulated as implicit functions. The results are visualized as glyphs and analyzed using a full set of specifically-designed interactions supported in our efficient web-based visualization tool. The usefulness of our method is demonstrated using various multi- and high-dimensional benchmark datasets. Our implicit differentiation vector transformation is evaluated through numerical comparisons; the overall method is evaluated through exploration examples and use cases.
Authors: Mikolaj Jankowski, Deniz Gunduz, Krystian Mikolajczyk
State-of-the-art performance for many edge applications is achieved by deep neural networks (DNNs). Often, these DNNs are location- and time-sensitive, and must be delivered over a wireless channel rapidly and efficiently. In this paper, we introduce AirNet, a family of novel training and transmission methods that allow DNNs to be efficiently delivered over wireless channels under stringent transmit power and latency constraints. This corresponds to a new class of joint source-channel coding problems, aimed at delivering DNNs with the goal of maximizing their accuracy at the receiver, rather than recovering them with high fidelity. In AirNet, we propose the direct mapping of the DNN parameters to transmitted channel symbols, while the network is trained to meet the channel constraints, and exhibit robustness against channel noise. AirNet achieves higher accuracy compared to separation-based alternatives. We further improve the performance of AirNet by pruning the network below the available bandwidth, and expanding it for improved robustness. We also benefit from unequal error protection by selectively expanding important layers of the network. Finally, we develop an approach, which simultaneously trains a spectrum of DNNs, each targeting a different channel condition, resolving the impractical memory requirements of training distinct networks for different channel conditions.
Authors: Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional controllable requirements such as embedding a traffic sign in a driving scene by manipulating patterns implicitly in the neuron level. In this paper, we introduce a method to incorporate domain knowledge explicitly in the generation process to achieve the Semantically Adversarial Generation (SAG). To be consistent with the composition of driving scenes, we first categorize the knowledge into two types, the property of objects and the relationship among objects. We then propose a tree-structured variational auto-encoder (T-VAE) to learn hierarchical scene representation. By imposing semantic rules on the properties of nodes and edges in the tree structure, explicit knowledge integration enables controllable generation. We construct a synthetic example to illustrate the controllability and explainability of our method in a succinct setting. We further extend to realistic environments for autonomous vehicles: our method efficiently identifies adversarial driving scenes against different state-of-the-art 3D point cloud segmentation models and satisfies the traffic rules specified as the explicit knowledge.
Authors: Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes DETReg achieves improved performance, e.g., when training with only 1% of the labels and in the few-shot learning settings.
Authors: Piotr Koniusz, Lei Wang, Ke Sun
We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity measure due to low numbers of aggregated vectors and the burstiness phenomenon, when a given feature appears more/less frequently than statistically expected. The Heat Diffusion Process (HDP) on a graph Laplacian is closely related to the Eigenvalue Power Normalization (EPN) of the covariance/auto-correlation matrix, whose inverse forms a loopy graph Laplacian. We show that the HDP and the EPN play the same role, i.e., to boost or dampen the magnitude of the eigenspectrum thus preventing the burstiness. We equip higher-order tensors with EPN which acts as a spectral detector of higher-order occurrences to prevent burstiness. We also prove that for a tensor of order r built from d dimensional feature descriptors, such a detector gives the likelihood if at least one higher-order occurrence is 'projected' into one of binom(d,r) subspaces represented by the tensor; thus forming a tensor power normalization metric endowed with binom(d,r) such 'detectors'. For experimental contributions, we apply several second- and higher-order pooling variants to action recognition, provide previously not presented comparisons of such pooling variants, and show state-of-the-art results on HMDB-51, YUP++ and MPII Cooking Activities.
Authors: Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu, Hongyang Li, Junchi Yan
Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g. trajectory prediction. The driving scene often involves heterogeneous elements such as the different types of objects (agents, lanes, traffic signs) and the semantic relations between objects are rich and diverse. Meanwhile, there also exist relativity across elements, which means that the spatial relation is a relative concept and need be encoded in a ego-centric manner instead of in a global coordinate system. Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges. For heterogeneous graph construction, we connect different types of nodes according to diverse semantic relations. For spatial relation encoding, the coordinates of the node as well as its in-edges are in the local node-centric coordinate system. For the aggregation module in the graph neural network (GNN), we adopt the transformer structure in a hierarchical way to fit the heterogeneous nature of inputs. Experimental results show that HDGT achieves state-of-the-art performance for the task of trajectory prediction, on INTERACTION Prediction Challenge and Waymo Open Motion Challenge.
Authors: Weixuan Sun, Zhen Qin, Hui Deng, Jianyuan Wang, Yi Zhang, Kaihao Zhang, Nick Barnes, Stan Birchfield, Lingpeng Kong, Yiran Zhong
Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Although linear attention was introduced in natural language processing (NLP) tasks to mitigate a similar issue, directly applying existing linear attention to vision transformers may not lead to satisfactory results. We investigate this problem and find that computer vision tasks focus more on local information compared with NLP tasks. Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance measured by its neighbouring patches. In this case, the neighbouring patches will receive stronger attention than far-away patches. Moreover, since our Vicinity Attention requires the token length to be much larger than the feature dimension to show its efficiency advantages, we further propose a new Vicinity Vision Transformer (VVT) structure to reduce the feature dimension without degenerating the accuracy. We perform extensive experiments on the CIFAR100, ImageNet1K, and ADE20K datasets to validate the effectiveness of our method. Our method has a slower growth rate of GFlops than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.
Authors: Jiangmeng Li, Wenwen Qiang, Yanan Zhang, Wenyi Mo, Changwen Zheng, Bing Su, Hui Xiong
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy and architecture design, it still remains two persistent defects: the interference of task-irrelevant information and sample inefficiency, which are related to the recurring existence of trivial constant solutions. From the perspective of dimensional analysis, we find out that the dimensional redundancy and dimensional confounder are the intrinsic issues behind the phenomena, and provide experimental evidence to support our viewpoint. We further propose a simple yet effective approach MetaMask, short for the dimensional Mask learned by Meta-learning, to learn representations against dimensional redundancy and confounder. MetaMask adopts the redundancy-reduction technique to tackle the dimensional redundancy issue and innovatively introduces a dimensional mask to reduce the gradient effects of specific dimensions containing the confounder, which is trained by employing a meta-learning paradigm with the objective of improving the performance of masked representations on a typical self-supervised task. We provide solid theoretical analyses to prove MetaMask can obtain tighter risk bounds for downstream classification compared to typical contrastive methods. Empirically, our method achieves state-of-the-art performance on various benchmarks.
Authors: Linfeng Liu, Siyu Liu, Lu Zhang, Xuan Vinh To, Fatima Nasrallah, Shekhar S. Chandra
Accurate medical classification requires a large number of multi-modal data, and in many cases, different feature types. Previous studies have shown promising results when using multi-modal data, outperforming single-modality models when classifying diseases such as Alzheimer's Disease (AD). However, those models are usually not flexible enough to handle missing modalities. Currently, the most common workaround is discarding samples with missing modalities which leads to considerable data under-utilization. Adding to the fact that labeled medical images are already scarce, the performance of data-driven methods like deep learning can be severely hampered. Therefore, a multi-modal method that can handle missing data in various clinical settings is highly desirable. In this paper, we present Multi-Modal Mixing Transformer (3MAT), a disease classification transformer that not only leverages multi-modal data but also handles missing data scenarios. In this work, we test 3MT for AD and Cognitively normal (CN) classification and mild cognitive impairment (MCI) conversion prediction to progressive MCI (pMCI) or stable MCI (sMCI) using clinical and neuroimaging data. The model uses a novel Cascaded Modality Transformer architecture with cross-attention to incorporate multi-modal information for more informed predictions. We propose a novel modality dropout mechanism to ensure an unprecedented level of modality independence and robustness to handle missing data scenarios. The result is a versatile network that enables the mixing of arbitrary numbers of modalities with different feature types and also ensures full data utilization missing data scenarios. The model is trained and evaluated on the ADNI dataset with the SOTRA performance and further evaluated with the AIBL dataset with missing data.
Authors: Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, Yanru Zhu, Hongfa Wang, Jiaxing Zhang, Tetsuya Sakai, Yujiu Yang
Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty. Little effort has studied the modeling of this uncertainty, particularly in pre-training on unlabeled datasets and fine-tuning in task-specific downstream datasets. In this paper, we project the representations of all modalities as probabilistic distributions via a Probability Distribution Encoder (PDE) by utilizing sequence-level interactions. Compared to the existing deterministic methods, such uncertainty modeling can convey richer multimodal semantic information and more complex relationships. Furthermore, we integrate uncertainty modeling with popular pre-training frameworks and propose suitable pre-training tasks: Distribution-based Vision-Language Contrastive learning (D-VLC), Distribution-based Masked Language Modeling (D-MLM), and Distribution-based Image-Text Matching (D-ITM). The fine-tuned models are applied to challenging downstream tasks, including image-text retrieval, visual question answering, visual reasoning, and visual entailment, and achieve state-of-the-art results.
Authors: Wentao Zhu, Xiaoxuan Ma, Zhaoyang Liu, Libin Liu, Wayne Wu, Yizhou Wang
We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations. The motion representations acquired in this way incorporate geometric, kinematic, and physical knowledge about human motion, which can be easily transferred to multiple downstream tasks. We implement the motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network. It could capture long-range spatio-temporal relationships among the skeletal joints comprehensively and adaptively, exemplified by the lowest 3D pose estimation error so far when trained from scratch. Furthermore, our proposed framework achieves state-of-the-art performance on all three downstream tasks by simply finetuning the pretrained motion encoder with a simple regression head (1-2 layers), which demonstrates the versatility of the learned motion representations. Code and models are available at https://motionbert.github.io/
Authors: Xiaoyu Pan, Huazheng Zhu, Jinglong Du, Guangtao Hu, Baoru Han, Yuanyuan Jia
The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that use a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesions contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results.
Authors: Bojan Žunkovič
Positive unlabeled learning is a binary classification problem with positive and unlabeled data. It is common in domains where negative labels are costly or impossible to obtain, e.g., medicine and personalized advertising. Most approaches to positive unlabeled learning apply to specific data types (e.g., images, categorical data) and can not generate new positive and negative samples. This work introduces a feature-space distance-based tensor network approach to the positive unlabeled learning problem. The presented method is not domain specific and significantly improves the state-of-the-art results on the MNIST image and 15 categorical/mixed datasets. The trained tensor network model is also a generative model and enables the generation of new positive and negative instances.
Authors: Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada
The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours, showing potential to integrate into quantisation network to quantities from image to network activation. The source code is available at https://github.com/ryeocthiv/CQFormer
Authors: Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose. Specifically, ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either a top-down or a bottom-up manner. It can be scaled up from about 20M to 1B parameters by taking advantage of the scalable model capacity and high parallelism of the vision transformer, setting a new Pareto front for throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, and pre-training and fine-tuning strategy. Based on the flexibility, a novel ViTPose+ model is proposed to deal with heterogeneous body keypoint categories in different types of body pose estimation tasks via knowledge factorization, i.e., adopting task-agnostic and task-specific feed-forward networks in the transformer. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our ViTPose model outperforms representative methods on the challenging MS COCO Human Keypoint Detection benchmark at both top-down and bottom-up settings. Furthermore, our ViTPose+ model achieves state-of-the-art performance simultaneously on a series of body pose estimation tasks, including MS COCO, AI Challenger, OCHuman, MPII for human keypoint detection, COCO-Wholebody for whole-body keypoint detection, as well as AP-10K and APT-36K for animal keypoint detection, without sacrificing inference speed.
Authors: Fernando Alonso-Fernandez, Josef Bigun, Julian Fierrez, Naser Damer, Hugo Proença, Arun Ross
Periocular refers to the externally visible region of the face that surrounds the eye socket. This feature-rich area can provide accurate identification in unconstrained or uncooperative scenarios, where the iris or face modalities may not offer sufficient biometric cues due to factors such as partial occlusion or high subject-to-camera distance. The COVID-19 pandemic has further highlighted its importance, as the ocular region remained the only visible facial area even in controlled settings due to the widespread use of masks. This paper discusses the state of the art in periocular biometrics, presenting an overall framework encompassing its most significant research aspects, which include: (a) ocular definition, acquisition, and detection; (b) identity recognition, including combination with other modalities and use of various spectra; and (c) ocular soft-biometric analysis. Finally, we conclude by addressing current challenges and proposing future directions.
Authors: Yan Yang, Liyuan Pan, Liu Liu
This paper proposes a pre-trained neural network for handling event camera data. Our model is a self-supervised learning framework, and uses paired event camera data and natural RGB images for training.
Our method contains three modules connected in a sequence: i) a family of event data augmentations, generating meaningful event images for self-supervised training; ii) a conditional masking strategy to sample informative event patches from event images, encouraging our model to capture the spatial layout of a scene and accelerating training; iii) a contrastive learning approach, enforcing the similarity of embeddings between matching event images, and between paired event and RGB images. An embedding projection loss is proposed to avoid the model collapse when enforcing the event image embedding similarities. A probability distribution alignment loss is proposed to encourage the event image to be consistent with its paired RGB image in the feature space.
Transfer learning performance on downstream tasks shows the superiority of our method over state-of-the-art methods. For example, we achieve top-1 accuracy at 64.83% on the N-ImageNet dataset.
Authors: Yushan Han, Hui Zhang, Huifang Li, Yi Jin, Congyan Lang, Yidong Li
Collaborative perception is essential to address occlusion and sensor failure issues in autonomous driving. In recent years, theoretical and experimental investigations of novel works for collaborative perception have increased tremendously. So far, however, few reviews have focused on systematical collaboration modules and large-scale collaborative perception datasets. This work reviews recent achievements in this field to bridge this gap and motivate future research. We start with a brief overview of collaboration schemes. After that, we systematically summarize the collaborative perception methods for ideal scenarios and real-world issues. The former focus on collaboration modules and efficiency, and the latter is devoted to addressing the problems in actual application. Furthermore, we present large-scale public datasets and summarize quantitative results on these benchmarks. Finally, we highlight gaps and overlooked challenges between current academic research and real-world applications.
Authors: Alexandre Almin, Léo Lemarié, Anh Duong, B Ravi Kiran
Autonomous driving (AD) perception today relies heavily on deep learning based architectures requiring large scale annotated datasets with their associated costs for curation and annotation. The 3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization. We propose a new dataset, Navya 3D Segmentation (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain, including rural, urban, industrial sites and universities from 13 countries. It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds. We also propose a novel method for sequential dataset split generation based on iterative multi-label stratification, and demonstrated to achieve a +1.2% mIoU improvement over the original split proposed by SemanticKITTI dataset. A complete benchmark for semantic segmentation task was performed, with state of the art methods. Finally, we demonstrate an Active Learning (AL) based dataset distillation framework. We introduce a novel heuristic-free sampling method called ego-pose distance based sampling in the context of AL. A detailed presentation on the dataset is available here https://www.youtube.com/watch?v=5m6ALIs-s20.
Authors: Sara Sarto, Manuele Barraco, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. Our source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.
Authors: Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale registration methods are rarely explored. Challenges mainly arise from the huge point number, complex distribution, and outliers of outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local features, and then leverage estimators (eg. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment without any further post-processing. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes. Furthermore, to effectively reduce mismatches, a bijective association transformer is designed for regressing the initial transformation. Extensive experiments on KITTI and NuScenes datasets demonstrate that our RegFormer achieves competitive performance in terms of both accuracy and efficiency.
Authors: Nathan Mankovich, Tolga Birdal
This paper presents a new, provably-convergent algorithm for computing the flag-mean and flag-median of a set of points on a flag manifold under the chordal metric. The flag manifold is a mathematical space consisting of flags, which are sequences of nested subspaces of a vector space that increase in dimension. The flag manifold is a superset of a wide range of known matrix spaces, including Stiefel and Grassmanians, making it a general object that is useful in a wide variety computer vision problems.
To tackle the challenge of computing first order flag statistics, we first transform the problem into one that involves auxiliary variables constrained to the Stiefel manifold. The Stiefel manifold is a space of orthogonal frames, and leveraging the numerical stability and efficiency of Stiefel-manifold optimization enables us to compute the flag-mean effectively. Through a series of experiments, we show the competence of our method in Grassmann and rotation averaging, as well as principal component analysis. We release our source code under https://github.com/nmank/FlagAveraging.
Authors: Ondrej Bohdal, Timothy Hospedales, Philip H.S. Torr, Fazl Barez
Successful deployment of artificial intelligence (AI) in various settings has led to numerous positive outcomes for individuals and society. However, AI systems have also been shown to harm parts of the population due to biased predictions. AI fairness focuses on mitigating such biases to ensure AI decision making is not discriminatory towards certain groups. We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time and act as a social stressor. More specifically, we discuss how biased models can lead to more negative real-world outcomes for certain groups, which may then become more prevalent by deploying new AI models trained on increasingly biased data, resulting in a feedback loop. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest. We examine current strategies for improving AI fairness, assess their limitations in terms of real-world deployment, and explore potential paths forward to ensure we reap AI's benefits without causing society's collapse.
Authors: Ning Ding, Kazuya Takeda, Wenhui Jin, Yingjiu Bei, Keisuke Fujii
The application of visual tracking to the performance analysis of sports players in dynamic competitions is vital for effective coaching. In doubles matches, coordinated positioning is crucial for maintaining control of the court and minimizing opponents' scoring opportunities. The analysis of such teamwork plays a vital role in understanding the dynamics of the game. However, previous studies have primarily focused on analyzing and assessing singles players without considering occlusion in broadcast videos. These studies have relied on discrete representations, which involve the analysis and representation of specific actions (e.g., strokes) or events that occur during the game while overlooking the meaningful spatial distribution. In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance. We present an efficient framework of deep neural networks that enables the calculation of full probability surfaces. This framework utilizes the embedding of a Gaussian mixture map of players' positions and employs graph convolution on their poses. In the experiment, we verify our approach by comparing various baselines and discovering the correlations between the score and control area. Additionally, we propose a practical application for assessing optimal positioning to provide instructions during a game. Our approach offers both visual and quantitative evaluations of players' movements, thereby providing valuable insights into doubles teamwork. The dataset and related project code is available at https://github.com/Ning-D/Drone_BD_ControlArea
Authors: Jadie Adams, Shireen Elhabian
Statistical Shape Modeling (SSM) is a valuable tool for investigating and quantifying anatomical variations within populations of anatomies. However, traditional correspondence-based SSM generation methods have a prohibitive inference process and require complete geometric proxies (e.g., high-resolution binary volumes or surface meshes) as input shapes to construct the SSM. Unordered 3D point cloud representations of shapes are more easily acquired from various medical imaging practices (e.g., thresholded images and surface scanning). Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases.
Authors: Jadie Adams, Shireen Elhabian
Statistical shape modeling (SSM) enables population-based quantitative analysis of anatomical shapes, informing clinical diagnosis. Deep learning approaches predict correspondence-based SSM directly from unsegmented 3D images but require calibrated uncertainty quantification, motivating Bayesian formulations. Variational information bottleneck DeepSSM (VIB-DeepSSM) is an effective, principled framework for predicting probabilistic shapes of anatomy from images with aleatoric uncertainty quantification. However, VIB is only half-Bayesian and lacks epistemic uncertainty inference. We derive a fully Bayesian VIB formulation and demonstrate the efficacy of two scalable implementation approaches: concrete dropout and batch ensemble. Additionally, we introduce a novel combination of the two that further enhances uncertainty calibration via multimodal marginalization. Experiments on synthetic shapes and left atrium data demonstrate that the fully Bayesian VIB network predicts SSM from images with improved uncertainty reasoning without sacrificing accuracy.
Authors: Jian Zhao, Jianan Li, Lei Jin, Jiaming Chu, Zhihao Zhang, Jun Wang, Jiangqiang Xia, Kai Wang, Yang Liu, Sadaf Gulshad, Jiaojiao Zhao, Tianyang Xu, Xuefeng Zhu, Shihan Liu, Zheng Zhu, Guibo Zhu, Zechao Li, Zheng Wang, Baigui Sun, Yandong Guo, Shin ichi Satoh, Junliang Xing, Jane Shen Shengmei
The 3rd Anti-UAV Workshop & Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking. The Anti-UAV dataset used for the Anti-UAV Challenge has been publicly released. There are two main differences between this year's competition and the previous two. First, we have expanded the existing dataset, and for the first time, released a training set so that participants can focus on improving their models. Second, we set up two tracks for the first time, i.e., Anti-UAV Tracking and Anti-UAV Detection & Tracking. Around 76 participating teams from the globe competed in the 3rd Anti-UAV Challenge. In this paper, we provide a brief summary of the 3rd Anti-UAV Workshop & Challenge including brief introductions to the top three methods in each track. The submission leaderboard will be reopened for researchers that are interested in the Anti-UAV challenge. The benchmark dataset and other information can be found at: https://anti-uav.github.io/.
Authors: Abdul Rehman Khan, Asifullah Khan
Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis in recent years. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range interactions in CNNs. Recently, Transformers have gained popularity in the computer vision community and also medical image segmentation due to their ability to process global features effectively. The scalability issues of self-attention mechanism and lack of the CNN-like inductive bias may have limited their adoption. Therefore, hybrid Vision transformers (CNN-Transformer), exploiting advantages of both Convolution and Self-attention Mechanisms, have gained importance. In this work, we present MaxViT-UNet, an Encoder-Decoder based hybrid vision transformer (CNN-Transformer) for medical image segmentation. The proposed Hybrid Decoder, based on MaxViT-block, is designed to harness the power of both the convolution and self-attention mechanisms at each decoding stage with nominal computational burden. The inclusion of multi-axis self-attention, within each decoder stage, significantly enhances the discriminating capacity between the object and background regions, and thereby helps in improving the segmentation efficiency. In the Hybrid Decoder block, the fusion process commences by integrating the upsampled lower level decoder features, obtained through transpose convolution, with the skip-connection features derived from the hybrid encoder. Subsequently, the fused features undergo refinement through the utilization of a multi-axis attention mechanism. The proposed decoder block is repeated multiple times to progressively segment the nuclei regions. Experimental results on MoNuSeg18 and MoNuSAC20 dataset demonstrates the effectiveness of the proposed technique.
Authors: Tobias Liaudat, Jean-Luc Starck, Martin Kilbinger, Pierre-Antoine Frugier
The accurate modelling of the Point Spread Function (PSF) is of paramount importance in astronomical observations, as it allows for the correction of distortions and blurring caused by the telescope and atmosphere. PSF modelling is crucial for accurately measuring celestial objects' properties. The last decades brought us a steady increase in the power and complexity of astronomical telescopes and instruments. Upcoming galaxy surveys like Euclid and LSST will observe an unprecedented amount and quality of data. Modelling the PSF for these new facilities and surveys requires novel modelling techniques that can cope with the ever-tightening error requirements. The purpose of this review is three-fold. First, we introduce the optical background required for a more physically-motivated PSF modelling and propose an observational model that can be reused for future developments. Second, we provide an overview of the different physical contributors of the PSF, including the optic- and detector-level contributors and the atmosphere. We expect that the overview will help better understand the modelled effects. Third, we discuss the different methods for PSF modelling from the parametric and non-parametric families for ground- and space-based telescopes, with their advantages and limitations. Validation methods for PSF models are then addressed, with several metrics related to weak lensing studies discussed in detail. Finally, we explore current challenges and future directions in PSF modelling for astronomical telescopes.
Authors: Matthias Minderer, Alexey Gritsenko, Neil Houlsby
Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detection training data can be expanded by using Web image-text pairs as weak supervision, this has not been done at scales comparable to image-level pretraining. Here, we scale up detection data with self-training, which uses an existing detector to generate pseudo-box annotations on image-text pairs. Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency. We present the OWLv2 model and OWL-ST self-training recipe, which address these challenges. OWLv2 surpasses the performance of previous state-of-the-art open-vocabulary detectors already at comparable training scales (~10M examples). However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31.2% to 44.6% (43% relative improvement). OWL-ST unlocks Web-scale training for open-world localization, similar to what has been seen for image classification and language modelling.
Authors: Thijs P. Kuipers, Erik J. Bekkers
Regular group convolutional neural networks (G-CNNs) have been shown to increase model performance and improve equivariance to different geometrical symmetries. This work addresses the problem of SE(3), i.e., roto-translation equivariance, on volumetric data. Volumetric image data is prevalent in many medical settings. Motivated by the recent work on separable group convolutions, we devise a SE(3) group convolution kernel separated into a continuous SO(3) (rotation) kernel and a spatial kernel. We approximate equivariance to the continuous setting by sampling uniform SO(3) grids. Our continuous SO(3) kernel is parameterized via RBF interpolation on similarly uniform grids. We demonstrate the advantages of our approach in volumetric medical image analysis. Our SE(3) equivariant models consistently outperform CNNs and regular discrete G-CNNs on challenging medical classification tasks and show significantly improved generalization capabilities. Our approach achieves up to a 16.5% gain in accuracy over regular CNNs.
Authors: Haoran Dou, Ning Bi, Luyi Han, Yuhao Huang, Ritse Mann, Xin Yang, Dong Ni, Nishant Ravikumar, Alejandro F. Frangi, Yunzhi Huang
Deep learning-based deformable registration methods have been widely investigated in diverse medical applications. Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the deformation field. Therefore, they inevitably require tuning the hyperparameter for optimal registration performance. Tuning the hyperparameters is highly computationally expensive and introduces undesired dependencies on domain knowledge. In this study, we construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyperparameter-free balance on multiple losses. In GSMorph, we reformulate the optimization procedure by projecting the gradient of similarity loss orthogonally to the plane associated with the smoothness constraint, rather than additionally introducing a hyperparameter to balance these two competing terms. Furthermore, our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference. In this study, We compared our method with state-of-the-art (SOTA) deformable registration approaches over two publicly available cardiac MRI datasets. GSMorph proves superior to five SOTA learning-based registration models and two conventional registration techniques, SyN and Demons, on both registration accuracy and smoothness.
Authors: Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, Tao Chen
Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.
Authors: Alexander Bigalke, Lasse Hansen, Tony C. W. Mok, Mattias P. Heinrich
State-of-the-art deep learning-based registration methods employ three different learning strategies: supervised learning, which requires costly manual annotations, unsupervised learning, which heavily relies on hand-crafted similarity metrics designed by domain experts, or learning from synthetic data, which introduces a domain shift. To overcome the limitations of these strategies, we propose a novel self-supervised learning paradigm for unsupervised registration, relying on self-training. Our idea is based on two key insights. Feature-based differentiable optimizers 1) perform reasonable registration even from random features and 2) stabilize the training of the preceding feature extraction network on noisy labels. Consequently, we propose cyclical self-training, where pseudo labels are initialized as the displacement fields inferred from random features and cyclically updated based on more and more expressive features from the learning feature extractor, yielding a self-reinforcement effect. We evaluate the method for abdomen and lung registration, consistently surpassing metric-based supervision and outperforming diverse state-of-the-art competitors. Source code is available at https://github.com/multimodallearning/reg-cyclical-self-train.
Authors: Rita Pucci, Niki Martinel
Underwater images are fundamental for studying and understanding the status of marine life. We focus on reducing the memory space required for image storage while the memory space consumption in the collecting phase limits the time lasting of this phase leading to the need for more image collection campaigns. We present a novel machine-learning model that reconstructs the colours of underwater images from their luminescence channel, thus saving 2/3 of the available storage space. Our model specialises in underwater colour reconstruction and consists of an encoder-decoder architecture. The encoder is composed of a convolutional encoder and a parallel specialised classifier trained with webly-supervised data. The encoder and the decoder use layers of capsules to capture the features of the entities in the image. The colour reconstruction process recalls the progressive and the generative adversarial training procedures. The progressive training gives the ground for a generative adversarial routine focused on the refining of colours giving the image bright and saturated colours which bring the image back to life. We validate the model both qualitatively and quantitatively on four benchmark datasets. This is the first attempt at colour reconstruction in greyscale underwater images. Extensive results on four benchmark datasets demonstrate that our solution outperforms state-of-the-art (SOTA) solutions. We also demonstrate that the generated colourisation enhances the quality of images compared to enhancement models at the SOTA.
Authors: Changjian Shui, Justin Szeto, Raghav Mehta, Douglas L. Arnold, Tal Arbel
Trustworthy deployment of deep learning medical imaging models into real-world clinical practice requires that they be calibrated. However, models that are well calibrated overall can still be poorly calibrated for a sub-population, potentially resulting in a clinician unwittingly making poor decisions for this group based on the recommendations of the model. Although methods have been shown to successfully mitigate biases across subgroups in terms of model accuracy, this work focuses on the open problem of mitigating calibration biases in the context of medical image analysis. Our method does not require subgroup attributes during training, permitting the flexibility to mitigate biases for different choices of sensitive attributes without re-training. To this end, we propose a novel two-stage method: Cluster-Focal to first identify poorly calibrated samples, cluster them into groups, and then introduce group-wise focal loss to improve calibration bias. We evaluate our method on skin lesion classification with the public HAM10000 dataset, and on predicting future lesional activity for multiple sclerosis (MS) patients. In addition to considering traditional sensitive attributes (e.g. age, sex) with demographic subgroups, we also consider biases among groups with different image-derived attributes, such as lesion load, which are required in medical image analysis. Our results demonstrate that our method effectively controls calibration error in the worst-performing subgroups while preserving prediction performance, and outperforming recent baselines.
Authors: Peter Lorenz, Ricard Durall, Janis Keuper
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the lightweight multi Local Intrinsic Dimensionality (multiLID), which has been originally developed in context of the detection of adversarial examples, for the automatic detection of synthetic images and the identification of the according generator networks. In contrast to many existing detection approaches, which often only work for GAN-generated images, the proposed method provides close to perfect detection results in many realistic use cases. Extensive experiments on known and newly created datasets demonstrate that the proposed multiLID approach exhibits superiority in diffusion detection and model identification. Since the empirical evaluations of recent publications on the detection of generated images are often mainly focused on the "LSUN-Bedroom" dataset, we further establish a comprehensive benchmark for the detection of diffusion-generated images, including samples from several diffusion models with different image sizes.
Authors: Yuhao Wang
Automated radiology report generation aims to generate radiology reports that contain rich, fine-grained descriptions of radiology imaging. Compared with image captioning in the natural image domain, medical images are very similar to each other, with only minor differences in the occurrence of diseases. Given the importance of these minor differences in the radiology report, it is crucial to encourage the model to focus more on the subtle regions of disease occurrence. Secondly, the problem of visual and textual data biases is serious. Not only do normal cases make up the majority of the dataset, but sentences describing areas with pathological changes also constitute only a small part of the paragraph. Lastly, generating medical image reports involves the challenge of long text generation, which requires more expertise and empirical training in medical knowledge. As a result, the difficulty of generating such reports is increased. To address these challenges, we propose a disease-oriented retrieval framework that utilizes similar reports as prior knowledge references. We design a factual consistency captioning generator to generate more accurate and factually consistent disease descriptions. Our framework can find most similar reports for a given disease from the CXR database by retrieving a disease-oriented mask consisting of the position and morphological characteristics. By referencing the disease-oriented similar report and the visual features, the factual consistency model can generate a more accurate radiology report.
Authors: Asif Hanif, Muzammal Naseer, Salman Khan, Mubarak Shah, Fahad Shahbaz Khan
It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these models cannot be deployed for real-world applications immediately due to their vulnerability to adversarial attacks. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models and demonstrate its advantages over conventional input or voxel domain attacks. Using our proposed attack, we introduce a novel frequency domain adversarial training approach for optimizing a robust model against voxel and frequency domain attacks. Moreover, we propose frequency consistency loss to regulate our frequency domain adversarial training that achieves a better tradeoff between model's performance on clean and adversarial samples. Code is publicly available at https://github.com/asif-hanif/vafa.
Authors: Yujiao Shi, Fei Wu, Akhil Perincherry, Ankit Vora, Hongdong Li
Image retrieval-based cross-view localization methods often lead to very coarse camera pose estimation, due to the limited sampling density of the database satellite images. In this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved satellite image. Our approach designs a geometry-guided cross-view transformer that combines the benefits of conventional geometry and learnable cross-view transformers to map the ground-view observations to an overhead view. Given the synthesized overhead view and observed satellite feature maps, we construct a neural pose optimizer with strong global information embedding ability to estimate the relative rotation between them. After aligning their rotations, we develop an uncertainty-guided spatial correlation to generate a probability map of the vehicle locations, from which the relative translation can be determined. Experimental results demonstrate that our method significantly outperforms the state-of-the-art. Notably, the likelihood of restricting the vehicle lateral pose to be within 1m of its Ground Truth (GT) value on the cross-view KITTI dataset has been improved from $35.54\%$ to $76.44\%$, and the likelihood of restricting the vehicle orientation to be within $1^{\circ}$ of its GT value has been improved from $19.64\%$ to $99.10\%$.
Authors: Siddharth Tourani, Carsten Rother, Muhammad Haris Khan, Bogdan Savchynskyy
We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images. Contrary to the standard \emph{supervised} approach, our method does not require ground truth correspondences between keypoint pairs. Instead, it is self-supervised by enforcing consistency of matchings between images of the same object category. As the matching and the consistency loss are discrete, their derivatives cannot be straightforwardly used for learning. We address this issue in a principled way by building our method upon the recent results on black-box differentiation of combinatorial solvers. This makes our method exceptionally flexible, as it is compatible with arbitrary network architectures and combinatorial solvers. Our experimental evaluation suggests that our technique sets a new state-of-the-art for unsupervised graph matching.
Authors: Zhiyu Wu, Jinshi Cui
Facial expression recognition (FER) remains a challenging task due to the ambiguity of expressions. The derived noisy labels significantly harm the performance in real-world scenarios. To address this issue, we present a new FER model named Landmark-Aware Net~(LA-Net), which leverages facial landmarks to mitigate the impact of label noise from two perspectives. Firstly, LA-Net uses landmark information to suppress the uncertainty in expression space and constructs the label distribution of each sample by neighborhood aggregation, which in turn improves the quality of training supervision. Secondly, the model incorporates landmark information into expression representations using the devised expression-landmark contrastive loss. The enhanced expression feature extractor can be less susceptible to label noise. Our method can be integrated with any deep neural network for better training supervision without introducing extra inference costs. We conduct extensive experiments on both in-the-wild datasets and synthetic noisy datasets and demonstrate that LA-Net achieves state-of-the-art performance.
Authors: Jinlong Li, Runsheng Xu, Jin Ma, Qin Zou, Jiaqi Ma, Hongkai Yu
Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, however such assumption may fail in different weather conditions. Due to the domain gap, a detection model trained under clear weather may not perform well in foggy and rainy conditions. Overcoming detection bottlenecks in foggy and rainy weather is a real challenge for autonomous vehicles deployed in the wild. To bridge the domain gap and improve the performance of object detectionin foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection. The adaptations at both the image-level and object-level are intended to minimize the differences in image style and object appearance between domains. Furthermore, in order to improve the model's performance on challenging examples, we introduce a novel adversarial gradient reversal layer that conducts adversarial mining on difficult instances in addition to domain adaptation. Additionally, we suggest generating an auxiliary domain through data augmentation to enforce a new domain-level metric regularization. Experimental findings on public V2V benchmark exhibit a substantial enhancement in object detection specifically for foggy and rainy driving scenarios.
Authors: Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn, Kunhee Kim, Pilhyeon Lee, Daesik Kim, Youngjung Uh, Hyeran Byun
To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corresponding patches of the content image. However, because of the low semantic correspondence between arbitrary content and artworks, the attention module repeatedly abuses specific local patches from the style image, resulting in disharmonious and evident repetitive artifacts. To overcome this limitation and accomplish impeccable artistic style transfer, we focus on enhancing the attention mechanism and capturing the rhythm of patterns that organize the style. In this paper, we introduce a novel metric, namely pattern repeatability, that quantifies the repetition of patterns in the style image. Based on the pattern repeatability, we propose Aesthetic Pattern-Aware style transfer Networks (AesPA-Net) that discover the sweet spot of local and global style expressions. In addition, we propose a novel self-supervisory task to encourage the attention mechanism to learn precise and meaningful semantic correspondence. Lastly, we introduce the patch-wise style loss to transfer the elaborate rhythm of local patterns. Through qualitative and quantitative evaluations, we verify the reliability of the proposed pattern repeatability that aligns with human perception, and demonstrate the superiority of the proposed framework.
Authors: Fa-Ting Hong, Dan Xu
Talking head video generation aims to animate a human face in a still image with dynamic poses and expressions using motion information derived from a target-driving video, while maintaining the person's identity in the source image. However, dramatic and complex motions in the driving video cause ambiguous generation, because the still source image cannot provide sufficient appearance information for occluded regions or delicate expression variations, which produces severe artifacts and significantly degrades the generation quality. To tackle this problem, we propose to learn a global facial representation space, and design a novel implicit identity representation conditioned memory compensation network, coined as MCNet, for high-fidelity talking head generation.~Specifically, we devise a network module to learn a unified spatial facial meta-memory bank from all training samples, which can provide rich facial structure and appearance priors to compensate warped source facial features for the generation. Furthermore, we propose an effective query mechanism based on implicit identity representations learned from the discrete keypoints of the source image. It can greatly facilitate the retrieval of more correlated information from the memory bank for the compensation. Extensive experiments demonstrate that MCNet can learn representative and complementary facial memory, and can clearly outperform previous state-of-the-art talking head generation methods on VoxCeleb1 and CelebV datasets. Please check our \href{https://github.com/harlanhong/ICCV2023-MCNET}{Project}.
Authors: Jia-Xin Zhuang, Jiabin Cai, Jianguo Zhang, Wei-shi Zheng, Ruixuan Wang
Automated medical image classification is the key component in intelligent diagnosis systems. However, most medical image datasets contain plenty of samples of common diseases and just a handful of rare ones, leading to major class imbalances. Currently, it is an open problem in intelligent diagnosis to effectively learn from imbalanced training data. In this paper, we propose a simple yet effective framework, named \textbf{C}lass \textbf{A}ttention to \textbf{RE}gions of the lesion (CARE), to handle data imbalance issues by embedding attention into the training process of \textbf{C}onvolutional \textbf{N}eural \textbf{N}etworks (CNNs). The proposed attention module helps CNNs attend to lesion regions of rare diseases, therefore helping CNNs to learn their characteristics more effectively. In addition, this attention module works only during the training phase and does not change the architecture of the original network, so it can be directly combined with any existing CNN architecture. The CARE framework needs bounding boxes to represent the lesion regions of rare diseases. To alleviate the need for manual annotation, we further developed variants of CARE by leveraging the traditional saliency methods or a pretrained segmentation model for bounding box generation. Results show that the CARE variants with automated bounding box generation are comparable to the original CARE framework with \textit{manual} bounding box annotations. A series of experiments on an imbalanced skin image dataset and a pneumonia dataset indicates that our method can effectively help the network focus on the lesion regions of rare diseases and remarkably improves the classification performance of rare diseases.
Authors: Moa Arvidsson, Sithichot Sawirot, Cristofer Englund, Fernando Alonso-Fernandez, Martin Torstensson, Boris Duran
Millions of vehicles are transported every year, tightly parked in vessels or boats. To reduce the risks of associated safety issues like fires, knowing the location of vehicles is essential, since different vehicles may need different mitigation measures, e.g. electric cars. This work is aimed at creating a solution based on a nano-drone that navigates across rows of parked vehicles and detects their license plates. We do so via a wall-following algorithm, and a CNN trained to detect license plates. All computations are done in real-time on the drone, which just sends position and detected images that allow the creation of a 2D map with the position of the plates. Our solution is capable of reading all plates across eight test cases (with several rows of plates, different drone speeds, or low light) by aggregation of measurements across several drone journeys.