Authors: Amarnath R, Vinay Kumar V
Recognizing handwritten digits is a challenging task primarily due to the diversity of writing styles and the presence of noisy images. The widely used MNIST dataset, which is commonly employed as a benchmark for this task, includes distorted digits with irregular shapes, incomplete strokes, and varying skew in both the training and testing datasets. Consequently, these factors contribute to reduced accuracy in digit recognition. To overcome this challenge, we propose a two-stage deep learning approach. In the first stage, we create a simple neural network to identify distorted digits within the training set. This model serves to detect and filter out such distorted and ambiguous images. In the second stage, we exclude these identified images from the training dataset and proceed to retrain the model using the filtered dataset. This process aims to improve the classification accuracy and confidence levels while mitigating issues of underfitting and overfitting. Our experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy rate of over 99.5% on the testing dataset. This significant improvement showcases the potential of our method in enhancing digit classification accuracy. In our future work, we intend to explore the scalability of this approach and investigate techniques to further enhance accuracy by reducing the size of the training data.
Authors: Bin Cheng, Zuhao Liu, Yunbo Peng, Yue Lin
Large-scale text-to-image models pre-trained on massive text-image pairs show excellent performance in image synthesis recently. However, image can provide more intuitive visual concepts than plain text. People may ask: how can we integrate the desired visual concept into an existing image, such as our portrait? Current methods are inadequate in meeting this demand as they lack the ability to preserve content or translate visual concepts effectively. Inspired by this, we propose a novel framework named visual concept translator (VCT) with the ability to preserve content in the source image and translate the visual concepts guided by a single reference image. The proposed VCT contains a content-concept inversion (CCI) process to extract contents and concepts, and a content-concept fusion (CCF) process to gather the extracted information to obtain the target image. Given only one reference image, the proposed VCT can complete a wide range of general image-to-image translation tasks with excellent results. Extensive experiments are conducted to prove the superiority and effectiveness of the proposed methods. Codes are available at https://github.com/CrystalNeuro/visual-concept-translator.
Authors: Putri A. van der Linden, David W. Romero, Erik J. Bekkers
Neural operations that rely on neighborhood information are much more expensive when deployed on point clouds than on grid data due to the irregular distances between points in a point cloud. In a grid, on the other hand, we can compute the kernel only once and reuse it for all query positions. As a result, operations that rely on neighborhood information scale much worse for point clouds than for grid data, specially for large inputs and large neighborhoods.
In this work, we address the scalability issue of point cloud methods by tackling its root cause: the irregularity of the data. We propose learnable gridification as the first step in a point cloud processing pipeline to transform the point cloud into a compact, regular grid. Thanks to gridification, subsequent layers can use operations defined on regular grids, e.g., Conv3D, which scale much better than native point cloud methods. We then extend gridification to point cloud to point cloud tasks, e.g., segmentation, by adding a learnable de-gridification step at the end of the point cloud processing pipeline to map the compact, regular grid back to its original point cloud form. Through theoretical and empirical analysis, we show that gridified networks scale better in terms of memory and time than networks directly applied on raw point cloud data, while being able to achieve competitive results. Our code is publicly available at https://github.com/computri/gridifier.
Authors: Maxime Fontana, Michael Spratling, Miaojing Shi
Multi-Task Learning (MTL) aims to learn multiple tasks simultaneously while exploiting their mutual relationships. By using shared resources to simultaneously calculate multiple outputs, this learning paradigm has the potential to have lower memory requirements and inference times compared to the traditional approach of using separate methods for each task. Previous work in MTL has mainly focused on fully-supervised methods, as task relationships can not only be leveraged to lower the level of data-dependency of those methods but they can also improve performance. However, MTL introduces a set of challenges due to a complex optimisation scheme and a higher labeling requirement. This review focuses on how MTL could be utilised under different partial supervision settings to address these challenges. First, this review analyses how MTL traditionally uses different parameter sharing techniques to transfer knowledge in between tasks. Second, it presents the different challenges arising from such a multi-objective optimisation scheme. Third, it introduces how task groupings can be achieved by analysing task relationships. Fourth, it focuses on how partially supervised methods applied to MTL can tackle the aforementioned challenges. Lastly, this review presents the available datasets, tools and benchmarking results of such methods.
Authors: Yiteng Xu, Peishan Cong, Yichen Yao, Runnan Chen, Yuenan Hou, Xinge Zhu, Xuming He, Jingyi Yu, Yuexin Ma
Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human-environment interactions, severe occlusions in crowds, etc. In this paper, we present a large-scale multi-modal dataset for human-centric scene understanding, dubbed HuCenLife, which is collected in diverse daily-life scenarios with rich and fine-grained annotations. Our HuCenLife can benefit many 3D perception tasks, such as segmentation, detection, action recognition, etc., and we also provide benchmarks for these tasks to facilitate related research. In addition, we design novel modules for LiDAR-based segmentation and action recognition, which are more applicable for large-scale human-centric scenarios and achieve state-of-the-art performance.
Authors: Milad Abdollahzadeh, Touba Malekzadeh, Christopher T. H. Teo, Keshigeyan Chandrasegaran, Guimeng Liu, Ngai-Man Cheung
In machine learning, generative modeling aims to learn to generate new data statistically similar to the training data distribution. In this paper, we survey learning generative models under limited data, few shots and zero shot, referred to as Generative Modeling under Data Constraint (GM-DC). This is an important topic when data acquisition is challenging, e.g. healthcare applications. We discuss background, challenges, and propose two taxonomies: one on GM-DC tasks and another on GM-DC approaches. Importantly, we study interactions between different GM-DC tasks and approaches. Furthermore, we highlight research gaps, research trends, and potential avenues for future exploration. Project website: https://gmdc-survey.github.io.
Authors: Matteo Ciotola, Giovanni Poggi, Giuseppe Scarpa
In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain. However, models trained on downsized images tend to perform poorly on high-resolution target images. For this reason, several research groups are now turning to unsupervised training in the full-resolution domain, through the definition of appropriate loss functions and training paradigms. In this context, we have recently proposed a full-resolution training framework which can be applied to many existing architectures.
Here, we propose a new deep learning-based pansharpening model that fully exploits the potential of this approach and provides cutting-edge performance. Besides architectural improvements with respect to previous work, such as the use of residual attention modules, the proposed model features a novel loss function that jointly promotes the spectral and spatial quality of the pansharpened data. In addition, thanks to a new fine-tuning strategy, it improves inference-time adaptation to target images. Experiments on a large variety of test images, performed in challenging scenarios, demonstrate that the proposed method compares favorably with the state of the art both in terms of numerical results and visual output. Code is available online at https://github.com/matciotola/Lambda-PNN.
Authors: Hooman Vaseli, Ang Nan Gu, S. Neda Ahmadi Amiri, Michael Y. Tsang, Andrea Fung, Nima Kondori, Armin Saadat, Purang Abolmaesumi, Teresa S. M. Tsang
Aortic stenosis (AS) is a common heart valve disease that requires accurate and timely diagnosis for appropriate treatment. Most current automatic AS severity detection methods rely on black-box models with a low level of trustworthiness, which hinders clinical adoption. To address this issue, we propose ProtoASNet, a prototypical network that directly detects AS from B-mode echocardiography videos, while making interpretable predictions based on the similarity between the input and learned spatio-temporal prototypes. This approach provides supporting evidence that is clinically relevant, as the prototypes typically highlight markers such as calcification and restricted movement of aortic valve leaflets. Moreover, ProtoASNet utilizes abstention loss to estimate aleatoric uncertainty by defining a set of prototypes that capture ambiguity and insufficient information in the observed data. This provides a reliable system that can detect and explain when it may fail. We evaluate ProtoASNet on a private dataset and the publicly available TMED-2 dataset, where it outperforms existing state-of-the-art methods with an accuracy of 80.0% and 79.7%, respectively. Furthermore, ProtoASNet provides interpretability and an uncertainty measure for each prediction, which can improve transparency and facilitate the interactive usage of deep networks to aid clinical decision-making. Our source code is available at: https://github.com/hooman007/ProtoASNet.
Authors: Vaibhav Sharma, Artur Yakimovich
In the past decades, automated high-content microscopy demonstrated its ability to deliver large quantities of image-based data powering the versatility of phenotypic drug screening and systems biology applications. However, as the sizes of image-based datasets grew, it became infeasible for humans to control, avoid and overcome the presence of imaging and sample preparation artefacts in the images. While novel techniques like machine learning and deep learning may address these shortcomings through generative image inpainting, when applied to sensitive research data this may come at the cost of undesired image manipulation. Undesired manipulation may be caused by phenomena such as neural hallucinations, to which some artificial neural networks are prone. To address this, here we evaluate the state-of-the-art inpainting methods for image restoration in a high-content fluorescence microscopy dataset of cultured cells with labelled nuclei. We show that architectures like DeepFill V2 and Edge Connect can faithfully restore microscopy images upon fine-tuning with relatively little data. Our results demonstrate that the area of the region to be restored is of higher importance than shape. Furthermore, to control for the quality of restoration, we propose a novel phenotype-preserving metric design strategy. In this strategy, the size and count of the restored biological phenotypes like cell nuclei are quantified to penalise undesirable manipulation. We argue that the design principles of our approach may also generalise to other applications.
Authors: Sanaz Karimijafarbigloo, Reza Azad, Dorit Merhof
Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at \href{https://github.com/mindflow-institue/annotation_free_fewshot}{\textcolor{magenta}{GitHub}}.
Authors: Reiner Birkl, Diana Wofk, Matthias Müller
We release MiDaS v3.1 for monocular depth estimation, offering a variety of new models based on different encoder backbones. This release is motivated by the success of transformers in computer vision, with a large variety of pretrained vision transformers now available. We explore how using the most promising vision transformers as image encoders impacts depth estimation quality and runtime of the MiDaS architecture. Our investigation also includes recent convolutional approaches that achieve comparable quality to vision transformers in image classification tasks. While the previous release MiDaS v3.0 solely leverages the vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT. These models offer different performance-runtime tradeoffs. The best model improves the depth estimation quality by 28% while efficient models enable downstream tasks requiring high frame rates. We also describe the general process for integrating new backbones. A video summarizing the work can be found at https://youtu.be/UjaeNNFf9sE and the code is available at https://github.com/isl-org/MiDaS.
Authors: Timothy L. Kline, Sumana Ramanathan, Harrison C. Gottlich, Panagiotis Korfiatis, Adriana V. Gregory
Purpose: This study evaluated the out-of-domain performance and generalization capabilities of automated medical image segmentation models, with a particular focus on adaptation to new image acquisitions and disease type.
Materials: Datasets from both non-contrast and contrast-enhanced abdominal CT scans of healthy patients and those with polycystic kidney disease (PKD) were used. A total of 400 images (100 non-contrast controls, 100 contrast controls, 100 non-contrast PKD, 100 contrast PKD) were utilized for training/validation of models to segment kidneys, livers, and spleens, and the final models were then tested on 100 non-contrast CT images of patients affected by PKD. Performance was evaluated using Dice, Jaccard, TPR, and Precision.
Results: Models trained on a diverse range of data showed no worse performance than models trained exclusively on in-domain data when tested on in-domain data. For instance, the Dice similarity of the model trained on 25% from each dataset was found to be non-inferior to the model trained purely on in-domain data.
Conclusions: The results indicate that broader training examples significantly enhances model generalization and out-of-domain performance, thereby improving automated segmentation tools' applicability in clinical settings. The study's findings provide a roadmap for future research to adopt a data-centric approach in medical image AI model development.
Authors: Jin Wang, Yu Hu, Lirong Xiang, Gota Morota, Samantha A. Brooks, Carissa L. Wickens, Emily K. Miller-Cushon, Haipeng Yu
Computer vision (CV), a non-intrusive and cost-effective technology, has furthered the development of precision livestock farming by enabling optimized decision-making through timely and individualized animal care. The availability of affordable two- and three-dimensional camera sensors, combined with various machine learning and deep learning algorithms, has provided a valuable opportunity to improve livestock production systems. However, despite the availability of various CV tools in the public domain, applying these tools to animal data can be challenging, often requiring users to have programming and data analysis skills, as well as access to computing resources. Moreover, the rapid expansion of precision livestock farming is creating a growing need to educate and train animal science students in CV. This presents educators with the challenge of efficiently demonstrating the complex algorithms involved in CV. Thus, the objective of this study was to develop ShinyAnimalCV, an open-source cloud-based web application. This application provides a user-friendly interface for performing CV tasks, including object segmentation, detection, three-dimensional surface visualization, and extraction of two- and three-dimensional morphological features. Nine pre-trained CV models using top-view animal data are included in the application. ShinyAnimalCV has been deployed online using cloud computing platforms. The source code of ShinyAnimalCV is available on GitHub, along with detailed documentation on training CV models using custom data and deploying ShinyAnimalCV locally to allow users to fully leverage the capabilities of the application. ShinyAnimalCV can contribute to CV research and teaching in the animal science community.
Authors: Canyu Zhang, Qing Guo, Xiaoguang Li, Renjie Wan, Hongkai Yu, Ivor Tsang, Song Wang
In this work, we introduce a challenging image restoration task, referred to as SuperInpaint, which aims to reconstruct missing regions in low-resolution images and generate completed images with arbitrarily higher resolutions. We have found that this task cannot be effectively addressed by stacking state-of-the-art super-resolution and image inpainting methods as they amplify each other's flaws, leading to noticeable artifacts. To overcome these limitations, we propose the detail-enhanced attentional implicit representation (DEAR) that can achieve SuperInpaint with a single model, resulting in high-quality completed images with arbitrary resolutions. Specifically, we use a deep convolutional network to extract the latent embedding of an input image and then enhance the high-frequency components of the latent embedding via an adaptive high-pass filter. This leads to detail-enhanced semantic embedding. We further feed the semantic embedding into an unmask-attentional module that suppresses embeddings from ineffective masked pixels. Additionally, we extract a pixel-wise importance map that indicates which pixels should be used for image reconstruction. Given the coordinates of a pixel we want to reconstruct, we first collect its neighboring pixels in the input image and extract their detail-enhanced semantic embeddings, unmask-attentional semantic embeddings, importance values, and spatial distances to the desired pixel. Then, we feed all the above terms into an implicit representation and generate the color of the specified pixel. To evaluate our method, we extend three existing datasets for this new task and build 18 meaningful baselines using SOTA inpainting and super-resolution methods. Extensive experimental results demonstrate that our method outperforms all existing methods by a significant margin on four widely used metrics.
Authors: Meike Nauta, Christin Seifert
Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, thereby combining classification and explanation. Despite the recent attention for intrinsically interpretable models, there is no comprehensive overview on evaluating the explanation quality of interpretable part-prototype models. Based on the Co-12 properties for explanation quality as introduced in arXiv:2201.08164 (e.g., correctness, completeness, compactness), we review existing work that evaluates part-prototype models, reveal research gaps and outline future approaches for evaluation of the explanation quality of part-prototype models. This paper, therefore, contributes to the progression and maturity of this relatively new research field on interpretable part-prototype models. We additionally provide a ``Co-12 cheat sheet'' that acts as a concise summary of our findings on evaluating part-prototype models.
Authors: Soorena Salari, Amirhossein Rasoulian, Hassan Rivaz, Yiming Xiao
In brain tumor resection, accurate removal of cancerous tissues while preserving eloquent regions is crucial to the safety and outcomes of the treatment. However, intra-operative tissue deformation (called brain shift) can move the surgical target and render the pre-surgical plan invalid. Intra-operative ultrasound (iUS) has been adopted to provide real-time images to track brain shift, and inter-modal (i.e., MRI-iUS) registration is often required to update the pre-surgical plan. Quality control for the registration results during surgery is important to avoid adverse outcomes, but manual verification faces great challenges due to difficult 3D visualization and the low contrast of iUS. Automatic algorithms are urgently needed to address this issue, but the problem was rarely attempted. Therefore, we propose a novel deep learning technique based on 3D focal modulation in conjunction with uncertainty estimation to accurately assess MRI-iUS registration errors for brain tumor surgery. Developed and validated with the public RESECT clinical database, the resulting algorithm can achieve an estimation error of 0.59+-0.57 mm.
Authors: Ross Greer, Akshay Gopalkrishnan, Maitrayee Keskar, Mohan Trivedi
This paper explores the representation of vehicle lights in computer vision and its implications for various tasks in the field of autonomous driving. Different specifications for representing vehicle lights, including bounding boxes, center points, corner points, and segmentation masks, are discussed in terms of their strengths and weaknesses. Three important tasks in autonomous driving that can benefit from vehicle light detection are identified: nighttime vehicle detection, 3D vehicle orientation estimation, and dynamic trajectory cues. Each task may require a different representation of the light. The challenges of collecting and annotating large datasets for training data-driven models are also addressed, leading to introduction of the LISA Vehicle Lights Dataset and associated Light Visibility Model, which provides light annotations specifically designed for downstream applications in vehicle detection, intent and trajectory prediction, and safe path planning. A comparison of existing vehicle light datasets is provided, highlighting the unique features and limitations of each dataset. Overall, this paper provides insights into the representation of vehicle lights and the importance of accurate annotations for training effective detection models in autonomous driving applications. Our dataset and model are made available at https://cvrr.ucsd.edu/vehicle-lights-dataset
Authors: Soorena Salari, Amirhossein Rasoulian, Hassan Rivaz, Yiming Xiao
Homologous anatomical landmarks between medical scans are instrumental in quantitative assessment of image registration quality in various clinical applications, such as MRI-ultrasound registration for tissue shift correction in ultrasound-guided brain tumor resection. While manually identified landmark pairs between MRI and ultrasound (US) have greatly facilitated the validation of different registration algorithms for the task, the procedure requires significant expertise, labor, and time, and can be prone to inter- and intra-rater inconsistency. So far, many traditional and machine learning approaches have been presented for anatomical landmark detection, but they primarily focus on mono-modal applications. Unfortunately, despite the clinical needs, inter-modal/contrast landmark detection has very rarely been attempted. Therefore, we propose a novel contrastive learning framework to detect corresponding landmarks between MRI and intra-operative US scans in neurosurgery. Specifically, two convolutional neural networks were trained jointly to encode image features in MRI and US scans to help match the US image patch that contain the corresponding landmarks in the MRI. We developed and validated the technique using the public RESECT database. With a mean landmark detection accuracy of 5.88+-4.79 mm against 18.78+-4.77 mm with SIFT features, the proposed method offers promising results for MRI-US landmark detection in neurosurgical applications for the first time.
Authors: Thomas Manzini, Robin Murphy
This paper details the challenges in applying two computer vision systems, an EfficientDET supervised learning model and the unsupervised RX spectral classifier, to 98.9 GB of drone imagery from the Wu-Murad wilderness search and rescue (WSAR) effort in Japan and identifies 3 directions for future research. There have been at least 19 proposed approaches and 3 datasets aimed at locating missing persons in drone imagery, but only 3 approaches (2 unsupervised and 1 of an unknown structure) are referenced in the literature as having been used in an actual WSAR operation. Of these proposed approaches, the EfficientDET architecture and the unsupervised spectral RX classifier were selected as the most appropriate for this setting. The EfficientDET model was applied to the HERIDAL dataset and despite achieving performance that is statistically equivalent to the state-of-the-art, the model fails to translate to the real world in terms of false positives (e.g., identifying tree limbs and rocks as people), and false negatives (e.g., failing to identify members of the search team). The poor results in practice for algorithms that showed good results on datasets suggest 3 areas of future research: more realistic datasets for wilderness SAR, computer vision models that are capable of seamlessly handling the variety of imagery that can be collected during actual WSAR operations, and better alignment on performance measures.
Authors: Sandika Biswas, Kejie Li, Biplab Banerjee, Subhasis Chaudhuri, Hamid Rezatofighi
Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image. The existing research mainly proposes optimization-based approaches for reconstructing the scene from a sequence of RGB frames with explicitly defined physical laws and constraints between different scene elements (humans and objects). However, it is hard to explicitly define and model every physical law in every scenario. This paper proposes using an implicit feature representation of the scene elements to distinguish a physically plausible alignment of humans and objects from an implausible one. We propose using a graph-based holistic representation with an encoded physical representation of the scene to analyze the human-object and object-object interactions within the scene. Using this graphical representation, we adversarially train our model to learn the feasible alignments of the scene elements from the training data itself without explicitly defining the laws and constraints between them. Unlike the existing inference-time optimization-based approaches, we use this adversarially trained model to produce a per-frame 3D reconstruction of the scene that abides by the physical laws and constraints. Our learning-based method achieves comparable 3D reconstruction quality to existing optimization-based holistic human-scene reconstruction methods and does not need inference time optimization. This makes it better suited when compared to existing methods, for potential use in robotic applications, such as robot navigation, etc.
Authors: Akshay Gopalkrishnan, Ross Greer, Maitrayee Keskar, Mohan Trivedi
Vehicle light detection is required for important downstream safe autonomous driving tasks, such as predicting a vehicle's light state to determine if the vehicle is making a lane change or turning. Currently, many vehicle light detectors use single-stage detectors which predict bounding boxes to identify a vehicle light, in a manner decoupled from vehicle instances. In this paper, we present a method for detecting a vehicle light given an upstream vehicle detection and approximation of a visible light's center. Our method predicts four approximate corners associated with each vehicle light. We experiment with CNN architectures, data augmentation, and contextual preprocessing methods designed to reduce surrounding-vehicle confusion. We achieve an average distance error from the ground truth corner of 5.09 pixels, about 17.24% of the size of the vehicle light on average. We train and evaluate our model on the LISA Lights dataset, allowing us to thoroughly evaluate our vehicle light corner detection model on a large variety of vehicle light shapes and lighting conditions. We propose that this model can be integrated into a pipeline with vehicle detection and vehicle light center detection to make a fully-formed vehicle light detection network, valuable to identifying trajectory-informative signals in driving scenes.
Authors: Rongqin Liang, Yuanman Li, Yingxin Yi, Jiantao Zhou, Xia Li
Identifying traffic accidents in driving videos is crucial to ensuring the safety of autonomous driving and driver assistance systems. To address the potential danger caused by the long-tailed distribution of driving events, existing traffic accident detection (TAD) methods mainly rely on unsupervised learning. However, TAD is still challenging due to the rapid movement of cameras and dynamic scenes in driving scenarios. Existing unsupervised TAD methods mainly rely on a single pretext task, i.e., an appearance-based or future object localization task, to detect accidents. However, appearance-based approaches are easily disturbed by the rapid movement of the camera and changes in illumination, which significantly reduce the performance of traffic accident detection. Methods based on future object localization may fail to capture appearance changes in video frames, making it difficult to detect ego-involved accidents (e.g., out of control of the ego-vehicle). In this paper, we propose a novel memory-augmented multi-task collaborative framework (MAMTCF) for unsupervised traffic accident detection in driving videos. Different from previous approaches, our method can more accurately detect both ego-involved and non-ego accidents by simultaneously modeling appearance changes and object motions in video frames through the collaboration of optical flow reconstruction and future object localization tasks. Further, we introduce a memory-augmented motion representation mechanism to fully explore the interrelation between different types of motion representations and exploit the high-level features of normal traffic patterns stored in memory to augment motion representations, thus enlarging the difference from anomalies. Experimental results on recently published large-scale dataset demonstrate that our method achieves better performance compared to previous state-of-the-art approaches.
Authors: Yuxiang Guo, Cheng Peng, Ram Prabhakar, Chun Pong Lau, Rama Chellappa
Gait recognition holds the promise of robustly identifying subjects based on their walking patterns instead of color information. While previous approaches have performed well for curated indoor scenes, they have significantly impeded applicability in unconstrained situations, e.g. outdoor, long distance scenes. We propose an end-to-end GAit DEtection and Recognition (GADER) algorithm for human authentication in challenging outdoor scenarios. Specifically, GADER leverages a Double Helical Signature to detect the fragment of human movement and incorporates a novel gait recognition method, which learns representations by distilling from an auxiliary RGB recognition model. At inference time, GADER only uses the silhouette modality but benefits from a more robust representation. Extensive experiments on indoor and outdoor datasets demonstrate that the proposed method outperforms the State-of-The-Arts for gait recognition and verification, with a significant 20.6% improvement on unconstrained, long distance scenes.
Authors: Hyoung Suk Park, Kiwan Jeon, Jin Keun Seo
This study introduces a novel reconstruction method for dental cone-beam computed tomography (CBCT), focusing on effectively reducing metal-induced artifacts commonly encountered in the presence of prevalent metallic implants. Despite significant progress in metal artifact reduction techniques, challenges persist owing to the intricate physical interactions between polychromatic X-ray beams and metal objects, which are further compounded by the additional effects associated with metal-tooth interactions and factors specific to the dental CBCT data environment. To overcome these limitations, we propose an implicit neural network that generates two distinct and informative tomographic images. One image represents the monochromatic attenuation distribution at a specific energy level, whereas the other captures the nonlinear beam-hardening factor resulting from the polychromatic nature of X-ray beams. In contrast to existing CT reconstruction techniques, the proposed method relies exclusively on the Beer--Lambert law, effectively preventing the generation of metal-induced artifacts during the backprojection process commonly implemented in conventional methods. Extensive experimental evaluations demonstrate that the proposed method effectively reduces metal artifacts while providing high-quality image reconstructions, thus emphasizing the significance of the second image in capturing the nonlinear beam-hardening factor.
Authors: Liang Xu, Mingxiao Chen, Yi Cheng, Pengfei Shao, Shuwei Shen, Peng Yao, Ronald X.Xu
The UNet architecture, based on Convolutional Neural Networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. To overcome these challenges, we propose a 2D medical image segmentation model called Multi-scale Cross Perceptron Attention Network (MCPA). The MCPA consists of three main components: an encoder, a decoder, and a Cross Perceptron. The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model global dependencies. Furthermore, we introduce a Progressive Dual-branch Structure to address the semantic segmentation of the image involving finer tissue structures. This structure gradually shifts the segmentation focus of MCPA network training from large-scale structural features to more sophisticated pixel-level features. We evaluate our proposed MCPA model on several publicly available medical image datasets from different tasks and devices, including the open large-scale dataset of CT (Synapse), MRI (ACDC), fundus camera (DRIVE, CHASE_DB1, HRF), and OCTA (ROSE). The experimental results show that our MCPA model achieves state-of-the-art performance. The code is available at https://github.com/simonustc/MCPA-for-2D-Medical-Image-Segmentation.
Authors: Junchao Huang, Xiaoqi He, Sheng Zhao
The purpose of multi-object tracking (MOT) is to continuously track and identify objects detected in videos. Currently, most methods for multi-object tracking model the motion information and combine it with appearance information to determine and track objects. In this paper, unfalsified control is employed to address the ID-switch problem in multi-object tracking. We establish sequences of appearance information variations for the trajectories during the tracking process and design a detection and rectification module specifically for ID-switch detection and recovery. We also propose a simple and effective strategy to address the issue of ambiguous matching of appearance information during the data association process. Experimental results on publicly available MOT datasets demonstrate that the tracker exhibits excellent effectiveness and robustness in handling tracking errors caused by occlusions and rapid movements.
Authors: Pu Sun, Honggang Qi, Yuezun Li, Siwei Lyu
Face-swap DeepFake is an emerging AI-based face forgery technique that can replace the original face in a video with a generated face of the target identity while retaining consistent facial attributes such as expression and orientation. Due to the high privacy of faces, the misuse of this technique can raise severe social concerns, drawing tremendous attention to defend against DeepFakes recently. In this paper, we describe a new proactive defense method called FakeTracer to expose face-swap DeepFakes via implanting traces in training. Compared to general face-synthesis DeepFake, the face-swap DeepFake is more complex as it involves identity change, is subjected to the encoding-decoding process, and is trained unsupervised, increasing the difficulty of implanting traces into the training phase. To effectively defend against face-swap DeepFake, we design two types of traces, sustainable trace (STrace) and erasable trace (ETrace), to be added to training faces. During the training, these manipulated faces affect the learning of the face-swap DeepFake model, enabling it to generate faces that only contain sustainable traces. In light of these two traces, our method can effectively expose DeepFakes by identifying them. Extensive experiments are conducted on the Celeb-DF dataset, compared with recent passive and proactive defense methods, and are studied thoroughly regarding various factors, corroborating the efficacy of our method on defending against face-swap DeepFake.
Authors: Bingxue Wang, Liwen Zou, Jun Chen, Yingying Cao, Zhenghua Cai, Yudong Qiu, Liang Mao, Zhongqiu Wang, Jingya Chen, Luying Gui, Xiaoping Yang
The presence of tertiary lymphoid structures (TLSs) on pancreatic pathological images is an important prognostic indicator of pancreatic tumors. Therefore, TLSs detection on pancreatic pathological images plays a crucial role in diagnosis and treatment for patients with pancreatic tumors. However, fully supervised detection algorithms based on deep learning usually require a large number of manual annotations, which is time-consuming and labor-intensive. In this paper, we aim to detect the TLSs in a manner of few-shot learning by proposing a weakly supervised segmentation network. We firstly obtain the lymphocyte density maps by combining a pretrained model for nuclei segmentation and a domain adversarial network for lymphocyte nuclei recognition. Then, we establish a cross-scale attention guidance mechanism by jointly learning the coarse-scale features from the original histopathology images and fine-scale features from our designed lymphocyte density attention. A noise-sensitive constraint is introduced by an embedding signed distance function loss in the training procedure to reduce tiny prediction errors. Experimental results on two collected datasets demonstrate that our proposed method significantly outperforms the state-of-the-art segmentation-based algorithms in terms of TLSs detection accuracy. Additionally, we apply our method to study the congruent relationship between the density of TLSs and peripancreatic vascular invasion and obtain some clinically statistical results.
Authors: Tuo Feng, Wenguan Wang, Xiaohan Wang, Yi Yang, Qinghua Zheng
Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc. Current studies put much focus on the adaption of neural networks to the complex geometries of point clouds, but are blind to a fundamental question: how to learn an appropriate point embedding space that is aware of both discriminative semantics and challenging variations? As a response, we propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space for automatically discovering subclass patterns which are latent yet representative across scenes. The mined patterns are, in turn, used to repaint the embedding space, so as to respect the underlying distribution of the entire training dataset and improve the robustness to the variations. Our algorithm is principled and readily pluggable to modern point cloud segmentation networks during training, without extra overhead during testing. With various 3D network architectures (i.e., voxel-based, point-based, Transformer-based, automatically searched), our algorithm shows notable improvements on famous point cloud segmentation datasets (i.e.,2.0-2.6% on single-scan and 2.0-2.2% multi-scan of SemanticKITTI, 1.8-1.9% on S3DIS, in terms of mIoU). Our algorithm also demonstrates utility in 3D detection, showing 2.0-3.4% mAP gains on KITTI.
Authors: Moon Ye-Bin, Jisoo Kim, Hongyeob Kim, Kilho Son, Tae-Hyun Oh
Recent label mix-based augmentation methods have shown their effectiveness in generalization despite their simplicity, and their favorable effects are often attributed to semantic-level augmentation. However, we found that they are vulnerable to highly skewed class distribution, because scarce data classes are rarely sampled for inter-class perturbation. We propose TextManiA, a text-driven manifold augmentation method that semantically enriches visual feature spaces, regardless of data distribution. TextManiA augments visual data with intra-class semantic perturbation by exploiting easy-to-understand visually mimetic words, i.e., attributes. To this end, we bridge between the text representation and a target visual feature space, and propose an efficient vector augmentation. To empirically support the validity of our design, we devise two visualization-based analyses and show the plausibility of the bridge between two different modality spaces. Our experiments demonstrate that TextManiA is powerful in scarce samples with class imbalance as well as even distribution. We also show compatibility with the label mix-based approaches in evenly distributed scarce data.
Authors: Jing Wu, Naira Hovakimyan, Jennifer Hobbs
Classifying and segmenting patterns from a limited number of examples is a significant challenge in remote sensing and earth observation due to the difficulty in acquiring accurately labeled data in large quantities. Previous studies have shown that meta-learning, which involves episodic training on query and support sets, is a promising approach. However, there has been little attention paid to direct fine-tuning techniques. This paper repurposes contrastive learning as a pre-training method for few-shot learning for classification and semantic segmentation tasks. Specifically, we introduce a generator-based contrastive learning framework (GenCo) that pre-trains backbones and simultaneously explores variants of feature samples. In fine-tuning, the auxiliary generator can be used to enrich limited labeled data samples in feature space. We demonstrate the effectiveness of our method in improving few-shot learning performance on two key remote sensing datasets: Agriculture-Vision and EuroSAT. Empirically, our approach outperforms purely supervised training on the nearly 95,000 images in Agriculture-Vision for both classification and semantic segmentation tasks. Similarly, the proposed few-shot method achieves better results on the land-cover classification task on EuroSAT compared to the results obtained from fully supervised model training on the dataset.
Authors: Min Ren, Yunlong Wang, Yuhao Zhu, Kunbo Zhang, Zhenan Sun
Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods.
Authors: Chenfeng Xu, Bichen Wu, Ji Hou, Sam Tsai, Ruilong Li, Jialiang Wang, Wei Zhan, Zijian He, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our method makes novel use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection performance. Specifically, to avoid the significant extra latency associated with per-scene optimization of NeRF, we introduce sufficient geometry priors to enhance the generalizability of NeRF-MLP. Furthermore, we subtly connect the detection and NeRF branches through a shared MLP, enabling an efficient adaptation of NeRF to detection and yielding geometry-aware volumetric representations for 3D detection. Our method outperforms state-of-the-arts by 3.9 mAP and 3.1 mAP on the ScanNet and ARKITScenes benchmarks, respectively. We provide extensive analysis to shed light on how NeRF-Det works. As a result of our joint-training design, NeRF-Det is able to generalize well to unseen scenes for object detection, view synthesis, and depth estimation tasks without requiring per-scene optimization. Code is available at \url{https://github.com/facebookresearch/NeRF-Det}.
Authors: Chengrui Wei, Meng Yang, Lei He, Nanning Zheng
It has long been an ill-posed problem to predict absolute depth maps from single images in real (unseen) indoor scenes. We observe that it is essentially due to not only the scale-ambiguous problem but also the focal-ambiguous problem that decreases the generalization ability of monocular depth estimation. That is, images may be captured by cameras of different focal lengths in scenes of different scales. In this paper, we develop a focal-and-scale depth estimation model to well learn absolute depth maps from single images in unseen indoor scenes. First, a relative depth estimation network is adopted to learn relative depths from single images with diverse scales/semantics. Second, multi-scale features are generated by mapping a single focal length value to focal length features and concatenating them with intermediate features of different scales in relative depth estimation. Finally, relative depths and multi-scale features are jointly fed into an absolute depth estimation network. In addition, a new pipeline is developed to augment the diversity of focal lengths of public datasets, which are often captured with cameras of the same or similar focal lengths. Our model is trained on augmented NYUDv2 and tested on three unseen datasets. Our model considerably improves the generalization ability of depth estimation by 41%/13% (RMSE) with/without data augmentation compared with five recent SOTAs and well alleviates the deformation problem in 3D reconstruction. Notably, our model well maintains the accuracy of depth estimation on original NYUDv2.
Authors: Huajian Huang, Yinzhe Xu, Yingshu Chen, Sai-Kit Yeung
360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception. In this paper, we explore 360{\deg} images for visual object tracking and perceive new challenges caused by large distortion, stitching artifacts, and other unique attributes of 360{\deg} images. To alleviate these problems, we take advantage of novel representations of target localization, i.e., bounding field-of-view, and then introduce a general 360 tracking framework that can adopt typical trackers for omnidirectional tracking. More importantly, we propose a new large-scale omnidirectional tracking benchmark dataset, 360VOT, in order to facilitate future research. 360VOT contains 120 sequences with up to 113K high-resolution frames in equirectangular projection. The tracking targets cover 32 categories in diverse scenarios. Moreover, we provide 4 types of unbiased ground truth, including (rotated) bounding boxes and (rotated) bounding field-of-views, as well as new metrics tailored for 360{\deg} images which allow for the accurate evaluation of omnidirectional tracking performance. Finally, we extensively evaluated 20 state-of-the-art visual trackers and provided a new baseline for future comparisons. Homepage: https://360vot.hkustvgd.com
Authors: Razi Mahmood, Ge Wang, Mannudeep Kalra, Pingkun Yan
With advances in generative artificial intelligence (AI), it is now possible to produce realistic-looking automated reports for preliminary reads of radiology images. This can expedite clinical workflows, improve accuracy and reduce overall costs. However, it is also well-known that such models often hallucinate, leading to false findings in the generated reports. In this paper, we propose a new method of fact-checking of AI-generated reports using their associated images. Specifically, the developed examiner differentiates real and fake sentences in reports by learning the association between an image and sentences describing real or potentially fake findings. To train such an examiner, we first created a new dataset of fake reports by perturbing the findings in the original ground truth radiology reports associated with images. Text encodings of real and fake sentences drawn from these reports are then paired with image encodings to learn the mapping to real/fake labels. The utility of such an examiner is demonstrated for verifying automatically generated reports by detecting and removing fake sentences. Future generative AI approaches can use the resulting tool to validate their reports leading to a more responsible use of AI in expediting clinical workflows.
Authors: Zhifeng Wang, Kaihao Zhang, Wenhan Luo, Ramesh Sankaranarayana
Facial expression is related to facial muscle contractions and different muscle movements correspond to different emotional states. For micro-expression recognition, the muscle movements are usually subtle, which has a negative impact on the performance of current facial emotion recognition algorithms. Most existing methods use self-attention mechanisms to capture relationships between tokens in a sequence, but they do not take into account the inherent spatial relationships between facial landmarks. This can result in sub-optimal performance on micro-expression recognition tasks.Therefore, learning to recognize facial muscle movements is a key challenge in the area of micro-expression recognition. In this paper, we propose a Hierarchical Transformer Network (HTNet) to identify critical areas of facial muscle movement. HTNet includes two major components: a transformer layer that leverages the local temporal features and an aggregation layer that extracts local and global semantical facial features. Specifically, HTNet divides the face into four different facial areas: left lip area, left eye area, right eye area and right lip area. The transformer layer is used to focus on representing local minor muscle movement with local self-attention in each area. The aggregation layer is used to learn the interactions between eye areas and lip areas. The experiments on four publicly available micro-expression datasets show that the proposed approach outperforms previous methods by a large margin. The codes and models are available at: \url{https://github.com/wangzhifengharrison/HTNet}
Authors: Yingbo Zhou, Zhihao Yue, Yutong Ye, Pengyu Zhang, Xian Wei, Mingsong Chen
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. To address this problem, we propose a novel feature Equalization fusion Generative Adversarial Network (EqGAN) for few-shot image generation. Unlike existing fusion strategies that rely on either deep features or local representations, we design two separate branches to fuse structures and textures by disentangling encoded features into shallow and deep contents. To refine image contents at all feature levels, we equalize the fused structure and texture semantics at different scales and supplement the decoder with richer information by skip connections. Since the fused structures and textures may be inconsistent with each other, we devise a consistent equalization loss between the equalized features and the intermediate output of the decoder to further align the semantics. Comprehensive experiments on three public datasets demonstrate that, EqGAN not only significantly improves generation performance with FID score (by up to 32.7%) and LPIPS score (by up to 4.19%), but also outperforms the state-of-the-arts in terms of accuracy (by up to 1.97%) for downstream classification tasks.
Authors: Xin Yuan, Linjie Li, Jianfeng Wang, Zhengyuan Yang, Kevin Lin, Zicheng Liu, Lijuan Wang
In this paper, we study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis. Considering the wavelet transform represents the image in spatial and frequency domains, we carefully design a novel architecture SFUNet to effectively capture the correlation for both domains. Specifically, in the standard denoising U-Net for pixel data, we supplement the 2D convolutions and spatial-only attention layers with our spatial frequency-aware convolution and attention modules to jointly model the complementary information from spatial and frequency domains in wavelet data. Our new architecture can be used as a drop-in replacement to the pixel-based network and is compatible with the vanilla DDPM training process. By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on CIFAR-10, FFHQ, LSUN-Bedroom, and LSUN-Church datasets, than the pixel-based counterpart.
Authors: Tao Wang, Kaihao Zhang, Ziqian Shao, Wenhan Luo, Bjorn Stenger, Tae-Kyun Kim, Wei Liu, Hongdong Li
Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. However, these methods often overlook the importance of considering degradation representations, which can lead to sub-optimal outcomes. In this paper, we address this limitation by proposing a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process, resulting in improved image enhancement. Our proposed degradation-aware learning scheme is based on the understanding that degradation representations play a crucial role in accurately modeling and capturing the specific degradation patterns present in low-light images. To this end, First, a joint learning framework for both image generation and image enhancement is presented to learn the degradation representations. Second, to leverage the learned degradation representations, we develop a Low-Light Diffusion model (LLDiffusion) with a well-designed dynamic diffusion module. This module takes into account both the color map and the latent degradation representations to guide the diffusion process. By incorporating these conditioning factors, the proposed LLDiffusion can effectively enhance low-light images, considering both the inherent degradation patterns and the desired color fidelity. Finally, we evaluate our proposed method on several well-known benchmark datasets, including synthetic and real-world unpaired datasets. Extensive experiments on public benchmarks demonstrate that our LLDiffusion outperforms state-of-the-art LLIE methods both quantitatively and qualitatively. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLDiffusion.
Authors: Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu
Physical adversarial attacks have put a severe threat to DNN-based object detectors. To enhance security, a combination of visible and infrared sensors is deployed in various scenarios, which has proven effective in disabling existing single-modal physical attacks. To further demonstrate the potential risks in such cases, we design a unified adversarial patch that can perform cross-modal physical attacks, achieving evasion in both modalities simultaneously with a single patch. Given the different imaging mechanisms of visible and infrared sensors, our work manipulates patches' shape features, which can be captured in different modalities when they undergo changes. To deal with challenges, we propose a novel boundary-limited shape optimization approach that aims to achieve compact and smooth shapes for the adversarial patch, making it easy to implement in the physical world. And a score-aware iterative evaluation method is also introduced to balance the fooling degree between visible and infrared detectors during optimization, which guides the adversarial patch to iteratively reduce the predicted scores of the multi-modal sensors. Furthermore, we propose an Affine-Transformation-based enhancement strategy that makes the learnable shape robust to various angles, thus mitigating the issue of shape deformation caused by different shooting angles in the real world. Our method is evaluated against several state-of-the-art object detectors, achieving an Attack Success Rate (ASR) of over 80%. We also demonstrate the effectiveness of our approach in physical-world scenarios under various settings, including different angles, distances, postures, and scenes for both visible and infrared sensors.
Authors: Sergio {Naval Marimont}, Vasilis Siomos, Giacomo Tarroni
Unsupervised Out-of-Distribution (OOD) detection consists in identifying anomalous regions in images leveraging only models trained on images of healthy anatomy. An established approach is to tokenize images and model the distribution of tokens with Auto-Regressive (AR) models. AR models are used to 1) identify anomalous tokens and 2) in-paint anomalous representations with in-distribution tokens. However, AR models are slow at inference time and prone to error accumulation issues which negatively affect OOD detection performance. Our novel method, MIM-OOD, overcomes both speed and error accumulation issues by replacing the AR model with two task-specific networks: 1) a transformer optimized to identify anomalous tokens and 2) a transformer optimized to in-paint anomalous tokens using masked image modelling (MIM). Our experiments with brain MRI anomalies show that MIM-OOD substantially outperforms AR models (DICE 0.458 vs 0.301) while achieving a nearly 25x speedup (9.5s vs 244s).
Authors: Ali Reza Omrani, Davide Moroni
Thanks to High Dynamic Range (HDR) imaging methods, the scope of photography has seen profound changes recently. To be more specific, such methods try to reconstruct the lost luminosity of the real world caused by the limitation of regular cameras from the Low Dynamic Range (LDR) images. Additionally, although the State-Of-The-Art methods in this topic perform well, they mainly concentrate on combining different exposures and have less attention to extracting the informative parts of the images. Thus, this paper aims to introduce a new model capable of incorporating information from the most visible areas of each image extracted by a visual attention module (VAM), which is a result of a segmentation strategy. In particular, the model, based on a deep learning architecture, utilizes the extracted areas to produce the final HDR image. The results demonstrate that our method outperformed most of the State-Of-The-Art algorithms.
Authors: Jianan Fan, Dongnan Liu, Hang Chang, Heng Huang, Mei Chen, Weidong Cai
The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. However, they generally operate under the closed-set adaptation setting assuming an identical label set between the source and target domains, which is over-restrictive in clinical practice where new classes commonly exist across datasets due to taxonomic inconsistency. While several methods have been presented to tackle both domain shifts and incoherent label sets, none of them take into account the common characteristics of the two issues and consider the learning dynamics along network training. In this work, we propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective. It exploits the low-rank nature of gradient space and devises a dual-stream distillation algorithm to regularize the learning dynamics of insufficiently annotated domain and classes with the external guidance obtained from reliable sources. Our approach resolves the issue of inadequate navigation along network optimization, which is the major obstacle in the taxonomy adaptive cross-domain adaptation scenario. We evaluate the proposed method extensively on several tasks towards various endpoints with clinical and open-world significance. The results demonstrate its effectiveness and improvements over previous methods.
Authors: Ryo Nakamura1, Hirokatsu Kataoka, Sora Takashima, Edgar Josafat Martinez Noriega, Rio Yokota, Nakamasa Inoue
Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks. These synthetic images are categorized according to the parameters in the mathematical formula that generate them. In the present work, we hypothesize that the process for generating different instances for the same category in FDSL, can be viewed as a form of data augmentation. We validate this hypothesis by replacing the instances with data augmentation, which means we only need a single image per category. Our experiments shows that this one-instance fractal database (OFDB) performs better than the original dataset where instances were explicitly generated. We further scale up OFDB to 21,000 categories and show that it matches, or even surpasses, the model pre-trained on ImageNet-21k in ImageNet-1k fine-tuning. The number of images in OFDB is 21k, whereas ImageNet-21k has 14M. This opens new possibilities for pre-training vision transformers with much smaller datasets.
Authors: Adrian Cosma, Emilian Radoi
Gait, the manner of walking, has been proven to be a reliable biometric with uses in surveillance, marketing and security. A promising new direction for the field is training gait recognition systems without explicit human annotations, through self-supervised learning approaches. Such methods are heavily reliant on strong augmentations for the same walking sequence to induce more data variability and to simulate additional walking variations. Current data augmentation schemes are heuristic and cannot provide the necessary data variation as they are only able to provide simple temporal and spatial distortions. In this work, we propose GaitMorph, a novel method to modify the walking variation for an input gait sequence. Our method entails the training of a high-compression model for gait skeleton sequences that leverages unlabelled data to construct a discrete and interpretable latent space, which preserves identity-related features. Furthermore, we propose a method based on optimal transport theory to learn latent transport maps on the discrete codebook that morph gait sequences between variations. We perform extensive experiments and show that our method is suitable to synthesize additional views for an input sequence.
Authors: Bo Yang, Xinyu Zhang, Jiahao Zhu, Jian Zhang, Dongjian Tian, Jun Luo, Mingliang Zhou, Yangjun Pi
Single-frame infrared small target detection is considered to be a challenging task, due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small targets, and small target information is easy to lose in the high-level semantic layer. In this paper, we propose an enhancing feature learning network (EFLNet) based on YOLOv7 framework to solve these problems. First, we notice that there is an extremely imbalance between the target and the background in the infrared image, which makes the model pay more attention to the background features, resulting in missed detection. To address this problem, we propose a new adaptive threshold focal loss function that adjusts the loss weight automatically, compelling the model to allocate greater attention to target features. Second, we introduce the normalized Gaussian Wasserstein distance to alleviate the difficulty of model convergence caused by the extreme sensitivity of the bounding box regression to infrared small targets. Finally, we incorporate a dynamic head mechanism into the network to enable adaptive learning of the relative importance of each semantic layer. Experimental results demonstrate our method can achieve better performance in the detection performance of infrared small targets compared to state-of-the-art deep-learning based methods.
Authors: Mikhail Goncharov, Vera Soboleva, Anvar Kurmukov, Maxim Pisov, Mikhail Belyaev
This paper introduces vox2vec - a contrastive method for self-supervised learning (SSL) of voxel-level representations. vox2vec representations are modeled by a Feature Pyramid Network (FPN): a voxel representation is a concatenation of the corresponding feature vectors from different pyramid levels. The FPN is pre-trained to produce similar representations for the same voxel in different augmented contexts and distinctive representations for different voxels. This results in unified multi-scale representations that capture both global semantics (e.g., body part) and local semantics (e.g., different small organs or healthy versus tumor tissue). We use vox2vec to pre-train a FPN on more than 6500 publicly available computed tomography images. We evaluate the pre-trained representations by attaching simple heads on top of them and training the resulting models for 22 segmentation tasks. We show that vox2vec outperforms existing medical imaging SSL techniques in three evaluation setups: linear and non-linear probing and end-to-end fine-tuning. Moreover, a non-linear head trained on top of the frozen vox2vec representations achieves competitive performance with the FPN trained from scratch while having 50 times fewer trainable parameters. The code is available at https://github.com/mishgon/vox2vec .
Authors: Ruikai Cui, Shi Qiu, Saeed Anwar, Jiawei Liu, Chaoyue Xing, Jing Zhang, Nick Barnes
Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. In contrast to previous approaches, we present Partial2Complete (P2C), the first self-supervised framework that completes point cloud objects using training samples consisting of only a single incomplete point cloud per object. Specifically, our framework groups incomplete point clouds into local patches as input and predicts masked patches by learning prior information from different partial objects. We also propose Region-Aware Chamfer Distance to regularize shape mismatch without limiting completion capability, and devise the Normal Consistency Constraint to incorporate a local planarity assumption, encouraging the recovered shape surface to be continuous and complete. In this way, P2C no longer needs multiple observations or complete point clouds as ground truth. Instead, structural cues are learned from a category-specific dataset to complete partial point clouds of objects. We demonstrate the effectiveness of our approach on both synthetic ShapeNet data and real-world ScanNet data, showing that P2C produces comparable results to methods trained with complete shapes, and outperforms methods learned with multiple partial observations. Code is available at https://github.com/CuiRuikai/Partial2Complete.
Authors: Till J. Bungert, Levin Kobelke, Paul F. Jaeger
To ensure the reliable use of classification systems in medical applications, it is crucial to prevent silent failures. This can be achieved by either designing classifiers that are robust enough to avoid failures in the first place, or by detecting remaining failures using confidence scoring functions (CSFs). A predominant source of failures in image classification is distribution shifts between training data and deployment data. To understand the current state of silent failure prevention in medical imaging, we conduct the first comprehensive analysis comparing various CSFs in four biomedical tasks and a diverse range of distribution shifts. Based on the result that none of the benchmarked CSFs can reliably prevent silent failures, we conclude that a deeper understanding of the root causes of failures in the data is required. To facilitate this, we introduce SF-Visuals, an interactive analysis tool that uses latent space clustering to visualize shifts and failures. On the basis of various examples, we demonstrate how this tool can help researchers gain insight into the requirements for safe application of classification systems in the medical domain. The open-source benchmark and tool are at: https://github.com/IML-DKFZ/sf-visuals.
Authors: Subhadeep Roy, Shankhanil Mitra, Soma Biswas, Rajiv Soundararajan
While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This motivates the study of test time adaptation (TTA) techniques to improve their performance at inference time. Existing auxiliary tasks and loss functions used for TTA may not be relevant for quality-aware adaptation of the pre-trained model. In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA. In particular, we introduce a group contrastive loss at the batch level and a relative rank loss at the sample level to make the model quality aware and adapt to the target data. Our experiments reveal that even using a small batch of images from the test distribution helps achieve significant improvement in performance by updating the batch normalization statistics of the source model.
Authors: Priyansh Saxena, Raahat Gupta, Akshat Maheshwari, Saumil Maheshwari
Semantic inpainting or image completion alludes to the task of inferring arbitrary large missing regions in images based on image semantics. Since the prediction of image pixels requires an indication of high-level context, this makes it significantly tougher than image completion, which is often more concerned with correcting data corruption and removing entire objects from the input image. On the other hand, image enhancement attempts to eliminate unwanted noise and blur from the image, along with sustaining most of the image details. Efficient image completion and enhancement model should be able to recover the corrupted and masked regions in images and then refine the image further to increase the quality of the output image. Generative Adversarial Networks (GAN), have turned out to be helpful in picture completion tasks. In this chapter, we will discuss the underlying GAN architecture and how they can be used used for image completion tasks.
Authors: Zhiyuan Li, Dongnan Liu, Heng Wang, Chaoyi Zhang, Weidong Cai
Training an image captioner without annotated image-sentence pairs has gained traction in recent years. Previous approaches can be categorized into two strategies: crawling sentences from mismatching corpora and aligning them with the given images as pseudo annotations, or pre-training the captioner using external image-text pairs. However, the aligning setting seems to reach its performance limit due to the quality problem of pairs, and pre-training requires significant computational resources. To address these challenges, we propose a new strategy ``LPM + retrieval-augmented learning" where the prior knowledge from large pre-trained models (LPMs) is leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which adopts an efficient approach to retrieve highly relevant short region descriptions from the mismatching corpora and use them to generate a variety of pseudo sentences with distinct representations as well as high quality via LPMs. In addition, a fluency filter and a CLIP-guided training objective are further introduced to facilitate model optimization. Experimental results demonstrate that our method surpasses the SOTA pre-training model (Flamingo3B) by achieving a CIDEr score of 78.1 (+5.1) while utilizing only 0.3% of its trainable parameters (1.3B VS 33M). Importantly, our approach eliminates the need of computationally expensive pre-training processes on external datasets (e.g., the requirement of 312M image-text pairs for Flamingo3B). We further show that with a simple extension, the generated pseudo sentences can be deployed as weak supervision to boost the 1% semi-supervised image caption benchmark up to 93.4 CIDEr score (+8.9) which showcases the versatility and effectiveness of our approach.
Authors: Benjia Zhou, Zhigang Chen, Albert Clapés, Jun Wan, Yanyan Liang, Sergio Escalera, Zhen Lei, Du Zhang
Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods. Our code is available at https://github.com/zhoubenjia/GFSLT-VLP.
Authors: Yiqian Wu, Hao Xu, Xiangjun Tang, Hongbo Fu, Xiaogang Jin
33D-aware face generators are commonly trained on 2D real-life face image datasets. Nevertheless, existing facial recognition methods often struggle to extract face data captured from various camera angles. Furthermore, in-the-wild images with diverse body poses introduce a high-dimensional challenge for 3D-aware generators, making it difficult to utilize data that contains complete neck and shoulder regions. Consequently, these face image datasets often contain only near-frontal face data, which poses challenges for 3D-aware face generators to construct \textit{full-head} 3D portraits. To this end, we first create the dataset {$\it{360}^{\circ}$}-\textit{Portrait}-\textit{HQ} (\textit{$\it{360}^{\circ}$PHQ}), which consists of high-quality single-view real portraits annotated with a variety of camera parameters {(the yaw angles span the entire $360^{\circ}$ range)} and body poses. We then propose \textit{3DPortraitGAN}, the first 3D-aware full-head portrait generator that learns a canonical 3D avatar distribution from the body-pose-various \textit{$\it{360}^{\circ}$PHQ} dataset with body pose self-learning. Our model can generate view-consistent portrait images from all camera angles (${360}^{\circ}$) with a full-head 3D representation. We incorporate a mesh-guided deformation field into volumetric rendering to produce deformed results to generate portrait images that conform to the body pose distribution of the dataset using our canonical generator. We integrate two pose predictors into our framework to predict more accurate body poses to address the issue of inaccurately estimated body poses in our dataset. Our experiments show that the proposed framework can generate view-consistent, realistic portrait images with complete geometry from all camera angles and accurately predict portrait body pose.
Authors: Abhishek Kuriyal, Vaibhav Kumar, Bharat Lohani
LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention) mechanisms individually in semantic segmentation architectures. However, there is limited work on combining the learned representations of these attention mechanisms to improve performance. Additionally, existing research that combines convolution with self-attention relies on global attention, which is not practical for processing large point clouds. To address these challenges, this study proposes a new architecture, pCTFusion, which combines kernel-based convolutions and self-attention mechanisms for better feature learning and capturing local and global dependencies in segmentation. The proposed architecture employs two types of self-attention mechanisms, local and global, based on the hierarchical positions of the encoder blocks. Furthermore, the existing loss functions do not consider the semantic and position-wise importance of the points, resulting in reduced accuracy, particularly at sharp class boundaries. To overcome this, the study models a novel attention-based loss function called Pointwise Geometric Anisotropy (PGA), which assigns weights based on the semantic distribution of points in a neighborhood. The proposed architecture is evaluated on SemanticKITTI outdoor dataset and showed a 5-7% improvement in performance compared to the state-of-the-art architectures. The results are particularly encouraging for minor classes, often misclassified due to class imbalance, lack of space, and neighbor-aware feature encoding. These developed methods can be leveraged for the segmentation of complex datasets and can drive real-world applications of LiDAR point cloud.
Authors: Shangde Gao, Yichao Fu, Ke Liu, Yuqiang Han
Knowledge amalgamation (KA) aims to learn a compact student model to handle the joint objective from multiple teacher models that are are specialized for their own tasks respectively. Current methods focus on coarsely aligning teachers and students in the common representation space, making it difficult for the student to learn the proper decision boundaries from a set of heterogeneous teachers. Besides, the KL divergence in previous works only minimizes the probability distribution difference between teachers and the student, ignoring the intrinsic characteristics of teachers. Therefore, we propose a novel Contrastive Knowledge Amalgamation (CKA) framework, which introduces contrastive losses and an alignment loss to achieve intra-class cohesion and inter-class separation.Contrastive losses intra- and inter- models are designed to widen the distance between representations of different classes. The alignment loss is introduced to minimize the sample-level distribution differences of teacher-student models in the common representation space.Furthermore, the student learns heterogeneous unsupervised classification tasks through soft targets efficiently and flexibly in the task-level amalgamation. Extensive experiments on benchmarks demonstrate the generalization capability of CKA in the amalgamation of specific task as well as multiple tasks. Comprehensive ablation studies provide a further insight into our CKA.
Authors: Junwen He, Yifan Wang, Lijun Wang, Huchuan Lu, Jun-Yan He, Jin-Peng Lan, Bin Luo, Yifeng Geng, Xuansong Xie
Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels.
Authors: Igor Dubinin, Felix Effenberger
Residual connections have been proposed as architecture-based inductive bias to mitigate the problem of exploding and vanishing gradients and increase task performance in both feed-forward and recurrent networks (RNNs) when trained with the backpropagation algorithm. Yet, little is known about how residual connections in RNNs influence their dynamics and fading memory properties. Here, we introduce weakly coupled residual recurrent networks (WCRNNs) in which residual connections result in well-defined Lyapunov exponents and allow for studying properties of fading memory. We investigate how the residual connections of WCRNNs influence their performance, network dynamics, and memory properties on a set of benchmark tasks. We show that several distinct forms of residual connections yield effective inductive biases that result in increased network expressivity. In particular, residual connections that (i) result in network dynamics at the proximity of the edge of chaos, (ii) allow networks to capitalize on characteristic spectral properties of the data, and (iii) result in heterogeneous memory properties are shown to increase practical expressivity. In addition, we demonstrate how our results can be extended to non-linear residuals and introduce a weakly coupled residual initialization scheme that can be used for Elman RNNs
Authors: Dimitri Korsch, Maha Shadaydeh, Joachim Denzler
Fine-grained classification is a particular case of a classification problem, aiming to classify objects that share the visual appearance and can only be distinguished by subtle differences. Fine-grained classification models are often deployed to determine animal species or individuals in automated animal monitoring systems. Precise visual explanations of the model's decision are crucial to analyze systematic errors. Attention- or gradient-based methods are commonly used to identify regions in the image that contribute the most to the classification decision. These methods deliver either too coarse or too noisy explanations, unsuitable for identifying subtle visual differences reliably. However, perturbation-based methods can precisely identify pixels causally responsible for the classification result. Fill-in of the dropout (FIDO) algorithm is one of those methods. It utilizes the concrete dropout (CD) to sample a set of attribution masks and updates the sampling parameters based on the output of the classification model. A known problem of the algorithm is a high variance in the gradient estimates, which the authors have mitigated until now by mini-batch updates of the sampling parameters. This paper presents a solution to circumvent these computational instabilities by simplifying the CD sampling and reducing reliance on large mini-batch sizes. First, it allows estimating the parameters with smaller mini-batch sizes without losing the quality of the estimates but with a reduced computational effort. Furthermore, our solution produces finer and more coherent attribution masks. Finally, we use the resulting attribution masks to improve the classification performance of a trained model without additional fine-tuning of the model.
Authors: Subhankar Chattoraj, Bhargava Reddy, Manoj Tadepalli, Preetham Putha
Purpose:Chest X-ray (CXR) is an essential tool and one of the most prescribed imaging to detect pulmonary abnormalities, with a yearly estimate of over 2 billion imaging performed worldwide. However, the accurate and timely diagnosis of TB remains an unmet goal. The prevalence of TB is highest in low-middle-income countries, and the requirement of a portable, automated, and reliable solution is required. In this study, we compared the performance of DL-based devices on digital and analog CXR. The evaluated DL-based device can be used in resource-constraint settings. Methods: A total of 10,000 CXR DICOMs(.dcm) and printed photos of the films acquired with three different cellular phones - Samsung S8, iPhone 8, and iPhone XS along with their radiological report were retrospectively collected from various sites across India from April 2020 to March 2021. Results: 10,000 chest X-rays were utilized to evaluate the DL-based device in identifying radiological signs of TB. The AUC of qXR for detecting signs of tuberculosis on the original DICOMs dataset was 0.928 with a sensitivity of 0.841 at a specificity of 0.806. At an optimal threshold, the difference in the AUC of three cellular smartphones with the original DICOMs is 0.024 (2.55%), 0.048 (5.10%), and 0.038 (1.91%). The minimum difference demonstrates the robustness of the DL-based device in identifying radiological signs of TB in both digital and analog CXR.
Authors: Xiaochen Ma, Bo Du, Xianggen Liu, Ahmed Y. Al Hammadi, Jizhe Zhou
Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture artifacts. Exploiting artifacts requires the model to extract non-semantic discrepancies between the manipulated and authentic regions, which needs to compare differences between these two areas explicitly. With the self-attention mechanism, naturally, the Transformer is the best candidate. Besides, artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border. Therefore, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision. We term this simple but effective ViT paradigm as the IML-ViT, which has great potential to become a new benchmark for IML. Extensive experiments on five benchmark datasets verified our model outperforms the state-of-the-art manipulation localization methods. Code and models are available at \url{https://github.com/SunnyHaze/IML-ViT}
Authors: Matteo Ciotola, Mario Ragosta, Giovanni Poggi, Giuseppe Scarpa
This work presents a new unsupervised framework for training deep learning models for super-resolution of Sentinel-2 images by fusion of its 10-m and 20-m bands. The proposed scheme avoids the resolution downgrade process needed to generate training data in the supervised case. On the other hand, a proper loss that accounts for cycle-consistency between the network prediction and the input components to be fused is proposed. Despite its unsupervised nature, in our preliminary experiments the proposed scheme has shown promising results in comparison to the supervised approach. Besides, by construction of the proposed loss, the resulting trained network can be ascribed to the class of multi-resolution analysis methods.
Authors: Harry Cheng, Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Mohan Kankanhalli
Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting their adaptability to various backbone architectures. This paper investigates the issue of over-sampled frames, a prevalent problem in many approaches yet it has received relatively little attention. Despite the use of fewer frames being a potential solution, this approach often results in a substantial decline in performance. To address this issue, we propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. This feature restoration technique brings a negligible increase in computational requirements compared to resource-intensive image encoders, such as ViT. To evaluate the effectiveness of our method, we conduct extensive experiments on four public datasets, including Kinetics-400, ActivityNet, UCF-101, and HMDB-51. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy. In addition, our method also surprisingly helps improve the generalization ability of the models under zero-shot settings.
Authors: Peter Bauer, Arij Bouazizi, Ulrich Kressel, Fabian B. Flohr
Accurate 3D human pose estimation (3D HPE) is crucial for enabling autonomous vehicles (AVs) to make informed decisions and respond proactively in critical road scenarios. Promising results of 3D HPE have been gained in several domains such as human-computer interaction, robotics, sports and medical analytics, often based on data collected in well-controlled laboratory environments. Nevertheless, the transfer of 3D HPE methods to AVs has received limited research attention, due to the challenges posed by obtaining accurate 3D pose annotations and the limited suitability of data from other domains.
We present a simple yet efficient weakly supervised approach for 3D HPE in the AV context by employing a high-level sensor fusion between camera and LiDAR data. The weakly supervised setting enables training on the target datasets without any 2D/3D keypoint labels by using an off-the-shelf 2D joint extractor and pseudo labels generated from LiDAR to image projections. Our approach outperforms state-of-the-art results by up to $\sim$ 13% on the Waymo Open Dataset in the weakly supervised setting and achieves state-of-the-art results in the supervised setting.
Authors: Aristo Renaldo Ruslim, Novanto Yudistira, Budi Darma Setiawan
Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a pretext task which will be trained on the model before being applied to a specific task. There are some examples of pretext tasks used in self-supervised learning in the field of image recognition, namely rotation prediction, solving jigsaw puzzles, and predicting relative positions on image. Previous studies have only used one type of transformation as a pretext task. This raises the question of how it affects if more than one pretext task is used and to use a gating network to combine all pretext tasks. Therefore, we propose the Gated Self-Supervised Learning method to improve image classification which use more than one transformation as pretext task and uses the Mixture of Expert architecture as a gating network in combining each pretext task so that the model automatically can study and focus more on the most useful augmentations for classification. We test performance of the proposed method in several scenarios, namely CIFAR imbalance dataset classification, adversarial perturbations, Tiny-Imagenet dataset classification, and semi-supervised learning. Moreover, there are Grad-CAM and T-SNE analysis that are used to see the proposed method for identifying important features that influence image classification and representing data for each class and separating different classes properly. Our code is in https://github.com/aristorenaldo/G-SSL
Authors: Yunkun Zhang, Jin Gao, Mu Zhou, Xiaosong Wang, Yu Qiao, Shaoting Zhang, Dequan Wang
The recent surge of foundation models in computer vision and natural language processing opens up perspectives in utilizing multi-modal clinical data to train large models with strong generalizability. Yet pathological image datasets often lack biomedical text annotation and enrichment. Guiding data-efficient image diagnosis from the use of biomedical text knowledge becomes a substantial interest. In this paper, we propose to Connect Image and Text Embeddings (CITE) to enhance pathological image classification. CITE injects text insights gained from language models pre-trained with a broad range of biomedical texts, leading to adapt foundation models towards pathological image understanding. Through extensive experiments on the PatchGastric stomach tumor pathological image dataset, we demonstrate that CITE achieves leading performance compared with various baselines especially when training data is scarce. CITE offers insights into leveraging in-domain text knowledge to reinforce data-efficient pathological image classification. Code is available at https://github.com/Yunkun-Zhang/CITE.
Authors: Andrew H. Song, Mane Williams, Drew F.K. Williamson, Guillaume Jaume, Andrew Zhang, Bowen Chen, Robert Serafin, Jonathan T.C. Liu, Alex Baras, Anil V. Parwani, Faisal Mahmood
Human tissue and its constituent cells form a microenvironment that is fundamentally three-dimensional (3D). However, the standard-of-care in pathologic diagnosis involves selecting a few two-dimensional (2D) sections for microscopic evaluation, risking sampling bias and misdiagnosis. Diverse methods for capturing 3D tissue morphologies have been developed, but they have yet had little translation to clinical practice; manual and computational evaluations of such large 3D data have so far been impractical and/or unable to provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy or microcomputed tomography and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting the value of capturing larger extents of heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, MAMBA provides a general and efficient framework for 3D weakly supervised learning for clinical decision support and can help to reveal novel 3D morphological biomarkers for prognosis and therapeutic response.
Authors: Abhijith Sharma, Phil Munz, Apurva Narayan
Visual AI systems are vulnerable to natural and synthetic physical corruption in the real-world. Such corruption often arises unexpectedly and alters the model's performance. In recent years, the primary focus has been on adversarial attacks. However, natural corruptions (e.g., snow, fog, dust) are an omnipresent threat to visual AI systems and should be considered equally important. Many existing works propose interesting solutions to train robust models against natural corruption. These works either leverage image augmentations, which come with the additional cost of model training, or place suspicious patches in the scene to design unadversarial examples. In this work, we propose the idea of naturalistic support artifacts (NSA) for robust prediction. The NSAs are shown to be beneficial in scenarios where model parameters are inaccessible and adding artifacts in the scene is feasible. The NSAs are natural looking objects generated through artifact training using DC-GAN to have high visual fidelity in the scene. We test against natural corruptions on the Imagenette dataset and observe the improvement in prediction confidence score by four times. We also demonstrate NSA's capability to increase adversarial accuracy by 8\% on average. Lastly, we qualitatively analyze NSAs using saliency maps to understand how they help improve prediction confidence.
Authors: Fanghua Yu, Xintao Wang, Zheyuan Li, Yan-Pei Cao, Ying Shan, Chao Dong
The demand for efficient 3D model generation techniques has grown exponentially, as manual creation of 3D models is time-consuming and requires specialized expertise. While generative models have shown potential in creating 3D textured shapes from 2D images, their applicability in 3D industries is limited due to the lack of a well-defined camera distribution in real-world scenarios, resulting in low-quality shapes. To overcome this limitation, we propose GET3D--, the first method that directly generates textured 3D shapes from 2D images with unknown pose and scale. GET3D-- comprises a 3D shape generator and a learnable camera sampler that captures the 6D external changes on the camera. In addition, We propose a novel training schedule to stably optimize both the shape generator and camera sampler in a unified framework. By controlling external variations using the learnable camera sampler, our method can generate aligned shapes with clear textures. Extensive experiments demonstrate the efficacy of GET3D--, which precisely fits the 6D camera pose distribution and generates high-quality shapes on both synthetic and realistic unconstrained datasets.
Authors: Marawan Elbatel, Hualiang Wang, Robert Martí, Huazhu Fu, Xiaomeng Li
In the medical field, federated learning commonly deals with highly imbalanced datasets, including skin lesions and gastrointestinal images. Existing federated methods under highly imbalanced datasets primarily focus on optimizing a global model without incorporating the intra-class variations that can arise in medical imaging due to different populations, findings, and scanners. In this paper, we study the inter-client intra-class variations with publicly available self-supervised auxiliary networks. Specifically, we find that employing a shared auxiliary pre-trained model, like MoCo-V2, locally on every client yields consistent divergence measurements. Based on these findings, we derive a dynamic balanced model aggregation via self-supervised priors (MAS) to guide the global model optimization. Fed-MAS can be utilized with different local learning methods for effective model aggregation toward a highly robust and unbiased global model. Our code is available at \url{https://github.com/xmed-lab/Fed-MAS}.
Authors: Ziyi Wang, Xumin Yu, Yongming Rao, Jie Zhou, Jiwen Lu
With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on Transformer-based backbones and the unordered nature of point clouds have restricted the further development of generative pre-training. In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model. We propose to generate view images from different instructed poses via the cross-attention mechanism as the pre-training scheme. Generating view images has more precise supervision than its point cloud counterpart, thus assisting 3D backbones to have a finer comprehension of the geometrical structure and stereoscopic relations of the point cloud. Experimental results have proved the superiority of our proposed 3D-to-2D generative pre-training over previous pre-training methods. Our method is also effective in boosting the performance of architecture-oriented approaches, achieving state-of-the-art performance when fine-tuning on ScanObjectNN classification and ShapeNetPart segmentation tasks. Code is available at https://github.com/wangzy22/TAP.
Authors: Chenming Wu, Jiadai Sun, Zhelun Shen, Liangjun Zhang
Simulating camera sensors is a crucial task in autonomous driving. Although neural radiance fields are exceptional at synthesizing photorealistic views in driving simulations, they still fail in generating extrapolated views. This paper proposes to incorporate map priors into neural radiance fields to synthesize out-of-trajectory driving views with semantic road consistency. The key insight is that map information can be utilized as a prior to guide the training of the radiance fields with uncertainty. Specifically, we utilize the coarse ground surface as uncertain information to supervise the density field and warp depth with uncertainty from unknown camera poses to ensure multi-view consistency. Experimental results demonstrate that our approach can produce semantic consistency in deviated views for vehicle camera simulation.
Authors: Usha Bhalla, Suraj Srinivas, Himabindu Lakkaraju
With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model behaviour. To this end, two broad strategies have been outlined in prior literature to explain models. Post hoc explanation methods explain the behaviour of complex black-box models by highlighting features that are critical to model predictions; however, prior work has shown that these explanations may not be faithful, and even more concerning is our inability to verify them. Specifically, it is nontrivial to evaluate if a given attribution is correct with respect to the underlying model. Inherently interpretable models, on the other hand, circumvent these issues by explicitly encoding explanations into model architecture, meaning their explanations are naturally faithful and verifiable, but they often exhibit poor predictive performance due to their limited expressive power. In this work, we aim to bridge the gap between the aforementioned strategies by proposing Verifiability Tuning (VerT), a method that transforms black-box models into models that naturally yield faithful and verifiable feature attributions. We begin by introducing a formal theoretical framework to understand verifiability and show that attributions produced by standard models cannot be verified. We then leverage this framework to propose a method to build verifiable models and feature attributions out of fully trained black-box models. Finally, we perform extensive experiments on semi-synthetic and real-world datasets, and show that VerT produces models that (1) yield explanations that are correct and verifiable and (2) are faithful to the original black-box models they are meant to explain.
Authors: Haotong Qin, Ge-Peng Ji, Salman Khan, Deng-Ping Fan, Fahad Shahbaz Khan, Luc Van Gool
Google's Bard has emerged as a formidable competitor to OpenAI's ChatGPT in the field of conversational AI. Notably, Bard has recently been updated to handle visual inputs alongside text prompts during conversations. Given Bard's impressive track record in handling textual inputs, we explore its capabilities in understanding and interpreting visual data (images) conditioned by text questions. This exploration holds the potential to unveil new insights and challenges for Bard and other forthcoming multi-modal Generative models, especially in addressing complex computer vision problems that demand accurate visual and language understanding. Specifically, in this study, we focus on 15 diverse task scenarios encompassing regular, camouflaged, medical, under-water and remote sensing data to comprehensively evaluate Bard's performance. Our primary finding indicates that Bard still struggles in these vision scenarios, highlighting the significant gap in vision-based understanding that needs to be bridged in future developments. We expect that this empirical study will prove valuable in advancing future models, leading to enhanced capabilities in comprehending and interpreting fine-grained visual data. Our project is released on https://github.com/htqin/GoogleBard-VisUnderstand
Authors: Aminollah Khormali, Jiann-Shiun Yuan
Deepfake detection methods have shown promising results in recognizing forgeries within a given dataset, where training and testing take place on the in-distribution dataset. However, their performance deteriorates significantly when presented with unseen samples. As a result, a reliable deepfake detection system must remain impartial to forgery types, appearance, and quality for guaranteed generalizable detection performance. Despite various attempts to enhance cross-dataset generalization, the problem remains challenging, particularly when testing against common post-processing perturbations, such as video compression or blur. Hence, this study introduces a deepfake detection framework, leveraging a self-supervised pre-training model that delivers exceptional generalization ability, withstanding common corruptions and enabling feature explainability. The framework comprises three key components: a feature extractor based on vision Transformer architecture that is pre-trained via self-supervised contrastive learning methodology, a graph convolution network coupled with a Transformer discriminator, and a graph Transformer relevancy map that provides a better understanding of manipulated regions and further explains the model's decision. To assess the effectiveness of the proposed framework, several challenging experiments are conducted, including in-data distribution performance, cross-dataset, cross-manipulation generalization, and robustness against common post-production perturbations. The results achieved demonstrate the remarkable effectiveness of the proposed deepfake detection framework, surpassing the current state-of-the-art approaches.
Authors: Guiqin Zhao
Inspired by deep convolution segmentation algorithms, scene text detectors break the performance ceiling of datasets steadily. However, these methods often encounter threshold selection bottlenecks and have poor performance on text instances with extreme aspect ratios. In this paper, we propose to automatically learn the discriminate segmentation threshold, which distinguishes text pixels from background pixels for segmentation-based scene text detectors and then further reduces the time-consuming manual parameter adjustment. Besides, we design a Global-information Enhanced Feature Pyramid Network (GE-FPN) for capturing text instances with macro size and extreme aspect ratios. Following the GE-FPN, we introduce a cascade optimization structure to further refine the text instances. Finally, together with the proposed threshold learning strategy and text detection structure, we design an Adaptive Segmentation Network (ASNet) for scene text detection. Extensive experiments are carried out to demonstrate that the proposed ASNet can achieve the state-of-the-art performance on four text detection benchmarks, i.e., ICDAR 2015, MSRA-TD500, ICDAR 2017 MLT and CTW1500. The ablation experiments also verify the effectiveness of our contributions.
Authors: Ahmet Burak Yildirim, Hamza Pehlivan, Bahri Batuhan Bilecen, Aysegul Dundar
Recent inversion methods have shown that real images can be inverted into StyleGAN's latent space and numerous edits can be achieved on those images thanks to the semantically rich feature representations of well-trained GAN models. However, extensive research has also shown that image inversion is challenging due to the trade-off between high-fidelity reconstruction and editability. In this paper, we tackle an even more difficult task, inverting erased images into GAN's latent space for realistic inpaintings and editings. Furthermore, by augmenting inverted latent codes with different latent samples, we achieve diverse inpaintings. Specifically, we propose to learn an encoder and mixing network to combine encoded features from erased images with StyleGAN's mapped features from random samples. To encourage the mixing network to utilize both inputs, we train the networks with generated data via a novel set-up. We also utilize higher-rate features to prevent color inconsistencies between the inpainted and unerased parts. We run extensive experiments and compare our method with state-of-the-art inversion and inpainting methods. Qualitative metrics and visual comparisons show significant improvements.
Authors: Zihan Zhang, Richard Liu, Kfir Aberman, Rana Hanocka
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain. In this work, we propose to adapt the gradual diffusion concept (operating along a diffusion time-axis) into the temporal-axis of the motion sequence. Our key idea is to extend the DDPM framework to support temporally varying denoising, thereby entangling the two axes. Using our special formulation, we iteratively denoise a motion buffer that contains a set of increasingly-noised poses, which auto-regressively produces an arbitrarily long stream of frames. With a stationary diffusion time-axis, in each diffusion step we increment only the temporal-axis of the motion such that the framework produces a new, clean frame which is removed from the beginning of the buffer, followed by a newly drawn noise vector that is appended to it. This new mechanism paves the way towards a new framework for long-term motion synthesis with applications to character animation and other domains.
Authors: Saleh Momeni, Bagher BabaAli
Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing offline Arabic handwritten text. Existing approaches typically utilize a combination of convolutional neural networks for image feature extraction and recurrent neural networks for temporal modeling, with connectionist temporal classification used for text generation. However, these methods suffer from a lack of parallelization due to the sequential nature of recurrent neural networks. Furthermore, these models cannot account for linguistic rules, necessitating the use of an external language model in the post-processing stage to boost accuracy. To overcome these issues, we introduce two alternative architectures, namely the Transformer Transducer and the standard sequence-to-sequence Transformer, and compare their performance in terms of accuracy and speed. Our approach can model language dependencies and relies only on the attention mechanism, thereby making it more parallelizable and less complex. We employ pre-trained Transformers for both image understanding and language modeling. Our evaluation on the Arabic KHATT dataset demonstrates that our proposed method outperforms the current state-of-the-art approaches for recognizing offline Arabic handwritten text.
Authors: Kecheng Zheng, Wei Wu, Ruili Feng, Kai Zhu, Jiawei Liu, Deli Zhao, Zheng-Jun Zha, Wei Chen, Yujun Shen
Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which masks the network parameters through a learnable selection. Inspired by neural pathways, we argue that the knowledge required by a downstream task already exists in the pre-trained weights but just gets concealed in the upstream pre-training stage. To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen. When updating the mask, we introduce a novel gradient dropout strategy to regularize the parameter selection, in order to prevent the model from forgetting old knowledge and overfitting the downstream data. Experimental results on 11 datasets demonstrate the consistent superiority of our method over previous alternatives. It is noteworthy that we manage to deliver 18.73% performance improvement compared to the zero-shot CLIP via masking an average of only 2.56% parameters. Furthermore, our method is synergistic with most existing parameter-efficient tuning methods and can boost the performance on top of them. Project page can be found here (https://wuw2019.github.io/RMT/).
Authors: Alex Costanzino, Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, Luigi Di Stefano
Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks. We propose a simple pipeline for learning to estimate depth properly for such surfaces with neural networks, without requiring any ground-truth annotation. We unveil how to obtain reliable pseudo labels by in-painting ToM objects in images and processing them with a monocular depth estimation model. These labels can be used to fine-tune existing monocular or stereo networks, to let them learn how to deal with ToM surfaces. Experimental results on the Booster dataset show the dramatic improvements enabled by our remarkably simple proposal.
Authors: Yang Zheng, Adam W. Harley, Bokui Shen, Gordon Wetzstein, Leonidas J. Guibas
We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks. Our data and code are publicly available at: https://pointodyssey.com
Authors: Zirui Wu, Tianyu Liu, Liyi Luo, Zhide Zhong, Jianteng Chen, Hongmin Xiao, Chao Hou, Haozhe Lou, Yuantao Chen, Runyi Yang, Yuxin Huang, Xiaoyu Ye, Zike Yan, Yongliang Shi, Yiyi Liao, Hao Zhao
Nowadays, autonomous cars can drive smoothly in ordinary cases, and it is widely recognized that realistic sensor simulation will play a critical role in solving remaining corner cases by simulating them. To this end, we propose an autonomous driving simulator based upon neural radiance fields (NeRFs). Compared with existing works, ours has three notable features: (1) Instance-aware. Our simulator models the foreground instances and background environments separately with independent networks so that the static (e.g., size and appearance) and dynamic (e.g., trajectory) properties of instances can be controlled separately. (2) Modular. Our simulator allows flexible switching between different modern NeRF-related backbones, sampling strategies, input modalities, etc. We expect this modular design to boost academic progress and industrial deployment of NeRF-based autonomous driving simulation. (3) Realistic. Our simulator set new state-of-the-art photo-realism results given the best module selection. Our simulator will be open-sourced while most of our counterparts are not. Project page: https://open-air-sun.github.io/mars/.
Authors: Lingdong Kong, Yaru Niu, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R. Cottereau, Ding Zhao, Liangjun Zhang, Hesheng Wang, Wei Tsang Ooi, Ruijie Zhu, Ziyang Song, Li Liu, Tianzhu Zhang, Jun Yu, Mohan Jing, Pengwei Li, Xiaohua Qi, Cheng Jin, Yingfeng Chen, Jie Hou, Jie Zhang, Zhen Kan, Qiang Ling, Liang Peng, Minglei Li, Di Xu, Changpeng Yang, Yuanqi Yao, Gang Wu, Jian Kuai, Xianming Liu, Junjun Jiang, Jiamian Huang, Baojun Li, Jiale Chen, Shuang Zhang, Sun Ao, Zhenyu Li, Runze Chen, Haiyong Luo, Fang Zhao, Jingze Yu
Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website.
Authors: Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos, Joao Frederico Carvalho, Linus Härenstam-Nielsen, Hossein Azizpour, Hedvig Kjellström, Daniel Cremers, Matteo Poggi
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation make this paradigm unfeasible for real-world applications. In this paper we propose HAMLET, a Hardware-Aware Modular Least Expensive Training framework for real-time domain adaptation. Our approach includes a hardware-aware back-propagation orchestration agent (HAMT) and a dedicated domain-shift detector that enables active control over when and how the model is adapted (LT). Thanks to these advancements, our approach is capable of performing semantic segmentation while simultaneously adapting at more than 29FPS on a single consumer-grade GPU. Our framework's encouraging accuracy and speed trade-off is demonstrated on OnDA and SHIFT benchmarks through experimental results.
Authors: Arjun Somayazulu, Changan Chen, Kristen Grauman
Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a target acoustic environment. Existing methods assume access to paired training data, where the audio is observed in both source and target environments, but this limits the diversity of training data or requires the use of simulated data or heuristics to create paired samples. We propose a self-supervised approach to visual acoustic matching where training samples include only the target scene image and audio -- without acoustically mismatched source audio for reference. Our approach jointly learns to disentangle room acoustics and re-synthesize audio into the target environment, via a conditional GAN framework and a novel metric that quantifies the level of residual acoustic information in the de-biased audio. Training with either in-the-wild web data or simulated data, we demonstrate it outperforms the state-of-the-art on multiple challenging datasets and a wide variety of real-world audio and environments.
Authors: Sen Wu, Hongyang R. Zhang, Gregory Valiant, Christopher Ré
Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this work, we consider a family of linear transformations and study their effects on the ridge estimator in an over-parametrized linear regression setting. First, we show that transformations that preserve the labels of the data can improve estimation by enlarging the span of the training data. Second, we show that transformations that mix data can improve estimation by playing a regularization effect. Finally, we validate our theoretical insights on MNIST. Based on the insights, we propose an augmentation scheme that searches over the space of transformations by how uncertain the model is about the transformed data. We validate our proposed scheme on image and text datasets. For example, our method outperforms random sampling methods by 1.24% on CIFAR-100 using Wide-ResNet-28-10. Furthermore, we achieve comparable accuracy to the SoTA Adversarial AutoAugment on CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets.
Authors: Buyu Li, Yongchi Zhao, Zhelun Shi, Lu Sheng
Generating 3D dances from music is an emerged research task that benefits a lot of applications in vision and graphics. Previous works treat this task as sequence generation, however, it is challenging to render a music-aligned long-term sequence with high kinematic complexity and coherent movements. In this paper, we reformulate it by a two-stage process, ie, a key pose generation and then an in-between parametric motion curve prediction, where the key poses are easier to be synchronized with the music beats and the parametric curves can be efficiently regressed to render fluent rhythm-aligned movements. We named the proposed method as DanceFormer, which includes two cascading kinematics-enhanced transformer-guided networks (called DanTrans) that tackle each stage, respectively. Furthermore, we propose a large-scale music conditioned 3D dance dataset, called PhantomDance, that is accurately labeled by experienced animators rather than reconstruction or motion capture. This dataset also encodes dances as key poses and parametric motion curves apart from pose sequences, thus benefiting the training of our DanceFormer. Extensive experiments demonstrate that the proposed method, even trained by existing datasets, can generate fluent, performative, and music-matched 3D dances that surpass previous works quantitatively and qualitatively. Moreover, the proposed DanceFormer, together with the PhantomDance dataset (https://github.com/libuyu/PhantomDanceDataset), are seamlessly compatible with industrial animation software, thus facilitating the adaptation for various downstream applications.
Authors: Shane Gilroy, Darragh Mullins, Edward Jones, Ashkan Parsi, Martin Glavin
Robust detection of vulnerable road users is a safety critical requirement for the deployment of autonomous vehicles in heterogeneous traffic. One of the most complex outstanding challenges is that of partial occlusion where a target object is only partially available to the sensor due to obstruction by another foreground object. A number of leading pedestrian detection benchmarks provide annotation for partial occlusion, however each benchmark varies greatly in their definition of the occurrence and severity of occlusion. Recent research demonstrates that a high degree of subjectivity is used to classify occlusion level in these cases and occlusion is typically categorized into 2 to 3 broad categories such as partially and heavily occluded. This can lead to inaccurate or inconsistent reporting of pedestrian detection model performance depending on which benchmark is used. This research introduces a novel, objective benchmark for partially occluded pedestrian detection to facilitate the objective characterization of pedestrian detection models. Characterization is carried out on seven popular pedestrian detection models for a range of occlusion levels from 0-99%, in order to demonstrate the efficacy and increased analysis capabilities of the proposed characterization method. Results demonstrate that pedestrian detection performance degrades, and the number of false negative detections increase as pedestrian occlusion level increases. Of the seven popular pedestrian detection routines characterized, CenterNet has the greatest overall performance, followed by SSDlite. RetinaNet has the lowest overall detection performance across the range of occlusion levels.
Authors: Yanwei Wang, Ching-Yun Ko, Pulkit Agrawal
One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias makes this system data inefficient. We hypothesize a sufficient representation of the current view and the goal view for a navigation policy can be learned by predicting the location and size of a crop of the current view that corresponds to the goal. We further show that training such random crop prediction in a self-supervised fashion purely on synthetic noise images transfers well to natural home images. The learned representation can then be bootstrapped to learn a navigation policy efficiently with little interaction data. The code is available at https://yanweiw.github.io/noise2ptz
Authors: Jiaming Zhang, Kailun Yang, Hao Shi, Simon Reiß, Kunyu Peng, Chaoxiang Ma, Haodong Fu, Philip H. S. Torr, Kaiwei Wang, Rainer Stiefelhagen
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360-degree imagery. To tackle these problems, first, we propose the upgraded Transformer for Panoramic Semantic Segmentation, i.e., Trans4PASS+, equipped with Deformable Patch Embedding (DPE) and Deformable MLP (DMLPv2) modules for handling object deformations and image distortions whenever (before or after adaptation) and wherever (shallow or deep levels). Second, we enhance the Mutual Prototypical Adaptation (MPA) strategy via pseudo-label rectification for unsupervised domain adaptive panoramic segmentation. Third, aside from Pinhole-to-Panoramic (Pin2Pan) adaptation, we create a new dataset (SynPASS) with 9,080 panoramic images, facilitating Synthetic-to-Real (Syn2Real) adaptation scheme in 360-degree imagery. Extensive experiments are conducted, which cover indoor and outdoor scenarios, and each of them is investigated with Pin2Pan and Syn2Real regimens. Trans4PASS+ achieves state-of-the-art performances on four domain adaptive panoramic semantic segmentation benchmarks. Code is available at https://github.com/jamycheung/Trans4PASS.
Authors: Yannick Hold-Geoffroy, Dominique Piché-Meunier, Kalyan Sunkavalli, Jean-Charles Bazin, François Rameau, Jean-François Lalonde
Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences. To produce beautiful composites, the camera needs to be geometrically calibrated, which can be tedious and requires a physical calibration target. In place of the traditional multi-image calibration process, we propose to infer the camera calibration parameters such as pitch, roll, field of view, and lens distortion directly from a single image using a deep convolutional neural network. We train this network using automatically generated samples from a large-scale panorama dataset, yielding competitive accuracy in terms of standard `2 error. However, we argue that minimizing such standard error metrics might not be optimal for many applications. In this work, we investigate human sensitivity to inaccuracies in geometric camera calibration. To this end, we conduct a large-scale human perception study where we ask participants to judge the realism of 3D objects composited with correct and biased camera calibration parameters. Based on this study, we develop a new perceptual measure for camera calibration and demonstrate that our deep calibration network outperforms previous single-image based calibration methods both on standard metrics as well as on this novel perceptual measure. Finally, we demonstrate the use of our calibration network for several applications, including virtual object insertion, image retrieval, and compositing. A demonstration of our approach is available at https://lvsn.github.io/deepcalib .
Authors: Guy Ohayon, Theo Adrai, Michael Elad, Tomer Michaeli
Stochastic restoration algorithms allow to explore the space of solutions that correspond to the degraded input. In this paper we reveal additional fundamental advantages of stochastic methods over deterministic ones, which further motivate their use. First, we prove that any restoration algorithm that attains perfect perceptual quality and whose outputs are consistent with the input must be a posterior sampler, and is thus required to be stochastic. Second, we illustrate that while deterministic restoration algorithms may attain high perceptual quality, this can be achieved only by filling up the space of all possible source images using an extremely sensitive mapping, which makes them highly vulnerable to adversarial attacks. Indeed, we show that enforcing deterministic models to be robust to such attacks profoundly hinders their perceptual quality, while robustifying stochastic models hardly influences their perceptual quality, and improves their output variability. These findings provide a motivation to foster progress in stochastic restoration methods, paving the way to better recovery algorithms.
Authors: Rongqin Liang, Yuanman Li, Jiantao Zhou, Xia Li
The pedestrian trajectory prediction task is an essential component of intelligent systems. Its applications include but are not limited to autonomous driving, robot navigation, and anomaly detection of monitoring systems. Due to the diversity of motion behaviors and the complex social interactions among pedestrians, accurately forecasting their future trajectory is challenging. Existing approaches commonly adopt GANs or CVAEs to generate diverse trajectories. However, GAN-based methods do not directly model data in a latent space, which may make them fail to have full support over the underlying data distribution; CVAE-based methods optimize a lower bound on the log-likelihood of observations, which may cause the learned distribution to deviate from the underlying distribution. The above limitations make existing approaches often generate highly biased or inaccurate trajectories. In this paper, we propose a novel generative flow based framework with dual graphormer for pedestrian trajectory prediction (STGlow). Different from previous approaches, our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors. Besides, our method has clear physical meanings for simulating the evolution of human motion behaviors. The forward process of the flow gradually degrades complex motion behavior into simple behavior, while its reverse process represents the evolution of simple behavior into complex motion behavior. Further, we introduce a dual graphormer combining with the graph structure to more adequately model the temporal dependencies and the mutual spatial interactions. Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches.
Authors: Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost van de Weijer
We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is often achieved via exemplar replay which can help recalibrate previous task classifiers to the feature drift which occurs when learning new tasks. Exemplar replay, however, comes at the cost of retaining samples from previous tasks which for many applications may not be possible. To address the problem of continual ViT training, we first propose gated class-attention to minimize the drift in the final ViT transformer block. This mask-based gating is applied to class-attention mechanism of the last transformer block and strongly regulates the weights crucial for previous tasks. Importantly, gated class-attention does not require the task-ID during inference, which distinguishes it from other parameter isolation methods. Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks. The combination of gated class-attention and cascaded feature drift compensation allows for plasticity towards new tasks while limiting forgetting of previous ones. Extensive experiments performed on CIFAR-100, Tiny-ImageNet and ImageNet100 demonstrate that our exemplar-free method obtains competitive results when compared to rehearsal based ViT methods.
Authors: Siyu Ren, Junhui Hou, Xiaodong Chen, Ying He, Wenping Wang
We present a learning-based method, namely GeoUDF,to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud.To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface. Besides,we model the local geometric structure of the input point clouds by explicitly learning a quadratic polynomial for each point. This not only facilitates upsampling the input sparse point cloud but also naturally induces unoriented normal, which further augments UDF estimation. Finally, to extract triangle meshes from the predicted UDF we propose a customized edge-based marching cube module. We conduct extensive experiments and ablation studies to demonstrate the significant advantages of our method over state-of-the-art methods in terms of reconstruction accuracy, efficiency, and generality. The source code is publicly available at https://github.com/rsy6318/GeoUDF.
Authors: Yingtian Zou, Vikas Verma, Sarthak Mittal, Wai Hoh Tang, Hieu Pham, Juho Kannala, Yoshua Bengio, Arno Solin, Kenji Kawaguchi
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization performance in many learning paradigms and applications. In this work, we first analyze Mixup and show that it implicitly regularizes infinitely many directional derivatives of all orders. Based on this new insight, we propose an improved version of Mixup, theoretically justified to deliver better generalization performance than the vanilla Mixup. To demonstrate the effectiveness of the proposed method, we conduct experiments across various domains such as images, tabular data, speech, and graphs. Our results show that the proposed method improves Mixup across multiple datasets using a variety of architectures, for instance, exhibiting an improvement over Mixup by 0.8% in ImageNet top-1 accuracy.
Authors: Reza Azad, René Arimond, Ehsan Khodapanah Aghdam, Amirhossein Kazerouni, Dorit Merhof
Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from quadratic computational complexity with respect to the number of tokens. Many architectures attempt to reduce model complexity by limiting the self-attention mechanism to local regions or by redesigning the tokenization process. In this paper, we propose DAE-Former, a novel method that seeks to provide an alternative perspective by efficiently designing the self-attention mechanism. More specifically, we reformulate the self-attention mechanism to capture both spatial and channel relations across the whole feature dimension while staying computationally efficient. Furthermore, we redesign the skip connection path by including the cross-attention module to ensure the feature reusability and enhance the localization power. Our method outperforms state-of-the-art methods on multi-organ cardiac and skin lesion segmentation datasets without requiring pre-training weights. The code is publicly available at https://github.com/mindflow-institue/DAEFormer.
Authors: Anpei Chen, Zexiang Xu, Xinyue Wei, Siyu Tang, Hao Su, Andreas Geiger
We present Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed input coordinates. This decomposition results in a unified framework that accommodates several recent signal representations including NeRF, Plenoxels, EG3D, Instant-NGP, and TensoRF. Additionally, our framework allows for the creation of powerful new signal representations, such as the "Dictionary Field" (DiF) which is a second contribution of this paper. Our experiments show that DiF leads to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, DiF enables generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from sparse observations and few-shot radiance field reconstruction.
Authors: Nicolaas J. Annau, Alex J. Cannon, Adam H. Monahan
This paper explores the application of emerging machine learning methods from image super-resolution (SR) to the task of statistical downscaling. We specifically focus on convolutional neural network-based Generative Adversarial Networks (GANs). Our GANs are conditioned on low-resolution (LR) inputs to generate high-resolution (HR) surface winds emulating Weather Research and Forecasting (WRF) model simulations over North America. Unlike traditional SR models, where LR inputs are idealized coarsened versions of the HR images, WRF emulation involves using non-idealized LR and HR pairs resulting in shared-scale mismatches due to internal variability. Our study builds upon current SR-based statistical downscaling by experimenting with a novel frequency-separation (FS) approach from the computer vision field. To assess the skill of SR models, we carefully select evaluation metrics, and focus on performance measures based on spatial power spectra. Our analyses reveal how GAN configurations influence spatial structures in the generated fields, particularly biases in spatial variability spectra. Using power spectra to evaluate the FS experiments reveals that successful applications of FS in computer vision do not translate to climate fields. However, the FS experiments demonstrate the sensitivity of power spectra to a commonly used GAN-based SR objective function, which helps interpret and understand its role in determining spatial structures. This result motivates the development of a novel partial frequency-separation scheme as a promising configuration option. We also quantify the influence on GAN performance of non-idealized LR fields resulting from internal variability. Furthermore, we conduct a spectra-based feature-importance experiment allowing us to explore the dependence of the spatial structure of generated fields on different physically relevant LR covariates.
Authors: Yangyang Shu, Anton van den Hengel, Lingqiao Liu
Self-supervised learning (SSL) strategies have demonstrated remarkable performance in various recognition tasks. However, both our preliminary investigation and recent studies suggest that they may be less effective in learning representations for fine-grained visual recognition (FGVR) since many features helpful for optimizing SSL objectives are not suitable for characterizing the subtle differences in FGVR. To overcome this issue, we propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes, dubbed as common rationales in this paper. Intuitively, common rationales tend to correspond to the discriminative patterns from the key parts of foreground objects. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective without using any pre-trained object parts or saliency detectors, making it seamlessly to be integrated with the existing SSL process. Specifically, we fit the GradCAM with a branch with limited fitting capacity, which allows the branch to capture the common rationales and discard the less common discriminative patterns. At the test stage, the branch generates a set of spatial weights to selectively aggregate features representing an instance. Extensive experimental results on four visual tasks demonstrate that the proposed method can lead to a significant improvement in different evaluation settings.
Authors: Bo Zhou, Huidong Xie, Qiong Liu, Xiongchao Chen, Xueqi Guo, Zhicheng Feng, S. Kevin Zhou, Biao Li, Axel Rominger, Kuangyu Shi, James S. Duncan, Chi Liu
Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in deep learning have shown great potential in improving low-count PET image quality, but acquiring a large, centralized, and diverse dataset from multiple institutions for training a robust model is difficult due to privacy and security concerns of patient data. Moreover, low-count PET data at different institutions may have different data distribution, thus requiring personalized models. While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional low-count PET denoising remains a challenge and is still highly under-explored. In this work, we propose FedFTN, a personalized federated learning strategy that addresses these challenges. FedFTN uses a local deep feature transformation network (FTN) to modulate the feature outputs of a globally shared denoising network, enabling personalized low-count PET denoising for each institution. During the federated learning process, only the denoising network's weights are communicated and aggregated, while the FTN remains at the local institutions for feature transformation. We evaluated our method using a large-scale dataset of multi-institutional low-count PET imaging data from three medical centers located across three continents, and showed that FedFTN provides high-quality low-count PET images, outperforming previous baseline FL reconstruction methods across all low-count levels at all three institutions.
Authors: Ziming Wang, Yujiang Liu, Yifan Duan, Xingchen Li, Xinran Zhang, Jianmin Ji, Erbao Dong, Yanyong Zhang
In this paper, we present the USTC FLICAR Dataset, which is dedicated to the development of simultaneous localization and mapping and precise 3D reconstruction of the workspace for heavy-duty autonomous aerial work robots. In recent years, numerous public datasets have played significant roles in the advancement of autonomous cars and unmanned aerial vehicles (UAVs). However, these two platforms differ from aerial work robots: UAVs are limited in their payload capacity, while cars are restricted to two-dimensional movements. To fill this gap, we create the "Giraffe" mapping robot based on a bucket truck, which is equipped with a variety of well-calibrated and synchronized sensors: four 3D LiDARs, two stereo cameras, two monocular cameras, Inertial Measurement Units (IMUs), and a GNSS/INS system. A laser tracker is used to record the millimeter-level ground truth positions. We also make its ground twin, the "Okapi" mapping robot, to gather data for comparison. The proposed dataset extends the typical autonomous driving sensing suite to aerial scenes, demonstrating the potential of combining autonomous driving perception systems with bucket trucks to create a versatile autonomous aerial working platform. Moreover, based on the Segment Anything Model (SAM), we produce the Semantic FLICAR dataset, which provides fine-grained semantic segmentation annotations for multimodal continuous data in both temporal and spatial dimensions. The dataset is available for download at: https://ustc-flicar.github.io/.
Authors: Enze Xie, Lewei Yao, Han Shi, Zhili Liu, Daquan Zhou, Zhaoqiang Liu, Jiawei Li, Zhenguo Li
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge, which is critical for real-world applications. This paper proposes DiffFit, a parameter-efficient strategy to fine-tune large pre-trained diffusion models that enable fast adaptation to new domains. DiffFit is embarrassingly simple that only fine-tunes the bias term and newly-added scaling factors in specific layers, yet resulting in significant training speed-up and reduced model storage costs. Compared with full fine-tuning, DiffFit achieves 2$\times$ training speed-up and only needs to store approximately 0.12\% of the total model parameters. Intuitive theoretical analysis has been provided to justify the efficacy of scaling factors on fast adaptation. On 8 downstream datasets, DiffFit achieves superior or competitive performances compared to the full fine-tuning while being more efficient. Remarkably, we show that DiffFit can adapt a pre-trained low-resolution generative model to a high-resolution one by adding minimal cost. Among diffusion-based methods, DiffFit sets a new state-of-the-art FID of 3.02 on ImageNet 512$\times$512 benchmark by fine-tuning only 25 epochs from a public pre-trained ImageNet 256$\times$256 checkpoint while being 30$\times$ more training efficient than the closest competitor.
Authors: Xijun Wang, Aggelos K. Katsaggelos
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions in different video scenarios and detect whether some actions are occurring. In this paper, we mimic how humans do and bring a new perspective for locating and identifying multiple actions in a video. We propose a network named VQK-Net with a video-specific query-key attention modeling that learns a unique query for each action category of each input video. The learned queries not only contain the actions' knowledge features at the abstract level but also have the ability to fit this knowledge into the target video scenario, and they will be used to detect the presence of the corresponding action along the temporal dimension. To better learn these action category queries, we exploit not only the features of the current input video but also the correlation between different videos through a novel video-specific action category query learner worked with a query similarity loss. Finally, we conduct extensive experiments on three commonly used datasets (THUMOS14, ActivityNet1.2, and ActivityNet1.3) and achieve state-of-the-art performance.
Authors: Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos
Atmospheric Turbulence (AT) correction is a challenging restoration task as it consists of two distortions: geometric distortion and spatially variant blur. Diffusion models have shown impressive accomplishments in photo-realistic image synthesis and beyond. In this paper, we propose a novel deep conditional diffusion model under a variational inference framework to solve the AT correction problem. We use this framework to improve performance by learning latent prior information from the input and degradation processes. We use the learned information to further condition the diffusion model. Experiments are conducted in a comprehensive synthetic AT dataset. We show that the proposed framework achieves good quantitative and qualitative results.
Authors: Jenny Schmalfuss, Lukas Mehl, Andrés Bruhn
Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more realistic threat scenario. Hence, in this work, we present a novel attack on motion estimation that exploits adversarially optimized particles to mimic weather effects like snowflakes, rain streaks or fog clouds. At the core of our attack framework is a differentiable particle rendering system that integrates particles (i) consistently over multiple time steps (ii) into the 3D space (iii) with a photo-realistic appearance. Through optimization, we obtain adversarial weather that significantly impacts the motion estimation. Surprisingly, methods that previously showed good robustness towards small per-pixel perturbations are particularly vulnerable to adversarial weather. At the same time, augmenting the training with non-optimized weather increases a method's robustness towards weather effects and improves generalizability at almost no additional cost. Our code will be available at https://github.com/cv-stuttgart/DistractingDownpour.
Authors: Siyuan Huang, Bo Zhang, Botian Shi, Peng Gao, Yikang Li, Hongsheng Li
Although Domain Generalization (DG) problem has been fast-growing in the 2D image tasks, its exploration on 3D point cloud data is still insufficient and challenged by more complex and uncertain cross-domain variances with uneven inter-class modality distribution. In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model. Specifically, we first design a Multi-grained Sub-domain Alignment (MSA) method, which can constrain the learned representations to be domain-agnostic and discriminative, by performing a multi-grained feature alignment process between the splitted sub-domains from the single source dataset. Then, a Sample-level Domain-aware Attention (SDA) strategy is presented, which can selectively enhance easy-to-adapt samples from different sub-domains according to the sample-level inter-domain distance to avoid the negative transfer. Experiments demonstrate that our SUG can boost the generalization ability for unseen target domains, even outperforming the existing unsupervised domain adaptation methods that have to access extensive target domain data. Our code is available at https://github.com/SiyuanHuang95/SUG.
Authors: Hyoung Suk Park, Chang Min Hyun, Sang-Hwy Lee, Jin Keun Seo, Kiwan Jeon
This paper presents a fully automatic registration method of dental cone-beam computed tomography (CBCT) and face scan data. It can be used for a digital platform of 3D jaw-teeth-face models in a variety of applications, including 3D digital treatment planning and orthognathic surgery. Difficulties in accurately merging facial scans and CBCT images are due to the different image acquisition methods and limited area of correspondence between the two facial surfaces. In addition, it is difficult to use machine learning techniques because they use face-related 3D medical data with radiation exposure, which are difficult to obtain for training. The proposed method addresses these problems by reusing an existing machine-learning-based 2D landmark detection algorithm in an open-source library and developing a novel mathematical algorithm that identifies paired 3D landmarks from knowledge of the corresponding 2D landmarks. A main contribution of this study is that the proposed method does not require annotated training data of facial landmarks because it uses a pre-trained facial landmark detection algorithm that is known to be robust and generalized to various 2D face image models. Note that this reduces a 3D landmark detection problem to a 2D problem of identifying the corresponding landmarks on two 2D projection images generated from two different projection angles. Here, the 3D landmarks for registration were selected from the sub-surfaces with the least geometric change under the CBCT and face scan environments. For the final fine-tuning of the registration, the Iterative Closest Point method was applied, which utilizes geometrical information around the 3D landmarks. The experimental results show that the proposed method achieved an averaged surface distance error of 0.74 mm for three pairs of CBCT and face scan datasets.
Authors: Aishwarya Venkataramanan, Assia Benbihi, Martin Laviale, Cedric Pradalier
Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty estimation, existing methods bring in significant changes to model architectures and training procedures. In this paper, we present a lightweight, fast, and high-performance regularization method for Mahalanobis distance-based uncertainty prediction, and that requires minimal changes to the network's architecture. To derive Gaussian latent representation favourable for Mahalanobis Distance calculation, we introduce a self-supervised representation learning method that separates in-class representations into multiple Gaussians. Classes with non-Gaussian representations are automatically identified and dynamically clustered into multiple new classes that are approximately Gaussian. Evaluation on standard OOD benchmarks shows that our method achieves state-of-the-art results on OOD detection with minimal inference time, and is very competitive on predictive probability calibration. Finally, we show the applicability of our method to a real-life computer vision use case on microorganism classification.
Authors: Zhijian Luo, Jiahui Tang, Yueen Hou, Zihan Huang, Yanzeng Gao
Image captured under low-light conditions presents unpleasing artifacts, which debilitate the performance of feature extraction for many upstream visual tasks. Low-light image enhancement aims at improving brightness and contrast, and further reducing noise that corrupts the visual quality. Recently, many image restoration methods based on Swin Transformer have been proposed and achieve impressive performance. However, on one hand, trivially employing Swin Transformer for low-light image enhancement would expose some artifacts, including over-exposure, brightness imbalance and noise corruption, etc. On the other hand, it is impractical to capture image pairs of low-light images and corresponding ground-truth, i.e. well-exposed image in same visual scene. In this paper, we propose a dual-branch network based on Swin Transformer, guided by a signal-to-noise ratio prior map which provides the spatial-varying information for low-light image enhancement. Moreover, we leverage unsupervised learning to construct the optimization objective based on Retinex model, to guide the training of proposed network. Experimental results demonstrate that the proposed model is competitive with the baseline models.
Authors: Ludovica Schaerf, Pepe Ballesteros, Valentine Bernasconi, Iacopo Neri, Dario Negueruela del Castillo
Art curatorial practice is characterized by the presentation of an art collection in a knowledgeable way. Machine processes are characterized by their capacity to manage and analyze large amounts of data. This paper envisages AI curation and audience interaction to explore the implications of contemporary machine learning models for the curatorial world. This project was developed for the occasion of the 2023 Helsinki Art Biennial, entitled New Directions May Emerge. We use the Helsinki Art Museum (HAM) collection to re-imagine the city of Helsinki through the lens of machine perception. We use visual-textual models to place indoor artworks in public spaces, assigning fictional coordinates based on similarity scores. We transform the space that each artwork inhabits in the city by generating synthetic 360 art panoramas. We guide the generation estimating depth values from 360 panoramas at each artwork location, and machine-generated prompts of the artworks. The result of this project is an AI curation that places the artworks in their imagined physical space, blurring the lines of artwork, context, and machine perception. The work is virtually presented as a web-based installation on this link this http URL, where users can navigate an alternative version of the city while exploring and interacting with its cultural heritage at scale.
Authors: Gianluca Berardi, Yulia Gryaditskaya
Recently, encoders like ViT (vision transformer) and ResNet have been trained on vast datasets and utilized as perceptual metrics for comparing sketches and images, as well as multi-domain encoders in a zero-shot setting. However, there has been limited effort to quantify the granularity of these encoders. Our work addresses this gap by focusing on multi-modal 2D projections of individual 3D instances. This task holds crucial implications for retrieval and sketch-based modeling. We show that in a zero-shot setting, the more abstract the sketch, the higher the likelihood of incorrect image matches. Even within the same sketch domain, sketches of the same object drawn in different styles, for example by distinct individuals, might not be accurately matched. One of the key findings of our research is that meticulous fine-tuning on one class of 3D shapes can lead to improved performance on other shape classes, reaching or surpassing the accuracy of supervised methods. We compare and discuss several fine-tuning strategies. Additionally, we delve deeply into how the scale of an object in a sketch influences the similarity of features at different network layers, helping us identify which network layers provide the most accurate matching. Significantly, we discover that ViT and ResNet perform best when dealing with similar object scales. We believe that our work will have a significant impact on research in the sketch domain, providing insights and guidance on how to adopt large pretrained models as perceptual losses.
Authors: Ravi Kakaiya, Rakshith Sathish, Ramanathan Sethuraman, Debdoot Sheet
Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such vehicles currently rely on segmentation and object detection algorithms to detect and track objects around its surrounding. The data collected from the vehicles are often sent to cloud servers to facilitate continual/life-long learning of these algorithms. Considering the bandwidth constraints, the data is compressed before sending it to servers, where it is typically decompressed for training and analysis. In this work, we propose the use of a learning-based compression Codec to reduce the overhead in latency incurred for the decompression operation in the standard pipeline. We demonstrate that the learned compressed representation can also be used to perform tasks like semantic segmentation in addition to decompression to obtain the images. We experimentally validate the proposed pipeline on the Cityscapes dataset, where we achieve a compression factor up to $66 \times$ while preserving the information required to perform segmentation with a dice coefficient of $0.84$ as compared to $0.88$ achieved using decompressed images while reducing the overall compute by $11\%$.
Authors: Leilei Ma, Dengdi Sun, Lei Wang, Haifeng Zhao, Bin Luo
Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on modeling label relationships with graph and understanding object regions using class activation maps (CAM). However, these methods ignore the complex intra- and inter-category relationships among specific semantic features, and CAM is prone to generate noisy information. To this end, we propose a novel semantic-aware dual contrastive learning framework that incorporates sample-to-sample contrastive learning (SSCL) as well as prototype-to-sample contrastive learning (PSCL). Specifically, we leverage semantic-aware representation learning to extract category-related local discriminative features and construct category prototypes. Then based on SSCL, label-level visual representations of the same category are aggregated together, and features belonging to distinct categories are separated. Meanwhile, we construct a novel PSCL module to narrow the distance between positive samples and category prototypes and push negative samples away from the corresponding category prototypes. Finally, the discriminative label-level features related to the image content are accurately captured by the joint training of the above three parts. Experiments on five challenging large-scale public datasets demonstrate that our proposed method is effective and outperforms the state-of-the-art methods. Code and supplementary materials are released on https://github.com/yu-gi-oh-leilei/SADCL.
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: 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: 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: Qiaoyi Su, Yuhong Chou, Yifan Hu, Jianing Li, Shijie Mei, Ziyang Zhang, Guoqi Li
Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics. Recently, deep SNNs trained directly have shown great success in achieving high performance on classification tasks with very few time steps. However, how to design a directly-trained SNN for the regression task of object detection still remains a challenging problem. To address this problem, we propose EMS-YOLO, a novel directly-trained SNN framework for object detection, which is the first trial to train a deep SNN with surrogate gradients for object detection rather than ANN-SNN conversion strategies. Specifically, we design a full-spike residual block, EMS-ResNet, which can effectively extend the depth of the directly-trained SNN with low power consumption. Furthermore, we theoretically analyze and prove the EMS-ResNet could avoid gradient vanishing or exploding. The results demonstrate that our approach outperforms the state-of-the-art ANN-SNN conversion methods (at least 500 time steps) in extremely fewer time steps (only 4 time steps). It is shown that our model could achieve comparable performance to the ANN with the same architecture while consuming 5.83 times less energy on the frame-based COCO Dataset and the event-based Gen1 Dataset.
Authors: Shengnan Hu, Ce Zheng, Zixiang Zhou, Chen Chen, Gita Sukthankar
Human-centric visual understanding is an important desideratum for effective human-robot interaction. In order to navigate crowded public places, social robots must be able to interpret the activity of the surrounding humans. This paper addresses one key aspect of human-centric visual understanding, multi-person pose estimation. Achieving good performance on multi-person pose estimation in crowded scenes is difficult due to the challenges of occluded joints and instance separation. In order to tackle these challenges and overcome the limitations of image features in representing invisible body parts, we propose a novel prompt-based pose inference strategy called LAMP (Language Assisted Multi-person Pose estimation). By utilizing the text representations generated by a well-trained language model (CLIP), LAMP can facilitate the understanding of poses on the instance and joint levels, and learn more robust visual representations that are less susceptible to occlusion. This paper demonstrates that language-supervised training boosts the performance of single-stage multi-person pose estimation, and both instance-level and joint-level prompts are valuable for training. The code is available at https://github.com/shengnanh20/LAMP.
Authors: Axel Durbet, Paul-Marie Grollemund, Kevin Thiry-Atighehchi
This paper provides a comprehensive analysis of information leakage during distance evaluation, with an emphasis on threshold-based obfuscated distance (i.e., Fuzzy Matcher). Leakage can occur due to a malware infection or the use of a weakly privacy-preserving matcher, exemplified by side channel attacks or partially obfuscated designs. We provide an exhaustive catalog of information leakage scenarios as well as their impacts on the security concerning data privacy. Each of the scenarios leads to generic attacks whose impacts are expressed in terms of computational costs, hence allowing the establishment of upper bounds on the security level.
Authors: Ruitao Chen, Guoyang Xie, Jiaqi Liu, Jinbao Wang, Ziqi Luo, Jinfan Wang, Feng Zheng
3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing (IM). Recently many advanced algorithms have been published, but most of them cannot meet the needs of IM. There are several disadvantages: i) difficult to deploy on production lines since their algorithms heavily rely on large pre-trained models; ii) hugely increase storage overhead due to overuse of memory banks; iii) the inference speed cannot be achieved in real-time. To overcome these issues, we propose an easy and deployment-friendly network (called EasyNet) without using pre-trained models and memory banks: firstly, we design a multi-scale multi-modality feature encoder-decoder to accurately reconstruct the segmentation maps of anomalous regions and encourage the interaction between RGB images and depth images; secondly, we adopt a multi-modality anomaly segmentation network to achieve a precise anomaly map; thirdly, we propose an attention-based information entropy fusion module for feature fusion during inference, making it suitable for real-time deployment. Extensive experiments show that EasyNet achieves an anomaly detection AUROC of 92.6% without using pre-trained models and memory banks. In addition, EasyNet is faster than existing methods, with a high frame rate of 94.55 FPS on a Tesla V100 GPU.
Authors: Xinzhu Liu, Di Guo, Huaping Liu
Multi-agent embodied tasks have recently been studied in complex indoor visual environments. Collaboration among multiple agents can improve work efficiency and has significant practical value. However, most of the existing research focuses on homogeneous multi-agent tasks. Compared with homogeneous agents, heterogeneous agents can leverage their different capabilities to allocate corresponding sub-tasks and cooperate to complete complex tasks. Heterogeneous multi-agent tasks are common in real-world scenarios, and the collaboration strategy among heterogeneous agents is a challenging and important problem to be solved. To study collaboration among heterogeneous agents, we propose the heterogeneous multi-agent tidying-up task, in which multiple heterogeneous agents with different capabilities collaborate with each other to detect misplaced objects and place them in reasonable locations. This is a demanding task since it requires agents to make the best use of their different capabilities to conduct reasonable task planning and complete the whole task. To solve this task, we build a heterogeneous multi-agent tidying-up benchmark dataset in a large number of houses with multiple rooms based on ProcTHOR-10K. We propose the hierarchical decision model based on misplaced object detection, reasonable receptacle prediction, as well as the handshake-based group communication mechanism. Extensive experiments are conducted to demonstrate the effectiveness of the proposed model. The project's website and videos of experiments can be found at https://hetercol.github.io/.
Authors: Lei Shen, Jianlong Jin, Ruixin Zhang, Huaen Li, Kai Zhao, Yingyi Zhang, Jingyun Zhang, Shouhong Ding, Yang Zhao, Wei Jia
Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric. However, the lack of large-scale public palmprint datasets limits further research and development of palmprint recognition. In this paper, we propose a novel realistic pseudo-palmprint generation (RPG) model to synthesize palmprints with massive identities. We first introduce a conditional modulation generator to improve the intra-class diversity. Then an identity-aware loss is proposed to ensure identity consistency against unpaired training. We further improve the B\'ezier palm creases generation strategy to guarantee identity independence. Extensive experimental results demonstrate that synthetic pretraining significantly boosts the recognition model performance. For example, our model improves the state-of-the-art B\'ezierPalm by more than $5\%$ and $14\%$ in terms of TAR@FAR=1e-6 under the $1:1$ and $1:3$ Open-set protocol. When accessing only $10\%$ of the real training data, our method still outperforms ArcFace with $100\%$ real training data, indicating that we are closer to real-data-free palmprint recognition.
Authors: Ruowei Wang, Yu Liu, Pei Su, Jianwei Zhang, Qijun Zhao
Shape generation is the practice of producing 3D shapes as various representations for 3D content creation. Previous studies on 3D shape generation have focused on shape quality and structure, without or less considering the importance of semantic information. Consequently, such generative models often fail to preserve the semantic consistency of shape structure or enable manipulation of the semantic attributes of shapes during generation. In this paper, we proposed a novel semantic generative model named 3D Semantic Subspace Traverser that utilizes semantic attributes for category-specific 3D shape generation and editing. Our method utilizes implicit functions as the 3D shape representation and combines a novel latent-space GAN with a linear subspace model to discover semantic dimensions in the local latent space of 3D shapes. Each dimension of the subspace corresponds to a particular semantic attribute, and we can edit the attributes of generated shapes by traversing the coefficients of those dimensions. Experimental results demonstrate that our method can produce plausible shapes with complex structures and enable the editing of semantic attributes. The code and trained models are available at https://github.com/TrepangCat/3D_Semantic_Subspace_Traverser
Authors: Jérémy Rousseau, Christian Alaka, Emma Covili, Hippolyte Mayard, Laura Misrachi, Willy Au
Medical radiography segmentation, and specifically dental radiography, is highly limited by the cost of labeling which requires specific expertise and labor-intensive annotations. In this work, we propose a straightforward pre-training method for semantic segmentation leveraging Denoising Diffusion Probabilistic Models (DDPM), which have shown impressive results for generative modeling. Our straightforward approach achieves remarkable performance in terms of label efficiency and does not require architectural modifications between pre-training and downstream tasks. We propose to first pre-train a Unet by exploiting the DDPM training objective, and then fine-tune the resulting model on a segmentation task. Our experimental results on the segmentation of dental radiographs demonstrate that the proposed method is competitive with state-of-the-art pre-training methods.
Authors: Renke Wang, Guimin Que, Shuo Chen, Xiang Li, Jun Li, Jian Yang
In this paper, we propose a novel method for single-view 3D style transfer that generates a unique 3D object with both shape and texture transfer. Our focus lies primarily on birds, a popular subject in 3D reconstruction, for which no existing single-view 3D transfer methods have been developed.The method we propose seeks to generate a 3D mesh shape and texture of a bird from two single-view images. To achieve this, we introduce a novel shape transfer generator that comprises a dual residual gated network (DRGNet), and a multi-layer perceptron (MLP). DRGNet extracts the features of source and target images using a shared coordinate gate unit, while the MLP generates spatial coordinates for building a 3D mesh. We also introduce a semantic UV texture transfer module that implements textural style transfer using semantic UV segmentation, which ensures consistency in the semantic meaning of the transferred regions. This module can be widely adapted to many existing approaches. Finally, our method constructs a novel 3D bird using a differentiable renderer. Experimental results on the CUB dataset verify that our method achieves state-of-the-art performance on the single-view 3D style transfer task. Code is available in https://github.com/wrk226/creative_birds.