Authors: Yao Lu, Yutian Huang, Jiaqi Nie, Zuohui Chen, Qi Xuan
Recently, the field of machine learning has undergone a transition from model-centric to data-centric. The advancements in diverse learning tasks have been propelled by the accumulation of more extensive datasets, subsequently facilitating the training of larger models on these datasets. However, these datasets remain relatively under-explored. To this end, we introduce a pioneering approach known as RK-core, to empower gaining a deeper understanding of the intricate hierarchical structure within datasets. Across several benchmark datasets, we find that samples with low coreness values appear less representative of their respective categories, and conversely, those with high coreness values exhibit greater representativeness. Correspondingly, samples with high coreness values make a more substantial contribution to the performance in comparison to those with low coreness values. Building upon this, we further employ RK-core to analyze the hierarchical structure of samples with different coreset selection methods. Remarkably, we find that a high-quality coreset should exhibit hierarchical diversity instead of solely opting for representative samples. The code is available at https://github.com/yaolu-zjut/Kcore.
Authors: Bosang Kim, Jonghyun Kim, Hyotae Lee, Lanying Jin, Jeongwon Ha, Dowoo Kwon, Jungpyo Kim, Wonhyeok Im, KyungMin Jin, Jungho Lee
In general, hand pose estimation aims to improve the robustness of model performance in the real-world scenes. However, it is difficult to enhance the robustness since existing datasets are obtained in restricted environments to annotate 3D information. Although neural networks quantitatively achieve a high estimation accuracy, unsatisfied results can be observed in visual quality. This discrepancy between quantitative results and their visual qualities remains an open issue in the hand pose representation. To this end, we propose a mesh represented recycle learning strategy for 3D hand pose and mesh estimation which reinforces synthesized hand mesh representation in a training phase. To be specific, a hand pose and mesh estimation model first predicts parametric 3D hand annotations (i.e., 3D keypoint positions and vertices for hand mesh) with real-world hand images in the training phase. Second, synthetic hand images are generated with self-estimated hand mesh representations. After that, the synthetic hand images are fed into the same model again. Thus, the proposed learning strategy simultaneously improves quantitative results and visual qualities by reinforcing synthetic mesh representation. To encourage consistency between original model output and its recycled one, we propose self-correlation loss which maximizes the accuracy and reliability of our learning strategy. Consequently, the model effectively conducts self-refinement on hand pose estimation by learning mesh representation from its own output. To demonstrate the effectiveness of our learning strategy, we provide extensive experiments on FreiHAND dataset. Notably, our learning strategy improves the performance on hand pose and mesh estimation without any extra computational burden during the inference.
Authors: Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Xintao Wang, Tien-Tsin Wong, Ying Shan
Enhancing a still image with motion offers more engaged visual experience. Traditional image animation techniques mainly focus on animating natural scenes with random dynamics, such as clouds and fluid, and thus limits their applicability to generic visual contents. To overcome this limitation, we explore the synthesis of dynamic content for open-domain images, converting them into animated videos. The key idea is to utilize the motion prior of text-to-video diffusion models by incorporating the image into the generative process as guidance. Given an image, we first project it into a text-aligned rich image embedding space using a learnable image encoding network, which facilitates the video model to digest the image content compatibly. However, some visual details still struggle to be preserved in the resulting videos. To supplement more precise image information, we further feed the full image to the diffusion model by concatenating it with the initial noises. Experimental results reveal that our proposed method produces visually convincing animated videos, exhibiting both natural motions and high fidelity to the input image. Comparative evaluation demonstrates the notable superiority of our approach over existing competitors. The source code will be released upon publication.
Authors: Matthew Hull, Zijie J. Wang, Duen Horng Chau
Deep Learning models, such as those used in an autonomous vehicle are vulnerable to adversarial attacks where an attacker could place an adversarial object in the environment, leading to mis-classification. Generating these adversarial objects in the digital space has been extensively studied, however successfully transferring these attacks from the digital realm to the physical realm has proven challenging when controlling for real-world environmental factors. In response to these limitations, we introduce REVAMP, an easy-to-use Python library that is the first-of-its-kind tool for creating attack scenarios with arbitrary objects and simulating realistic environmental factors, lighting, reflection, and refraction. REVAMP enables researchers and practitioners to swiftly explore various scenarios within the digital realm by offering a wide range of configurable options for designing experiments and using differentiable rendering to reproduce physically plausible adversarial objects. We will demonstrate and invite the audience to try REVAMP to produce an adversarial texture on a chosen object while having control over various scene parameters. The audience will choose a scene, an object to attack, the desired attack class, and the number of camera positions to use. Then, in real time, we show how this altered texture causes the chosen object to be mis-classified, showcasing the potential of REVAMP in real-world scenarios. REVAMP is open-source and available at https://github.com/poloclub/revamp.
Authors: Iman Yazdanpanah
SCGAN adds a similarity constraint between generated images and conditions as a regularization term on generative adversarial networks. Similarity constraint works as a tutor to instruct the generator network to comprehend the difference of representations based on conditions. We understand how SCGAN works on a deeper level. This understanding makes us realize that the similarity constraint functions like the contrastive loss function. We believe that a model with high understanding and intelligence measures the similarity between images based on their structure and high level features, just like humans do. Two major changes we applied to SCGAN in order to make a modified model are using SSIM to measure similarity between images and applying contrastive loss principles to the similarity constraint. The modified model performs better using FID and FactorVAE metrics. The modified model also has better generalisability compared to other models. Keywords Generative Adversarial Nets, Unsupervised Learning, Disentangled Representation Learning, Contrastive Disentanglement, SSIM
Authors: Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Teare
Textural Inversion, a prompt learning method, learns a singular embedding for a new "word" to represent image style and appearance, allowing it to be integrated into natural language sentences to generate novel synthesised images. However, identifying and integrating multiple object-level concepts within one scene poses significant challenges even when embeddings for individual concepts are attainable. This is further confirmed by our empirical tests. To address this challenge, we introduce a framework for Multi-Concept Prompt Learning (MCPL), where multiple new "words" are simultaneously learned from a single sentence-image pair. To enhance the accuracy of word-concept correlation, we propose three regularisation techniques: Attention Masking (AttnMask) to concentrate learning on relevant areas; Prompts Contrastive Loss (PromptCL) to separate the embeddings of different concepts; and Bind adjective (Bind adj.) to associate new "words" with known words. We evaluate via image generation, editing, and attention visualisation with diverse images. Extensive quantitative comparisons demonstrate that our method can learn more semantically disentangled concepts with enhanced word-concept correlation. Additionally, we introduce a novel dataset and evaluation protocol tailored for this new task of learning object-level concepts.
Authors: Rezaul Karim, Richard P. Wildes
Video segmentation encompasses a wide range of categories of problem formulation, e.g., object, scene, actor-action and multimodal video segmentation, for delineating task-specific scene components with pixel-level masks. Recently, approaches in this research area shifted from concentrating on ConvNet-based to transformer-based models. In addition, various interpretability approaches have appeared for transformer models and video temporal dynamics, motivated by the growing interest in basic scientific understanding, model diagnostics and societal implications of real-world deployment. Previous surveys mainly focused on ConvNet models on a subset of video segmentation tasks or transformers for classification tasks. Moreover, component-wise discussion of transformer-based video segmentation models has not yet received due focus. In addition, previous reviews of interpretability methods focused on transformers for classification, while analysis of video temporal dynamics modelling capabilities of video models received less attention. In this survey, we address the above with a thorough discussion of various categories of video segmentation, a component-wise discussion of the state-of-the-art transformer-based models, and a review of related interpretability methods. We first present an introduction to the different video segmentation task categories, their objectives, specific challenges and benchmark datasets. Next, we provide a component-wise review of recent transformer-based models and document the state of the art on different video segmentation tasks. Subsequently, we discuss post-hoc and ante-hoc interpretability methods for transformer models and interpretability methods for understanding the role of the temporal dimension in video models. Finally, we conclude our discussion with future research directions.
Authors: Weiyi Wu, Chongyang Gao, Joseph DiPalma, Soroush Vosoughi, Saeed Hassanpour
Recent advances in whole-slide image (WSI) scanners and computational capabilities have significantly propelled the application of artificial intelligence in histopathology slide analysis. While these strides are promising, current supervised learning approaches for WSI analysis come with the challenge of exhaustively labeling high-resolution slides - a process that is both labor-intensive and time-consuming. In contrast, self-supervised learning (SSL) pretraining strategies are emerging as a viable alternative, given that they don't rely on explicit data annotations. These SSL strategies are quickly bridging the performance disparity with their supervised counterparts. In this context, we introduce an SSL framework. This framework aims for transferable representation learning and semantically meaningful clustering by synergizing invariance loss and clustering loss in WSI analysis. Notably, our approach outperforms common SSL methods in downstream classification and clustering tasks, as evidenced by tests on the Camelyon16 and a pancreatic cancer dataset. The code and additional details are accessible at: https://github.com/wwyi1828/CluSiam.
Authors: Cheng-Fu Yang, Yen-Chun Chen, Jianwei Yang, Xiyang Dai, Lu Yuan, Yu-Chiang Frank Wang, Kai-Wei Chang
End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent's insensitivity to subtle changes in natural language instructions. To mitigate this issue, we propose explicitly aligning the agent's hidden states with the instructions via contrastive learning. Nevertheless, the semantic gap between high-level language instructions and the agent's low-level action space remains an obstacle. Therefore, we further introduce a novel concept of meta-actions to bridge the gap. Meta-actions are ubiquitous action patterns that can be parsed from the original action sequence. These patterns represent higher-level semantics that are intuitively aligned closer to the instructions. When meta-actions are applied as additional training signals, the agent generalizes better to unseen environments. Compared to a strong multi-modal Transformer baseline, we achieve a significant 4.5% absolute gain in success rate in unseen environments of ALFRED Embodied Instruction Following. Additional analysis shows that the contrastive objective and meta-actions are complementary in achieving the best results, and the resulting agent better aligns its states with corresponding instructions, making it more suitable for real-world embodied agents. The code is available at: https://github.com/joeyy5588/LACMA.
Authors: Gustavo A. Vargas Hakim, David Osowiechi, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers
Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.
Authors: Chenhao Xu, Chang-Tsun Li, Yongjian Hu, Chee Peng Lim, Douglas Creighton
Video instance segmentation, also known as multi-object tracking and segmentation, is an emerging computer vision research area introduced in 2019, aiming at detecting, segmenting, and tracking instances in videos simultaneously. By tackling the video instance segmentation tasks through effective analysis and utilization of visual information in videos, a range of computer vision-enabled applications (e.g., human action recognition, medical image processing, autonomous vehicle navigation, surveillance, etc) can be implemented. As deep-learning techniques take a dominant role in various computer vision areas, a plethora of deep-learning-based video instance segmentation schemes have been proposed. This survey offers a multifaceted view of deep-learning schemes for video instance segmentation, covering various architectural paradigms, along with comparisons of functional performance, model complexity, and computational overheads. In addition to the common architectural designs, auxiliary techniques for improving the performance of deep-learning models for video instance segmentation are compiled and discussed. Finally, we discuss a range of major challenges and directions for further investigations to help advance this promising research field.
Authors: Dayang Wang, Yongshun Xu, Shuo Han, Zhan Wu, Li Zhou, Bahareh Morovati, Hengyong Yu
Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In the fields of computer vision and natural language processing, masked autoencoders (MAE) have been recognized as an effective label-free self-pretraining method for transformers, due to their exceptional feature representation ability. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experiments results show that the proposed LoMAE can enhance the transformer's denoising performance and greatly relieve the dependence on the ground truth clean data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels.
Authors: Cong Yao
In this report, we introduce DocXChain, a powerful open-source toolchain for document parsing, which is designed and developed to automatically convert the rich information embodied in unstructured documents, such as text, tables and charts, into structured representations that are readable and manipulable by machines. Specifically, basic capabilities, including text detection, text recognition, table structure recognition and layout analysis, are provided. Upon these basic capabilities, we also build a set of fully functional pipelines for document parsing, i.e., general text reading, table parsing, and document structurization, to drive various applications related to documents in real-world scenarios. Moreover, DocXChain is concise, modularized and flexible, such that it can be readily integrated with existing tools, libraries or models (such as LangChain and ChatGPT), to construct more powerful systems that can accomplish more complicated and challenging tasks. The code of DocXChain is publicly available at:~\url{https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/Applications/DocXChain}
Authors: Dongshen Han, Sheng Zheng, Chaoning Zhang
As Segment Anything Model (SAM) becomes a popular foundation model in computer vision, its adversarial robustness has become a concern that cannot be ignored. This works investigates whether it is possible to attack SAM with image-agnostic Universal Adversarial Perturbation (UAP). In other words, we seek a single perturbation that can fool the SAM to predict invalid masks for most (if not all) images. We demonstrate convetional image-centric attack framework is effective for image-independent attacks but fails for universal adversarial attack. To this end, we propose a novel perturbation-centric framework that results in a UAP generation method based on self-supervised contrastive learning (CL), where the UAP is set to the anchor sample and the positive sample is augmented from the UAP. The representations of negative samples are obtained from the image encoder in advance and saved in a memory bank. The effectiveness of our proposed CL-based UAP generation method is validated by both quantitative and qualitative results. On top of the ablation study to understand various components in our proposed method, we shed light on the roles of positive and negative samples in making the generated UAP effective for attacking SAM.
Authors: Hanbo Bi, Yingchao Feng, Zhiyuan Yan, Yongqiang Mao, Wenhui Diao, Hongqi Wang, Xian Sun
Few-shot segmentation (FSS) is proposed to segment unknown class targets with just a few annotated samples. Most current FSS methods follow the paradigm of mining the semantics from the support images to guide the query image segmentation. However, such a pattern of `learning from others' struggles to handle the extreme intra-class variation, preventing FSS from being directly generalized to remote sensing scenes. To bridge the gap of intra-class variance, we develop a Dual-Mining network named DMNet for cross-image mining and self-mining, meaning that it no longer focuses solely on support images but pays more attention to the query image itself. Specifically, we propose a Class-public Region Mining (CPRM) module to effectively suppress irrelevant feature pollution by capturing the common semantics between the support-query image pair. The Class-specific Region Mining (CSRM) module is then proposed to continuously mine the class-specific semantics of the query image itself in a `filtering' and `purifying' manner. In addition, to prevent the co-existence of multiple classes in remote sensing scenes from exacerbating the collapse of FSS generalization, we also propose a new Known-class Meta Suppressor (KMS) module to suppress the activation of known-class objects in the sample. Extensive experiments on the iSAID and LoveDA remote sensing datasets have demonstrated that our method sets the state-of-the-art with a minimum number of model parameters. Significantly, our model with the backbone of Resnet-50 achieves the mIoU of 49.58% and 51.34% on iSAID under 1-shot and 5-shot settings, outperforming the state-of-the-art method by 1.8% and 1.12%, respectively. The code is publicly available at https://github.com/HanboBizl/DMNet.
Authors: Abhinav Agarwalla, Xuhua Huang, Jason Ziglar, Francesco Ferroni, Laura Leal-Taixé, James Hays, Aljoša Ošep, Deva Ramanan
State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up segmentation-centric fashion wherein they build upon semantic segmentation networks by utilizing clustering to obtain object instances. In this paper, we re-think this approach and propose a surprisingly simple yet effective detection-centric network for both LPS and tracking. Our network is modular by design and optimized for all aspects of both the panoptic segmentation and tracking task. One of the core components of our network is the object instance detection branch, which we train using point-level (modal) annotations, as available in segmentation-centric datasets. In the absence of amodal (cuboid) annotations, we regress modal centroids and object extent using trajectory-level supervision that provides information about object size, which cannot be inferred from single scans due to occlusions and the sparse nature of the lidar data. We obtain fine-grained instance segments by learning to associate lidar points with detected centroids. We evaluate our method on several 3D/4D LPS benchmarks and observe that our model establishes a new state-of-the-art among open-sourced models, outperforming recent query-based models.
Authors: Alzayat Saleh, Alex Olsen, Jake Wood, Bronson Philippa, Mostafa Rahimi Azghadi
Image classification is a crucial task in modern weed management and crop intervention technologies. However, the limited size, diversity, and balance of existing weed datasets hinder the development of deep learning models for generalizable weed identification. In addition, the expensive labelling requirements of mainstream fully-supervised weed classifiers make them cost- and time-prohibitive to deploy widely, for new weed species, and in site-specific weed management. This paper proposes a novel method for Weed Contrastive Learning through visual Representations (WeedCLR), that uses class-optimized loss with Von Neumann Entropy of deep representation for weed classification in long-tailed datasets. WeedCLR leverages self-supervised learning to learn rich and robust visual features without any labels and applies a class-optimized loss function to address the class imbalance problem in long-tailed datasets. WeedCLR is evaluated on two public weed datasets: CottonWeedID15, containing 15 weed species, and DeepWeeds, containing 8 weed species. WeedCLR achieves an average accuracy improvement of 4.3\% on CottonWeedID15 and 5.6\% on DeepWeeds over previous methods. It also demonstrates better generalization ability and robustness to different environmental conditions than existing methods without the need for expensive and time-consuming human annotations. These significant improvements make WeedCLR an effective tool for weed classification in long-tailed datasets and allows for more rapid and widespread deployment of site-specific weed management and crop intervention technologies.
Authors: Esteban Segarra Martinez, Ryan P. McMahan
Point clouds are a 3D space representation of an environment that was recorded with a high precision laser scanner. These scanners can suffer from environmental interference such as surface shading, texturing, and reflections. Because of this, point clouds may be contaminated with fake or incorrect colors. Current open source or proprietary tools offer limited or no access to correcting these visual errors automatically.
RecolorCloud is a tool developed to resolve these color conflicts by utilizing automated color recoloring. We offer the ability to deleting or recoloring outlier points automatically with users only needing to specify bounding box regions to effect colors. Results show a vast improvement of the photo-realistic quality of large point clouds. Additionally, users can quickly recolor a point cloud with set semantic segmentation colors.
Authors: Zijie Pan, Jiachen Lu, Xiatian Zhu, Li Zhang
High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative models, pretrained on extensive curated web datasets, using knowledge transfer techniques like Score Distillation Sampling (SDS). Efficiently addressing the requirements of high-resolution rendering often necessitates the adoption of latent representation-based models, such as the Latent Diffusion Model (LDM). In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM. However, this gradient propagation pathway has never been optimized, remaining uncontrolled during training. We find that the unregulated gradients adversely affect the 3D model's capacity in acquiring texture-related information from the image generative model, leading to poor quality appearance synthesis. To address this overarching challenge, we propose an innovative operation termed Pixel-wise Gradient Clipping (PGC) designed for seamless integration into existing 3D generative models, thereby enhancing their synthesis quality. Specifically, we control the magnitude of stochastic gradients by clipping the pixel-wise gradients efficiently, while preserving crucial texture-related gradient directions. Despite this simplicity and minimal extra cost, extensive experiments demonstrate the efficacy of our PGC in enhancing the performance of existing 3D generative models for high-resolution object rendering.
Authors: Jianping Yao, Son N. Tran, Samantha Sawyer, Saurabh Garg
The growing demand for sustainable development brings a series of information technologies to help agriculture production. Especially, the emergence of machine learning applications, a branch of artificial intelligence, has shown multiple breakthroughs which can enhance and revolutionize plant pathology approaches. In recent years, machine learning has been adopted for leaf disease classification in both academic research and industrial applications. Therefore, it is enormously beneficial for researchers, engineers, managers, and entrepreneurs to have a comprehensive view about the recent development of machine learning technologies and applications for leaf disease detection. This study will provide a survey in different aspects of the topic including data, techniques, and applications. The paper will start with publicly available datasets. After that, we summarize common machine learning techniques, including traditional (shallow) learning, deep learning, and augmented learning. Finally, we discuss related applications. This paper would provide useful resources for future study and application of machine learning for smart agriculture in general and leaf disease classification in particular.
Authors: Xiang Zhang, Senyu Li, Zijun Wu, Ning Shi
Recent advancements in multimodal techniques open exciting possibilities for models excelling in diverse tasks involving text, audio, and image processing. Models like GPT-4V, blending computer vision and language modeling, excel in complex text and image tasks. Numerous prior research endeavors have diligently examined the performance of these Vision Large Language Models (VLLMs) across tasks like object detection, image captioning and others. However, these analyses often focus on evaluating the performance of each modality in isolation, lacking insights into their cross-modal interactions. Specifically, questions concerning whether these vision-language models execute vision and language tasks consistently or independently have remained unanswered. In this study, we draw inspiration from recent investigations into multilingualism and conduct a comprehensive analysis of model's cross-modal interactions. We introduce a systematic framework that quantifies the capability disparities between different modalities in the multi-modal setting and provide a set of datasets designed for these evaluations. Our findings reveal that models like GPT-4V tend to perform consistently modalities when the tasks are relatively simple. However, the trustworthiness of results derived from the vision modality diminishes as the tasks become more challenging. Expanding on our findings, we introduce "Vision Description Prompting," a method that effectively improves performance in challenging vision-related tasks.
Authors: Junghyun Kim, Gi-Cheon Kang, Jaein Kim, Seoyun Yang, Minjoon Jung, Byoung-Tak Zhang
Language-Conditioned Robotic Grasping (LCRG) aims to develop robots that ground and grasp objects based on natural language instructions. While robots capable of recognizing personal objects like "my wallet" can interact more naturally with non-expert users, current LCRG systems primarily limit robots to understanding only generic expressions. To this end, we introduce a task scenario GraspMine with a novel dataset that aims to locate and grasp personal objects given personal indicators via learning from a single human-robot interaction. To address GraspMine, we propose Personalized Grasping Agent (PGA), that learns personal objects by propagating user-given information through a Reminiscence-a collection of raw images from the user's environment. Specifically, PGA acquires personal object information by a user presenting a personal object with its associated indicator, followed by PGA inspecting the object by rotating it. Based on the acquired information, PGA pseudo-labels objects in the Reminiscence by our proposed label propagation algorithm. Harnessing the information acquired from the interactions and the pseudo-labeled objects in the Reminiscence, PGA adapts the object grounding model to grasp personal objects. Experiments on GraspMine show that PGA significantly outperforms baseline methods both in offline and online settings, signifying its effectiveness and personalization applicability on real-world scenarios. Finally, qualitative analysis shows the effectiveness of PGA through a detailed investigation of results in each phase.
Authors: uya Yoshikawa, Tomoharu Iwata
The quality of explanations for the predictions of complex machine learning predictors is often measured using insertion and deletion metrics, which assess the faithfulness of the explanations, i.e., how correctly the explanations reflect the predictor's behavior. To improve the faithfulness, we propose insertion/deletion metric-aware explanation-based optimization (ID-ExpO), which optimizes differentiable predictors to improve both insertion and deletion scores of the explanations while keeping their predictive accuracy. Since the original insertion and deletion metrics are indifferentiable with respect to the explanations and directly unavailable for gradient-based optimization, we extend the metrics to be differentiable and use them to formalize insertion and deletion metric-based regularizers. The experimental results on image and tabular datasets show that the deep neural networks-based predictors fine-tuned using ID-ExpO enable popular post-hoc explainers to produce more faithful and easy-to-interpret explanations while keeping high predictive accuracy.
Authors: Haoqing Li, Jinfu Yang, Yifei Xu, Runshi Wang
Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotation. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient and cursory annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets reveal that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.
Authors: Guanqun Sun, Yizhi Pan, Weikun Kong, Zichang Xu, Jianhua Ma, Teeradaj Racharak, Le-Minh Nguyen, Junyi Xin
Great progress has been made in automatic medical image segmentation due to powerful deep representation learning. The influence of transformer has led to research into its variants, and large-scale replacement of traditional CNN modules. However, such trend often overlooks the intrinsic feature extraction capabilities of the transformer and potential refinements to both the model and the transformer module through minor adjustments. This study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to introduce the Transformer and dual attention block into the encoder and decoder of the traditional U-shaped architecture. Unlike prior transformer-based solutions, our DA-TransUNet utilizes attention mechanism of transformer and multifaceted feature extraction of DA-Block, which can efficiently combine global, local, and multi-scale features to enhance medical image segmentation. Meanwhile, experimental results show that a dual attention block is added before the Transformer layer to facilitate feature extraction in the U-net structure. Furthermore, incorporating dual attention blocks in skip connections can enhance feature transfer to the decoder, thereby improving image segmentation performance. Experimental results across various benchmark of medical image segmentation reveal that DA-TransUNet significantly outperforms the state-of-the-art methods. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.
Authors: Gia Minh Hoang, Youngjoo Lee, Jae Gwan Kim
Alzheimer's disease is one of the most common types of neurodegenerative disease, characterized by the accumulation of amyloid-beta plaque and tau tangles. Recently, deep learning approaches have shown promise in Alzheimer's disease diagnosis. In this study, we propose a reproducible model that utilizes a 3D convolutional neural network with a dual attention module for Alzheimer's disease classification. We trained the model in the ADNI database and verified the generalizability of our method in two independent datasets (AIBL and OASIS1). Our method achieved state-of-the-art classification performance, with an accuracy of 91.94% for MCI progression classification and 96.30% for Alzheimer's disease classification on the ADNI dataset. Furthermore, the model demonstrated good generalizability, achieving an accuracy of 86.37% on the AIBL dataset and 83.42% on the OASIS1 dataset. These results indicate that our proposed approach has competitive performance and generalizability when compared to recent studies in the field.
Authors: Mariia Zameshina (LIGM), Olivier Teytaud (TAU), Laurent Najman (LIGM)
Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Diverse Diffusion, a method for boosting image diversity beyond gender and ethnicity, spanning into richer realms, including color diversity.Diverse Diffusion is a general unsupervised technique that can be applied to existing text-to-image models. Our approach focuses on finding vectors in the Stable Diffusion latent space that are distant from each other. We generate multiple vectors in the latent space until we find a set of vectors that meets the desired distance requirements and the required batch size.To evaluate the effectiveness of our diversity methods, we conduct experiments examining various characteristics, including color diversity, LPIPS metric, and ethnicity/gender representation in images featuring humans.The results of our experiments emphasize the significance of diversity in generating realistic and varied images, offering valuable insights for improving text-to-image models. Through the enhancement of image diversity, our approach contributes to the creation of more inclusive and representative AI-generated art.
Authors: Mariia Zameshina (LIGM), Marlene Careil (MM, IDS), Olivier Teytaud (LRI, TANC), Laurent Najman (LIGM)
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression.In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications. Drawing inspiration from Fawkes, our method entails shifting the original image within the embedding space towards a decoy image.We evaluate our approach using privacy metrics on traditional and novel facial image datasets. Additionally, we propose new criteria for evaluating the robustness of privacy-protection methods against unknown image recognition techniques, and we demonstrate that our approach is effective even in unknown embedding transfer scenarios. We also provide a human evaluation that further proves that the modified image preserves its utility as it remains recognisable as an image of the same person by friends and family.
Authors: Hussain Alasmawi, Leanne Bricker, Mohammad Yaqub
Ultrasound is the primary imaging modality in clinical practice during pregnancy. More than 140M fetuses are born yearly, resulting in numerous scans. The availability of a large volume of fetal ultrasound scans presents the opportunity to train robust machine learning models. However, the abundance of scans also has its challenges, as manual labeling of each image is needed for supervised methods. Labeling is typically labor-intensive and requires expertise to annotate the images accurately. This study presents an unsupervised approach for automatically clustering ultrasound images into a large range of fetal views, reducing or eliminating the need for manual labeling. Our Fetal Ultrasound Semantic Clustering (FUSC) method is developed using a large dataset of 88,063 images and further evaluated on an additional unseen dataset of 8,187 images achieving over 92% clustering purity. The result of our investigation hold the potential to significantly impact the field of fetal ultrasound imaging and pave the way for more advanced automated labeling solutions. Finally, we make the code and the experimental setup publicly available to help advance the field.
Authors: Sidi Wu, Yizi Chen, Konrad Schindler, Lorenz Hurni
Historical maps provide useful spatio-temporal information on the Earth's surface before modern earth observation techniques came into being. To extract information from maps, neural networks, which gain wide popularity in recent years, have replaced hand-crafted map processing methods and tedious manual labor. However, aleatoric uncertainty, known as data-dependent uncertainty, inherent in the drawing/scanning/fading defects of the original map sheets and inadequate contexts when cropping maps into small tiles considering the memory limits of the training process, challenges the model to make correct predictions. As aleatoric uncertainty cannot be reduced even with more training data collected, we argue that complementary spatio-temporal contexts can be helpful. To achieve this, we propose a U-Net-based network that fuses spatio-temporal features with cross-attention transformers (U-SpaTem), aggregating information at a larger spatial range as well as through a temporal sequence of images. Our model achieves a better performance than other state-or-art models that use either temporal or spatial contexts. Compared with pure vision transformers, our model is more lightweight and effective. To the best of our knowledge, leveraging both spatial and temporal contexts have been rarely explored before in the segmentation task. Even though our application is on segmenting historical maps, we believe that the method can be transferred into other fields with similar problems like temporal sequences of satellite images. Our code is freely accessible at https://github.com/chenyizi086/wu.2023.sigspatial.git.
Authors: Zeynep Hilal Kilimci, Mustafa Yalcin, Ayhan Kucukmanisa, Amit Kumar Mishra
Heart disease, also known as cardiovascular disease, is a prevalent and critical medical condition characterized by the impairment of the heart and blood vessels, leading to various complications such as coronary artery disease, heart failure, and myocardial infarction. The timely and accurate detection of heart disease is of paramount importance in clinical practice. Early identification of individuals at risk enables proactive interventions, preventive measures, and personalized treatment strategies to mitigate the progression of the disease and reduce adverse outcomes. In recent years, the field of heart disease detection has witnessed notable advancements due to the integration of sophisticated technologies and computational approaches. These include machine learning algorithms, data mining techniques, and predictive modeling frameworks that leverage vast amounts of clinical and physiological data to improve diagnostic accuracy and risk stratification. In this work, we propose to detect heart disease from ECG images using cutting-edge technologies, namely vision transformer models. These models are Google-Vit, Microsoft-Beit, and Swin-Tiny. To the best of our knowledge, this is the initial endeavor concentrating on the detection of heart diseases through image-based ECG data by employing cuttingedge technologies namely, transformer models. To demonstrate the contribution of the proposed framework, the performance of vision transformer models are compared with state-of-the-art studies. Experiment results show that the proposed framework exhibits remarkable classification results.
Authors: William Ndzimbong, Cyril Fourniol, Loic Themyr, Nicolas Thome, Yvonne Keeza, Beniot Sauer, Pierre-Thierry Piechaud, Arnaud Mejean, Jacques Marescaux, Daniel George, Didier Mutter, Alexandre Hostettler, Toby Collins
Inter-modal image registration (IMIR) and image segmentation with abdominal Ultrasound (US) data has many important clinical applications, including image-guided surgery, automatic organ measurement and robotic navigation. However, research is severely limited by the lack of public datasets. We propose TRUSTED (the Tridimensional Renal Ultra Sound TomodEnsitometrie Dataset), comprising paired transabdominal 3DUS and CT kidney images from 48 human patients (96 kidneys), including segmentation, and anatomical landmark annotations by two experienced radiographers. Inter-rater segmentation agreement was over 94 (Dice score), and gold-standard segmentations were generated using the STAPLE algorithm. Seven anatomical landmarks were annotated, important for IMIR systems development and evaluation. To validate the dataset's utility, 5 competitive Deep Learning models for automatic kidney segmentation were benchmarked, yielding average DICE scores from 83.2% to 89.1% for CT, and 61.9% to 79.4% for US images. Three IMIR methods were benchmarked, and Coherent Point Drift performed best with an average Target Registration Error of 4.53mm. The TRUSTED dataset may be used freely researchers to develop and validate new segmentation and IMIR methods.
Authors: Shreyasi Pathak, Jörg Schlötterer, Jeroen Geerdink, Onno Dirk Vijlbrief, Maurice van Keulen, Christin Seifert
Automatic methods for early detection of breast cancer on mammography can significantly decrease mortality. Broad uptake of those methods in hospitals is currently hindered because the methods have too many constraints. They assume annotations available for single images or even regions-of-interest (ROIs), and a fixed number of images per patient. Both assumptions do not hold in a general hospital setting. Relaxing those assumptions results in a weakly supervised learning setting, where labels are available per case, but not for individual images or ROIs. Not all images taken for a patient contain malignant regions and the malignant ROIs cover only a tiny part of an image, whereas most image regions represent benign tissue. In this work, we investigate a two-level multi-instance learning (MIL) approach for case-level breast cancer prediction on two public datasets (1.6k and 5k cases) and an in-house dataset of 21k cases. Observing that breast cancer is usually only present in one side, while images of both breasts are taken as a precaution, we propose a domain-specific MIL pooling variant. We show that two-level MIL can be applied in realistic clinical settings where only case labels, and a variable number of images per patient are available. Data in realistic settings scales with continuous patient intake, while manual annotation efforts do not. Hence, research should focus in particular on unsupervised ROI extraction, in order to improve breast cancer prediction for all patients.
Authors: Jiaxu Zhang, Shaoli Huang, Zhigang Tu, Xin Chen, Xiaohang Zhan, Gang Yu, Ying Shan
Previous motion generation methods are limited to the pre-rigged 3D human model, hindering their applications in the animation of various non-rigged characters. In this work, we present TapMo, a Text-driven Animation Pipeline for synthesizing Motion in a broad spectrum of skeleton-free 3D characters. The pivotal innovation in TapMo is its use of shape deformation-aware features as a condition to guide the diffusion model, thereby enabling the generation of mesh-specific motions for various characters. Specifically, TapMo comprises two main components - Mesh Handle Predictor and Shape-aware Diffusion Module. Mesh Handle Predictor predicts the skinning weights and clusters mesh vertices into adaptive handles for deformation control, which eliminates the need for traditional skeletal rigging. Shape-aware Motion Diffusion synthesizes motion with mesh-specific adaptations. This module employs text-guided motions and mesh features extracted during the first stage, preserving the geometric integrity of the animations by accounting for the character's shape and deformation. Trained in a weakly-supervised manner, TapMo can accommodate a multitude of non-human meshes, both with and without associated text motions. We demonstrate the effectiveness and generalizability of TapMo through rigorous qualitative and quantitative experiments. Our results reveal that TapMo consistently outperforms existing auto-animation methods, delivering superior-quality animations for both seen or unseen heterogeneous 3D characters.
Authors: Thalles Silva, Adín Ramírez Rivera
We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent without additional non-differentiable modules to solve the cluster assignment problem. CARP optimizes a new pretext task based on random partitions of prototypes that regularizes the model and enforces consistency between views' assignments. Additionally, our method improves training stability and prevents collapsed solutions in joint-embedding training. Through an extensive evaluation, we demonstrate that CARP's representations are suitable for learning downstream tasks. We evaluate CARP's representations capabilities in 17 datasets across many standard protocols, including linear evaluation, few-shot classification, k-NN, k-means, image retrieval, and copy detection. We compare CARP performance to 11 existing self-supervised methods. We extensively ablate our method and demonstrate that our proposed random partition pretext task improves the quality of the learned representations by devising multiple random classification tasks. In transfer learning tasks, CARP achieves the best performance on average against many SSL methods trained for a longer time.
Authors: Zhihong Chen, Zilei Wang, Yixin Zhang
Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation phase, which is typically limited to high-confidence pseudo-labels and results in a loss of information. To address this issue, we propose a new approach to take full advantage of pseudo-labels by introducing high and low confidence thresholds. Specifically, the pseudo-labels with confidence scores above the high threshold are used conventionally, while those between the low and high thresholds are exploited using the Low-confidence Pseudo-labels Utilization (LPU) module. The LPU module consists of Proposal Soft Training (PST) and Local Spatial Contrastive Learning (LSCL). PST generates soft labels of proposals for soft training, which can mitigate the label mismatch problem. LSCL exploits the local spatial relationship of proposals to improve the model's ability to differentiate between spatially adjacent proposals, thereby optimizing representational features further. Combining the two components overcomes the challenges faced by traditional methods in utilizing low-confidence pseudo-labels. Extensive experiments on five cross-domain object detection benchmarks demonstrate that our proposed method outperforms the previous SFOD methods, achieving state-of-the-art performance.
Authors: Jun Liu, Jiantao Zhou, Jinyu Tian, Weiwei Sun
With the increasing prevalence of cloud computing platforms, ensuring data privacy during the cloud-based image related services such as classification has become crucial. In this study, we propose a novel privacypreserving image classification scheme that enables the direct application of classifiers trained in the plaintext domain to classify encrypted images, without the need of retraining a dedicated classifier. Moreover, encrypted images can be decrypted back into their original form with high fidelity (recoverable) using a secret key. Specifically, our proposed scheme involves utilizing a feature extractor and an encoder to mask the plaintext image through a newly designed Noise-like Adversarial Example (NAE). Such an NAE not only introduces a noise-like visual appearance to the encrypted image but also compels the target classifier to predict the ciphertext as the same label as the original plaintext image. At the decoding phase, we adopt a Symmetric Residual Learning (SRL) framework for restoring the plaintext image with minimal degradation. Extensive experiments demonstrate that 1) the classification accuracy of the classifier trained in the plaintext domain remains the same in both the ciphertext and plaintext domains; 2) the encrypted images can be recovered into their original form with an average PSNR of up to 51+ dB for the SVHN dataset and 48+ dB for the VGGFace2 dataset; 3) our system exhibits satisfactory generalization capability on the encryption, decryption and classification tasks across datasets that are different from the training one; and 4) a high-level of security is achieved against three potential threat models. The code is available at https://github.com/csjunjun/RIC.git.
Authors: Jun Liu, Jiantao Zhou, Haiwei Wu, Weiwei Sun, Jinyu Tian
Online Social Networks (OSNs) have blossomed into prevailing transmission channels for images in the modern era. Adversarial examples (AEs) deliberately designed to mislead deep neural networks (DNNs) are found to be fragile against the inevitable lossy operations conducted by OSNs. As a result, the AEs would lose their attack capabilities after being transmitted over OSNs. In this work, we aim to design a new framework for generating robust AEs that can survive the OSN transmission; namely, the AEs before and after the OSN transmission both possess strong attack capabilities. To this end, we first propose a differentiable network termed SImulated OSN (SIO) to simulate the various operations conducted by an OSN. Specifically, the SIO network consists of two modules: 1) a differentiable JPEG layer for approximating the ubiquitous JPEG compression and 2) an encoder-decoder subnetwork for mimicking the remaining operations. Based upon the SIO network, we then formulate an optimization framework to generate robust AEs by enforcing model outputs with and without passing through the SIO to be both misled. Extensive experiments conducted over Facebook, WeChat and QQ demonstrate that our attack methods produce more robust AEs than existing approaches, especially under small distortion constraints; the performance gain in terms of Attack Success Rate (ASR) could be more than 60%. Furthermore, we build a public dataset containing more than 10,000 pairs of AEs processed by Facebook, WeChat or QQ, facilitating future research in the robust AEs generation. The dataset and code are available at https://github.com/csjunjun/RobustOSNAttack.git.
Authors: Yuanxing Xu, Yuting Wei, Bin Wu
The surge in video and social media content underscores the need for a deeper understanding of multimedia data. Most of the existing mature video understanding techniques perform well with short formats and content that requires only shallow understanding, but do not perform well with long format videos that require deep understanding and reasoning. Deep Video Understanding (DVU) Challenge aims to push the boundaries of multimodal extraction, fusion, and analytics to address the problem of holistically analyzing long videos and extract useful knowledge to solve different types of queries. This paper introduces a query-aware method for long video localization and relation discrimination, leveraging an imagelanguage pretrained model. This model adeptly selects frames pertinent to queries, obviating the need for a complete movie-level knowledge graph. Our approach achieved first and fourth positions for two groups of movie-level queries. Sufficient experiments and final rankings demonstrate its effectiveness and robustness.
Authors: Yiming Wang, Qian Huang, Bin Tang, Huashan Sun, Xing Li
Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15\% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93\% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.
Authors: Aravinda Reddy PN, K.Sreenivasa Rao, Raghavendra Ramachandra, Pabitra mitra
We present a novel face swapping method using the progressively growing structure of a pre-trained StyleGAN. Previous methods use different encoder decoder structures, embedding integration networks to produce high-quality results, but their quality suffers from entangled representation. We disentangle semantics by deriving identity and attribute features separately. By learning to map the concatenated features into the extended latent space, we leverage the state-of-the-art quality and its rich semantic extended latent space. Extensive experiments suggest that the proposed method successfully disentangles identity and attribute features and outperforms many state-of-the-art face swapping methods, both qualitatively and quantitatively.
Authors: Yuanduo Hong, Jue Wang, Weichao Sun, Huihui Pan
In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic segmentation. Current state-of-the-art systems incorporate numerous inductive biases and employ cumbersome decoders. Building upon the original motivations of plain ViTs, which are simplicity and generality, we explore high-performance `minimalist' systems to this end. Our primary purpose is to provide simple and efficient baselines for practical semantic segmentation with plain ViTs. Specifically, we first explore the feasibility and methodology for achieving high-performance semantic segmentation using the last feature map. As a result, we introduce the PlainSeg, a model comprising only three 3$\times$3 convolutions in addition to the transformer layers (either encoder or decoder). In this process, we offer insights into two underlying principles: (i) high-resolution features are crucial to high performance in spite of employing simple up-sampling techniques and (ii) the slim transformer decoder requires a much larger learning rate than the wide transformer decoder. On this basis, we further present the PlainSeg-Hier, which allows for the utilization of hierarchical features. Extensive experiments on four popular benchmarks demonstrate the high performance and efficiency of our methods. They can also serve as powerful tools for assessing the transfer ability of base models in semantic segmentation. Code is available at \url{https://github.com/ydhongHIT/PlainSeg}.
Authors: Joshua Butke, Noriaki Hashimoto, Ichiro Takeuchi, Hiroaki Miyoshi, Koichi Ohshima, Jun Sakuma
Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is computationally expensive as, for each image, all instances have to be processed simultaneously. The MLP-Mixer is an under-explored alternative model to common vision transformers, especially for large-scale datasets. Due to the lack of a self-attention mechanism, they have linear computational complexity to the number of input patches but achieve comparable performance on natural image datasets. We propose a combination of feature embedding and clustering to preprocess the full whole-slide image into a reduced prototype representation which can then serve as input to a suitable MLP-Mixer architecture. Our experiments on two public benchmarks and one inhouse malignant lymphoma dataset show comparable performance to current state-of-the-art methods, while achieving lower training costs in terms of computational time and memory load. Code is publicly available at https://github.com/butkej/ProtoMixer.
Authors: David Liu, Zhengkun Li, Zihao Wu, Changying Li
Robotic crop phenotyping has emerged as a key technology to assess crops' morphological and physiological traits at scale. These phenotypical measurements are essential for developing new crop varieties with the aim of increasing productivity and dealing with environmental challenges such as climate change. However, developing and deploying crop phenotyping robots face many challenges such as complex and variable crop shapes that complicate robotic object detection, dynamic and unstructured environments that baffle robotic control, and real-time computing and managing big data that challenge robotic hardware/software. This work specifically tackles the first challenge by proposing a novel Digital-Twin(DT)MARS-CycleGAN model for image augmentation to improve our Modular Agricultural Robotic System (MARS)'s crop object detection from complex and variable backgrounds. Our core idea is that in addition to the cycle consistency losses in the CycleGAN model, we designed and enforced a new DT-MARS loss in the deep learning model to penalize the inconsistency between real crop images captured by MARS and synthesized images sensed by DT MARS. Therefore, the generated synthesized crop images closely mimic real images in terms of realism, and they are employed to fine-tune object detectors such as YOLOv8. Extensive experiments demonstrated that our new DT/MARS-CycleGAN framework significantly boosts our MARS' crop object/row detector's performance, contributing to the field of robotic crop phenotyping.
Authors: Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang
Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. In this paper, we propose to learn heterogeneous anomaly distributions using the limited anomaly examples to address this issue. To this end, we introduce a novel approach, namely Anomaly Heterogeneity Learning (AHL), that simulates a diverse set of heterogeneous (seen and unseen) anomaly distributions and then utilizes them to learn a unified heterogeneous abnormality model. Further, AHL is a generic framework that existing OSAD models can plug and play for enhancing their abnormality modeling. Extensive experiments on nine real-world anomaly detection datasets show that AHL can 1) substantially enhance different state-of-the-art (SOTA) OSAD models in detecting both seen and unseen anomalies, achieving new SOTA performance on a large set of datasets, and 2) effectively generalize to unseen anomalies in new target domains.
Authors: Lin Li, Yifei Wang, Chawin Sitawarin, Michael Spratling
Existing works have made great progress in improving adversarial robustness, but typically test their method only on data from the same distribution as the training data, i.e. in-distribution (ID) testing. As a result, it is unclear how such robustness generalizes under input distribution shifts, i.e. out-of-distribution (OOD) testing. This is a concerning omission as such distribution shifts are unavoidable when methods are deployed in the wild. To address this issue we propose a benchmark named OODRobustBench to comprehensively assess OOD adversarial robustness using 23 dataset-wise shifts (i.e. naturalistic shifts in input distribution) and 6 threat-wise shifts (i.e., unforeseen adversarial threat models). OODRobustBench is used to assess 706 robust models using 60.7K adversarial evaluations. This large-scale analysis shows that: 1) adversarial robustness suffers from a severe OOD generalization issue; 2) ID robustness correlates strongly with OOD robustness, in a positive linear way, under many distribution shifts. The latter enables the prediction of OOD robustness from ID robustness. Based on this, we are able to predict the upper limit of OOD robustness for existing robust training schemes. The results suggest that achieving OOD robustness requires designing novel methods beyond the conventional ones. Last, we discover that extra data, data augmentation, advanced model architectures and particular regularization approaches can improve OOD robustness. Noticeably, the discovered training schemes, compared to the baseline, exhibit dramatically higher robustness under threat shift while keeping high ID robustness, demonstrating new promising solutions for robustness against both multi-attack and unforeseen attacks.
Authors: Cheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang, Yen-Yu Lin
We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation. However, existing methods require extra 2D annotations to achieve 2D-3D information fusion. Considering the high annotation cost of point clouds, effective 2D and 3D feature fusion based on weakly supervised learning is in great demand. To this end, we propose a transformer model with two encoders and one decoder for weakly supervised point cloud segmentation using only scene-level class tags. Specifically, the two encoders compute the self-attended features for 3D point clouds and 2D multi-view images, respectively. The decoder implements interlaced 2D-3D cross-attention and carries out implicit 2D and 3D feature fusion. We alternately switch the roles of queries and key-value pairs in the decoder layers. It turns out that the 2D and 3D features are iteratively enriched by each other. Experiments show that it performs favorably against existing weakly supervised point cloud segmentation methods by a large margin on the S3DIS and ScanNet benchmarks. The project page will be available at https://jimmy15923.github.io/mit_web/.
Authors: Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong
Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR decomposes different types of degradations adaptively, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively recognize and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalization capability of our method.
Authors: Jack Breen, Katie Allen, Kieran Zucker, Geoff Hall, Nishant Ravikumar, Nicolas M. Orsi
For many patients, current ovarian cancer treatments offer limited clinical benefit. For some therapies, it is not possible to predict patients' responses, potentially exposing them to the adverse effects of treatment without any therapeutic benefit. As part of the automated prediction of treatment effectiveness in ovarian cancer using histopathological images (ATEC23) challenge, we evaluated the effectiveness of deep learning to predict whether a course of treatment including the antiangiogenic drug bevacizumab could contribute to remission or prevent disease progression for at least 6 months in a set of 282 histopathology whole slide images (WSIs) from 78 ovarian cancer patients. Our approach used a pretrained Hierarchical Image Pyramid Transformer (HIPT) to extract region-level features and an attention-based multiple instance learning (ABMIL) model to aggregate features and classify whole slides. The optimal HIPT-ABMIL model had an internal balanced accuracy of 60.2% +- 2.9% and an AUC of 0.646 +- 0.033. Histopathology-specific model pretraining was found to be beneficial to classification performance, though hierarchical transformers were not, with a ResNet feature extractor achieving similar performance. Due to the dataset being small and highly heterogeneous, performance was variable across 5-fold cross-validation folds, and there were some extreme differences between validation and test set performance within folds. The model did not generalise well to tissue microarrays, with accuracy worse than random chance. It is not yet clear whether ovarian cancer WSIs contain information that can be used to accurately predict treatment response, with further validation using larger, higher-quality datasets required.
Authors: Zheyuan Zhang, Lanhong Yao, Bin Wang, Debesh Jha, Elif Keles, Alpay Medetalibeyoglu, Ulas Bagci
Large-scale, big-variant, and high-quality data are crucial for developing robust and successful deep-learning models for medical applications since they potentially enable better generalization performance and avoid overfitting. However, the scarcity of high-quality labeled data always presents significant challenges. This paper proposes a novel approach to address this challenge by developing controllable diffusion models for medical image synthesis, called EMIT-Diff. We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data that preserve the essential characteristics of the original medical images by incorporating edge information of objects to guide the synthesis process. In our approach, we ensure that the synthesized samples adhere to medically relevant constraints and preserve the underlying structure of imaging data. Due to the random sampling process by the diffusion model, we can generate an arbitrary number of synthetic images with diverse appearances. To validate the effectiveness of our proposed method, we conduct an extensive set of medical image segmentation experiments on multiple datasets, including Ultrasound breast (+13.87%), CT spleen (+0.38%), and MRI prostate (+7.78%), achieving significant improvements over the baseline segmentation methods. For the first time, to our best knowledge, the promising results demonstrate the effectiveness of our EMIT-Diff for medical image segmentation tasks and show the feasibility of introducing a first-ever text-guided diffusion model for general medical image segmentation tasks. With carefully designed ablation experiments, we investigate the influence of various data augmentation ratios, hyper-parameter settings, patch size for generating random merging mask settings, and combined influence with different network architectures.
Authors: Peibei Cao, Rafal K. Mantiuk, Kede Ma
High dynamic range (HDR) imaging has gained increasing popularity for its ability to faithfully reproduce the luminance levels in natural scenes. Accordingly, HDR image quality assessment (IQA) is crucial but has been superficially treated. The majority of existing IQA models are developed for and calibrated against low dynamic range (LDR) images, which have been shown to be poorly correlated with human perception of HDR image quality. In this work, we propose a family of HDR IQA models by transferring the recent advances in LDR IQA. The key step in our approach is to specify a simple inverse display model that decomposes an HDR image to a set of LDR images with different exposures, which will be assessed by existing LDR quality models. The local quality scores of each exposure are then aggregated with the help of a simple well-exposedness measure into a global quality score for each exposure, which will be further weighted across exposures to obtain the overall quality score. When assessing LDR images, the proposed HDR quality models reduce gracefully to the original LDR ones with the same performance. Experiments on four human-rated HDR image datasets demonstrate that our HDR quality models are consistently better than existing IQA methods, including the HDR-VDP family. Moreover, we demonstrate their strengths in perceptual optimization of HDR novel view synthesis.
Authors: Oriane Siméoni, Éloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick Pérez
The recent enthusiasm for open-world vision systems show the high interest of the community to perform perception tasks outside of the closed-vocabulary benchmark setups which have been so popular until now. Being able to discover objects in images/videos without knowing in advance what objects populate the dataset is an exciting prospect. But how to find objects without knowing anything about them? Recent works show that it is possible to perform class-agnostic unsupervised object localization by exploiting self-supervised pre-trained features. We propose here a survey of unsupervised object localization methods that discover objects in images without requiring any manual annotation in the era of self-supervised ViTs. We gather links of discussed methods in the repository https://github.com/valeoai/Awesome-Unsupervised-Object-Localization.
Authors: Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduce a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. To boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. The designed asymmetric predictor head and an InfoNCE warm-up strategy enhance the robustness to hyper-parameters and benefit the resulting performance. Experimental results show that our proposed ReSSL substantially outperforms the state-of-the-art methods across different network architectures, including various lightweight networks (\eg, EfficientNet and MobileNet).
Authors: Changhun Lee, Hyungjun Kim, Eunhyeok Park, Jae-Joon Kim
Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights are constrained to the binary values. To compensate for the accuracy drop, we propose a novel BNN design called Binary Neural Network with INSTAnce-aware threshold (INSTA-BNN), which controls the quantization threshold dynamically in an input-dependent or instance-aware manner. According to our observation, higher-order statistics can be a representative metric to estimate the characteristics of the input distribution. INSTA-BNN is designed to adjust the threshold dynamically considering various information, including higher-order statistics, but it is also optimized judiciously to realize minimal overhead on a real device. Our extensive study shows that INSTA-BNN outperforms the baseline by 3.0% and 2.8% on the ImageNet classification task with comparable computing cost, achieving 68.5% and 72.2% top-1 accuracy on ResNet-18 and MobileNetV1 based models, respectively.
Authors: Yumeng Li, Ning Gao, Hanna Ziesche, Gerhard Neumann
We present a novel meta-learning approach for 6D pose estimation on unknown objects. In contrast to ``instance-level" and ``category-level" pose estimation methods, our algorithm learns object representation in a category-agnostic way, which endows it with strong generalization capabilities across object categories. Specifically, we employ a neural process-based meta-learning approach to train an encoder to capture texture and geometry of an object in a latent representation, based on very few RGB-D images and ground-truth keypoints. The latent representation is then used by a simultaneously meta-trained decoder to predict the 6D pose of the object in new images. Furthermore, we propose a novel geometry-aware decoder for the keypoint prediction using a Graph Neural Network (GNN), which explicitly takes geometric constraints specific to each object into consideration. To evaluate our algorithm, extensive experiments are conducted on the \linemod dataset, and on our new fully-annotated synthetic datasets generated from Multiple Categories in Multiple Scenes (MCMS). Experimental results demonstrate that our model performs well on unseen objects with very different shapes and appearances. Remarkably, our model also shows robust performance on occluded scenes although trained fully on data without occlusion. To our knowledge, this is the first work exploring \textbf{cross-category level} 6D pose estimation.
Authors: Xin Zheng, Jianke Zhu
Prism-based LiDARs are more compact and cheaper than the conventional mechanical multi-line spinning LiDARs, which have become increasingly popular in robotics, recently. However, there are several challenges for these new LiDAR sensors, including small field of view, severe motion distortions, and irregular patterns, which hinder them from being widely used in LiDAR odometry, practically. To tackle these problems, we present an effective continuous-time LiDAR odometry (ECTLO) method for the Risley-prism-based LiDARs with non-repetitive scanning patterns. A single range image covering historical points in LiDAR's small FoV is adopted for efficient map representation. To account for the noisy data from occlusions after map updating, a filter-based point-to-plane Gaussian Mixture Model is used for robust registration. Moreover, a LiDAR-only continuous-time motion model is employed to relieve the inevitable distortions. Extensive experiments have been conducted on various testbeds using the prism-based LiDARs with different scanning patterns, whose promising results demonstrate the efficacy of our proposed approach.
Authors: Aurélien Colin (1,2), Pierre Tandeo (1), Charles Peureux (2), Romain Husson (2), Nicolas Longépé (3), Ronan Fablet (1) ((1) IMT Atlantique, Lab-STICC, UMR CNRS, France, (2) Collecte Localisation Satellites, Brest, France, (3) Phi-lab Explore Office, ESRIN, European Space Agency (ESA), Frascati, Italy)
Remote sensing of rainfall events is critical for both operational and scientific needs, including for example weather forecasting, extreme flood mitigation, water cycle monitoring, etc. Ground-based weather radars, such as NOAA's Next-Generation Radar (NEXRAD), provide reflectivity and precipitation estimates of rainfall events. However, their observation range is limited to a few hundred kilometers, prompting the exploration of other remote sensing methods, particularly over the open ocean, that represents large areas not covered by land-based radars. Here we propose a deep learning approach to deliver a three-class segmentation of SAR observations in terms of rainfall regimes. SAR satellites deliver very high resolution observations with a global coverage. This seems particularly appealing to inform fine-scale rain-related patterns, such as those associated with convective cells with characteristic scales of a few kilometers. We demonstrate that a convolutional neural network trained on a collocated Sentinel-1/NEXRAD dataset clearly outperforms state-of-the-art filtering schemes such as the Koch's filters. Our results indicate high performance in segmenting precipitation regimes, delineated by thresholds at 24.7, 31.5, and 38.8 dBZ. Compared to current methods that rely on Koch's filters to draw binary rainfall maps, these multi-threshold learning-based models can provide rainfall estimation. They may be of interest in improving high-resolution SAR-derived wind fields, which are degraded by rainfall, and provide an additional tool for the study of rain cells.
Authors: Meiling Fang, Wufei Yang, Arjan Kuijper, Vitomir Struc, Naser Damer
Face recognition (FR) algorithms have been proven to exhibit discriminatory behaviors against certain demographic and non-demographic groups, raising ethical and legal concerns regarding their deployment in real-world scenarios. Despite the growing number of fairness studies in FR, the fairness of face presentation attack detection (PAD) has been overlooked, mainly due to the lack of appropriately annotated data. To avoid and mitigate the potential negative impact of such behavior, it is essential to assess the fairness in face PAD and develop fair PAD models. To enable fairness analysis in face PAD, we present a Combined Attribute Annotated PAD Dataset (CAAD-PAD), offering seven human-annotated attribute labels. Then, we comprehensively analyze the fairness of PAD and its relation to the nature of the training data and the Operational Decision Threshold Assignment (ODTA) through a set of face PAD solutions. Additionally, we propose a novel metric, the Accuracy Balanced Fairness (ABF), that jointly represents both the PAD fairness and the absolute PAD performance. The experimental results pointed out that female and faces with occluding features (e.g. eyeglasses, beard, etc.) are relatively less protected than male and non-occlusion groups by all PAD solutions. To alleviate this observed unfairness, we propose a plug-and-play data augmentation method, FairSWAP, to disrupt the identity/semantic information and encourage models to mine the attack clues. The extensive experimental results indicate that FairSWAP leads to better-performing and fairer face PADs in 10 out of 12 investigated cases.
Authors: Chen Qian, Yuncheng Gao, Mingyang Han, Zi Wang, Dan Ruan, Yu Shen, Yiping Wu, Yirong Zhou, Chengyan Wang, Boyu Jiang, Ran Tao, Zhigang Wu, Jiazheng Wang, Liuhong Zhu, Yi Guo, Taishan Kang, Jianzhong Lin, Tao Gong, Chen Yang, Guoqiang Fei, Meijin Lin, Di Guo, Jianjun Zhou, Meiyun Wang, Xiaobo Qu
Diffusion magnetic resonance imaging (MRI) is the only imaging modality for non-invasive movement detection of in vivo water molecules, with significant clinical and research applications. Diffusion MRI (DWI) acquired by multi-shot techniques can achieve higher resolution, better signal-to-noise ratio, and lower geometric distortion than single-shot, but suffers from inter-shot motion-induced artifacts. These artifacts cannot be removed prospectively, leading to the absence of artifact-free training labels. Thus, the potential of deep learning in multi-shot DWI reconstruction remains largely untapped. To break the training data bottleneck, here, we propose a Physics-Informed Deep DWI reconstruction method (PIDD) to synthesize high-quality paired training data by leveraging the physical diffusion model (magnitude synthesis) and inter-shot motion-induced phase model (motion phase synthesis). The network is trained only once with 100,000 synthetic samples, achieving encouraging results on multiple realistic in vivo data reconstructions. Advantages over conventional methods include: (a) Better motion artifact suppression and reconstruction stability; (b) Outstanding generalization to multi-scenario reconstructions, including multi-resolution, multi-b-value, multi-undersampling, multi-vendor, and multi-center; (c) Excellent clinical adaptability to patients with verifications by seven experienced doctors (p<0.001). In conclusion, PIDD presents a novel deep learning framework by exploiting the power of MRI physics, providing a cost-effective and explainable way to break the data bottleneck in deep learning medical imaging.
Authors: Oona Rainio, Mohamed M.S. Nasser, Matti Vuorinen, Riku Klén
For augmentation of the square-shaped image data of a convolutional neural network (CNN), we introduce a new method, in which the original images are mapped onto a disk with a conformal mapping, rotated around the center of this disk and mapped under such a M\"obius transformation that preserves the disk, and then mapped back onto their original square shape. This process does not result the loss of information caused by removing areas from near the edges of the original images unlike the typical transformations used in the data augmentation for a CNN. We offer here the formulas of all the mappings needed together with detailed instructions how to write a code for transforming the images. The new method is also tested with simulated data and, according the results, using this method to augment the training data of 10 images into 40 images decreases the amount of the error in the predictions by a CNN for a test set of 160 images in a statistically significant way (p-value=0.0360).
Authors: Daniel Rodriguez-Criado, Pilar Bachiller, George Vogiatzis, Luis J. Manso
Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several challenges. First of all, each person must be uniquely identified in the different views to separate the 2D information provided by the cameras. Secondly, the 3D pose estimation process from the multi-view 2D information of each person must be robust against noise and potential occlusions in the scenario. In this work, we address these two challenges with the help of deep learning. Specifically, we present a model based on Graph Neural Networks capable of predicting the cross-view correspondence of the people in the scenario along with a Multilayer Perceptron that takes the 2D points to yield the 3D poses of each person. These two models are trained in a self-supervised manner, thus avoiding the need for large datasets with 3D annotations.
Authors: Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing
To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes. However, existing cross-modal 3D detectors do not fully utilize the image domain information to address the bottleneck issues of the LiDAR-based detectors. This paper presents a new cross-modal 3D object detector, namely UPIDet, which aims to unleash the potential of the image branch from two aspects. First, UPIDet introduces a new 2D auxiliary task called normalized local coordinate map estimation. This approach enables the learning of local spatial-aware features from the image modality to supplement sparse point clouds. Second, we discover that the representational capability of the point cloud backbone can be enhanced through the gradients backpropagated from the training objectives of the image branch, utilizing a succinct and effective point-to-pixel module. Extensive experiments and ablation studies validate the effectiveness of our method. Notably, we achieved the top rank in the highly competitive cyclist class of the KITTI benchmark at the time of submission. The source code is available at https://github.com/Eaphan/UPIDet.
Authors: David M. Chan, Austin Myers, Sudheendra Vijayanarasimhan, David A. Ross, John Canny
If you ask a human to describe an image, they might do so in a thousand different ways. Traditionally, image captioning models are trained to generate a single "best" (most like a reference) image caption. Unfortunately, doing so encourages captions that are "informationally impoverished," and focus on only a subset of the possible details, while ignoring other potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: "Image Captioning by Committee Consensus" (IC3), designed to generate a single caption that captures high-level details from several annotator viewpoints. Humans rate captions produced by IC3 at least as helpful as baseline SOTA models more than two thirds of the time, and IC3 can improve the performance of SOTA automated recall systems by up to 84%, outperforming single human-generated reference captions, and indicating significant improvements over SOTA approaches for visual description. Code is available at https://davidmchan.github.io/caption-by-committee/
Authors: Yifei Zhou, Juntao Ren, Fengyu Li, Ramin Zabih, Ser-Nam Lim
Advances in the field of vision-language contrastive learning have made it possible for many downstream applications to be carried out efficiently and accurately by simply taking the dot product between image and text representations. One of the most representative approaches proposed recently known as CLIP has garnered widespread adoption due to its effectiveness. CLIP is trained with an InfoNCE loss that takes into account both positive and negative samples to help learn a much more robust representation space. This paper reveals that the common downstream practice of taking a dot product is only a zeroth-order approximation of the optimization goal, resulting in a loss of information during test-time. Intuitively, since the model has been optimized based on the InfoNCE loss, test-time procedures should also be in alignment. The question lies in how one can retrieve any semblance of negative samples information during inference in a computationally efficient way. To this end, we propose Distribution Normalization (DN), where we approximate the mean representation of a batch of test samples and use such a mean to represent what would be analogous to negative samples in the InfoNCE loss. DN requires no retraining or fine-tuning and can be effortlessly applied during inference. Extensive experiments on a wide variety of downstream tasks exhibit a clear advantage of DN over the dot product on top of other existing test-time augmentation methods.
Authors: Aurélien Colin (1, 2), Pierre Tandeo (1, 3), Charles Peureux (2), Romain Husson (2), Ronan Fablet (1, 3) ((1) IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, France, (2) Collecte Localisation Satellites, Brest, France, (3) Odyssey, Inria/IMT, France)
Synthetic Aperture Radar is known to be able to provide high-resolution estimates of surface wind speed. These estimates usually rely on a Geophysical Model Function (GMF) that has difficulties accounting for non-wind processes such as rain events. Convolutional neural network, on the other hand, have the capacity to use contextual information and have demonstrated their ability to delimit rainfall areas. By carefully building a large dataset of SAR observations from the Copernicus Sentinel-1 mission, collocated with both GMF and atmospheric model wind speeds as well as rainfall estimates, we were able to train a wind speed estimator with reduced errors under rain. Collocations with in-situ wind speed measurements from buoys show a root mean square error that is reduced by 27% (resp. 45%) under rainfall estimated at more than 1 mm/h (resp. 3 mm/h). These results demonstrate the capacity of deep learning models to correct rain-related errors in SAR products.
Authors: Yuiko Sakuma, Masato Ishii, Takuya Narihira
We address the challenge of training a large supernet for the object detection task, using a relatively small amount of training data. Specifically, we propose an efficient supernet-based neural architecture search (NAS) method that uses search space pruning. The search space defined by the supernet is pruned by removing candidate models that are predicted to perform poorly. To effectively remove the candidates over a wide range of resource constraints, we particularly design a performance predictor for supernet, called path filter, which is conditioned by resource constraints and can accurately predict the relative performance of the models that satisfy similar resource constraints. Hence, supernet training is more focused on the best-performing candidates. Our path filter handles prediction for paths with different resource budgets. Compared to once-for-all, our proposed method reduces the computational cost of the optimal network architecture by 30% and 63%, while yielding better accuracy-floating point operations Pareto front (0.85 and 0.45 points of improvement on average precision for Pascal VOC and COCO, respectively).
Authors: Zhendong Wang, Yifan Jiang, Huangjie Zheng, Peihao Wang, Pengcheng He, Zhangyang Wang, Weizhu Chen, Mingyuan Zhou
Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users. At the core of our innovations is a new conditional score function at the patch level, where the patch location in the original image is included as additional coordinate channels, while the patch size is randomized and diversified throughout training to encode the cross-region dependency at multiple scales. Sampling with our method is as easy as in the original diffusion model. Through Patch Diffusion, we could achieve $\mathbf{\ge 2\times}$ faster training, while maintaining comparable or better generation quality. Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e.g.$, as few as 5,000 images to train from scratch. We achieve outstanding FID scores in line with state-of-the-art benchmarks: 1.77 on CelebA-64$\times$64, 1.93 on AFHQv2-Wild-64$\times$64, and 2.72 on ImageNet-256$\times$256. We share our code and pre-trained models at https://github.com/Zhendong-Wang/Patch-Diffusion.
Authors: Zhendong Wang, Yifan Jiang, Yadong Lu, Yelong Shen, Pengcheng He, Weizhu Chen, Zhangyang Wang, Mingyuan Zhou
We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly over six different tasks using these prompts. The resulting Prompt Diffusion model is the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation on the trained tasks and generalizes effectively to new, unseen vision tasks with their respective prompts. Our model also shows compelling text-guided image editing results. Our framework aims to facilitate research into in-context learning for computer vision. We share our code and pre-trained models at https://github.com/Zhendong-Wang/Prompt-Diffusion.
Authors: Birger Winkel, David Nakath, Felix Woelk, Kevin Köser
In order to advance underwater computer vision and robotics from lab environments and clear water scenarios to the deep dark ocean or murky coastal waters, representative benchmarks and realistic datasets with ground truth information are required. In particular, determining the camera pose is essential for many underwater robotic or photogrammetric applications and known ground truth is mandatory to evaluate the performance of e.g., simultaneous localization and mapping approaches in such extreme environments. This paper presents the conception, calibration and implementation of an external reference system for determining the underwater camera pose in real-time. The approach, based on an HTC Vive tracking system in air, calculates the underwater camera pose by fusing the poses of two controllers tracked above the water surface of a tank. It is shown that the mean deviation of this approach to an optical marker based reference in air is less than 3 mm and 0.3 deg. Finally, the usability of the system for underwater applications is demonstrated.
Authors: Emanuele Bugliarello, Aida Nematzadeh, Lisa Anne Hendricks
Recent work in vision-and-language pretraining has investigated supervised signals from object detection data to learn better, fine-grained multimodal representations. In this work, we take a step further and explore how we can tap into supervision from small-scale visual relation data. In particular, we propose two pretraining approaches to contextualise visual entities in a multimodal setup. With verbalised scene graphs, we transform visual relation triplets into structured captions, and treat them as additional image descriptions. With masked relation prediction, we further encourage relating entities from image regions with visually masked contexts. When applied to strong baselines pretrained on large amounts of Web data, zero-shot evaluations on both coarse-grained and fine-grained tasks show the efficacy of our methods in learning multimodal representations from weakly-supervised relations data.
Authors: Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Li Tang, Linjun Li, Yongqi Wang, Aoxiong Yin, Ziang Zhang, Zhou Zhao
Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities. However, the reliance on massive high-quality data pairs limits its further development on more modalities. This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR). Specifically, given two existing MCRs pre-trained on (A, B) and (B, C) modality pairs, we project them to a new space and use the data from the overlapping modality B to aligning the two MCRs in the new space. Meanwhile, since the modality pairs (A, B) and (B, C) are already aligned within each MCR, the connection learned by overlapping modality can also be transferred to non-overlapping modality pair (A, C). To unleash the potential of C-MCR, we further introduce a semantic-enhanced inter- and intra-MCR connection method. We first enhance the semantic consistency and completion of embeddings across different modalities for more robust alignment. Then we utilize the inter-MCR alignment to establish the connection, and employ the intra-MCR alignment to better maintain the connection for inputs from non-overlapping modalities. To demonstrate the effectiveness of C-MCR, we connect CLIP and CLAP via texts to derive audio-visual representations, and integrate CLIP and ULIP via images for 3D-language representations. Remarkably, without using any paired data, C-MCR for audio-visual achieves state-of-the-art performance on audio-image retrieval, audio-visual source localization, and counterfactual audio-image recognition tasks. Furthermore, C-MCR for 3D-language also attains advanced zero-shot 3D point cloud classification accuracy on ModelNet40.
Authors: Gengze Zhou, Yicong Hong, Qi Wu
Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, advancing the development of a universal embodied agent. In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). At each step, NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status, and makes the decision to approach the target. Through comprehensive experiments, we demonstrate NavGPT can explicitly perform high-level planning for navigation, including decomposing instruction into sub-goal, integrating commonsense knowledge relevant to navigation task resolution, identifying landmarks from observed scenes, tracking navigation progress, and adapting to exceptions with plan adjustment. Furthermore, we show that LLMs is capable of generating high-quality navigational instructions from observations and actions along a path, as well as drawing accurate top-down metric trajectory given the agent's navigation history. Despite the performance of using NavGPT to zero-shot R2R tasks still falling short of trained models, we suggest adapting multi-modality inputs for LLMs to use as visual navigation agents and applying the explicit reasoning of LLMs to benefit learning-based models.
Authors: Yuexiong Ding, Xiaowei Luo
Accident of struck-by machines is one of the leading causes of casualties on construction sites. Monitoring workers' proximities to avoid human-machine collisions has aroused great concern in construction safety management. Existing methods are either too laborious and costly to apply extensively, or lacking spatial perception for accurate monitoring. Therefore, this study proposes a novel framework for proximity monitoring using only an ordinary 2D camera to realize real-time human-machine collision warning, which is designed to integrate a monocular 3D object detection model to perceive spatial information from 2D images and a post-processing classification module to identify the proximity as four predefined categories: Dangerous, Potentially Dangerous, Concerned, and Safe. A virtual dataset containing 22000 images with 3D annotations is constructed and publicly released to facilitate the system development and evaluation. Experimental results show that the trained 3D object detection model achieves 75% loose AP within 20 meters. Besides, the implemented system is real-time and camera carrier-independent, achieving an F1 of roughly 0.8 within 50 meters under specified settings for machines of different sizes. This study preliminarily reveals the potential and feasibility of proximity monitoring using only a 2D camera, providing a new promising and economical way for early warning of human-machine collisions.
Authors: Ziyi Chang, George Alex Koulieris, Hubert P. H. Shum
Diffusion models are generative models, which gradually add and remove noise to learn the underlying distribution of training data for data generation. The components of diffusion models have gained significant attention with many design choices proposed. Existing reviews have primarily focused on higher-level solutions, thereby covering less on the design fundamentals of components. This study seeks to address this gap by providing a comprehensive and coherent review on component-wise design choices in diffusion models. Specifically, we organize this review according to their three key components, namely the forward process, the reverse process, and the sampling procedure. This allows us to provide a fine-grained perspective of diffusion models, benefiting future studies in the analysis of individual components, the applicability of design choices, and the implementation of diffusion models.
Authors: Ziyan Wang, Hao Wang
Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct. Different from typical variational autoencoders assuming I.I.D. representations (a data point's representation is not directly affected by other data points), our VIR borrows data with similar regression labels to compute the latent representation's variational distribution; furthermore, different from deterministic regression models producing point estimates, VIR predicts the entire normal-inverse-gamma distributions and modulates the associated conjugate distributions to impose probabilistic reweighting on the imbalanced data, thereby providing better uncertainty estimation. Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation. Code will soon be available at https://github.com/Wang-ML-Lab/variational-imbalanced-regression.
Authors: Kailas Vodrahalli, James Zou
As generative AI becomes more prevalent, it is important to study how human users interact with such models. In this work, we investigate how people use text-to-image models to generate desired target images. To study this interaction, we created ArtWhisperer, an online game where users are given a target image and are tasked with iteratively finding a prompt that creates a similar-looking image as the target. Through this game, we recorded over 50,000 human-AI interactions; each interaction corresponds to one text prompt created by a user and the corresponding generated image. The majority of these are repeated interactions where a user iterates to find the best prompt for their target image, making this a unique sequential dataset for studying human-AI collaborations. In an initial analysis of this dataset, we identify several characteristics of prompt interactions and user strategies. People submit diverse prompts and are able to discover a variety of text descriptions that generate similar images. Interestingly, prompt diversity does not decrease as users find better prompts. We further propose a new metric to quantify the steerability of AI using our dataset. We define steerability as the expected number of interactions required to adequately complete a task. We estimate this value by fitting a Markov chain for each target task and calculating the expected time to reach an adequate score in the Markov chain. We quantify and compare AI steerability across different types of target images and two different models, finding that images of cities and natural world images are more steerable than artistic and fantasy images. These findings provide insights into human-AI interaction behavior, present a concrete method of assessing AI steerability, and demonstrate the general utility of the ArtWhisperer dataset.
Authors: Rui Wang, Peipei Li, Huaibo Huang, Chunshui Cao, Ran He, Zhaofeng He
We present a novel language-driven ordering alignment method for ordinal classification. The labels in ordinal classification contain additional ordering relations, making them prone to overfitting when relying solely on training data. Recent developments in pre-trained vision-language models inspire us to leverage the rich ordinal priors in human language by converting the original task into a vision-language alignment task. Consequently, we propose L2RCLIP, which fully utilizes the language priors from two perspectives. First, we introduce a complementary prompt tuning technique called RankFormer, designed to enhance the ordering relation of original rank prompts. It employs token-level attention with residual-style prompt blending in the word embedding space. Second, to further incorporate language priors, we revisit the approximate bound optimization of vanilla cross-entropy loss and restructure it within the cross-modal embedding space. Consequently, we propose a cross-modal ordinal pairwise loss to refine the CLIP feature space, where texts and images maintain both semantic alignment and ordering alignment. Extensive experiments on three ordinal classification tasks, including facial age estimation, historical color image (HCI) classification, and aesthetic assessment demonstrate its promising performance.
Authors: Gregory Sech, Paolo Soleni, Wouter B. Verschoof-van der Vaart, Žiga Kokalj, Arianna Traviglia, Marco Fiorucci
When applying deep learning to remote sensing data in archaeological research, a notable obstacle is the limited availability of suitable datasets for training models. The application of transfer learning is frequently employed to mitigate this drawback. However, there is still a need to explore its effectiveness when applied across different archaeological datasets. This paper compares the performance of various transfer learning configurations using two semantic segmentation deep neural networks on two LiDAR datasets. The experimental results indicate that transfer learning-based approaches in archaeology can lead to performance improvements, although a systematic enhancement has not yet been observed. We provide specific insights about the validity of such techniques that can serve as a baseline for future works.
Authors: Yaozu Ye, Hao Shi, Kailun Yang, Ze Wang, Xiaoting Yin, Yining Lin, Mao Liu, Yaonan Wang, Kaiwei Wang
Optical flow estimation is a fundamental task in the field of autonomous driving. Event cameras are capable of responding to log-brightness changes in microseconds. Its characteristic of producing responses only to the changing region is particularly suitable for optical flow estimation. In contrast to the super low-latency response speed of event cameras, existing datasets collected via event cameras, however, only provide limited frame rate optical flow ground truth, (e.g., at 10Hz), greatly restricting the potential of event-driven optical flow. To address this challenge, we put forward a high-frame-rate, low-latency event representation Unified Voxel Grid, sequentially fed into the network bin by bin. We then propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. The key component of our EVA-Flow is the stacked Spatiotemporal Motion Refinement (SMR) module, which predicts temporally dense optical flow and enhances the accuracy via spatial-temporal motion refinement. The time-dense feature warping utilized in the SMR module provides implicit supervision for the intermediate optical flow. Additionally, we introduce the Rectified Flow Warp Loss (RFWL) for the unsupervised evaluation of intermediate optical flow in the absence of ground truth. This is, to the best of our knowledge, the first work focusing on anytime optical flow estimation via event cameras. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), fastest inference (9.2ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.
Authors: Yiming Quan, Shian Chen
This study presents a generalised least squares based method for fitting polygons and ellipses to data points. The method is based on a trigonometric fitness function that approximates a unit shape accurately, making it applicable to various geometric shapes with minimal fitting parameters. Furthermore, the proposed method does not require any constraints and can handle incomplete data. The method is validated on synthetic and real-world data sets and compared with the existing methods in the literature for polygon and ellipse fitting. The test results show that the method achieves high accuracy and outperforms the referenced methods in terms of root-mean-square error, especially for noise-free data. The proposed method is a powerful tool for shape fitting in computer vision and geometry processing applications.
Authors: Zhaoyi Sun, Mingquan Lin, Qingqing Zhu, Qianqian Xie, Fei Wang, Zhiyong Lu, Yifan Peng
Computer-assisted diagnostic and prognostic systems of the future should be capable of simultaneously processing multimodal data. Multimodal deep learning (MDL), which involves the integration of multiple sources of data, such as images and text, has the potential to revolutionize the analysis and interpretation of biomedical data. However, it only caught researchers' attention recently. To this end, there is a critical need to conduct a systematic review on this topic, identify the limitations of current work, and explore future directions. In this scoping review, we aim to provide a comprehensive overview of the current state of the field and identify key concepts, types of studies, and research gaps with a focus on biomedical images and texts joint learning, mainly because these two were the most commonly available data types in MDL research. This study reviewed the current uses of multimodal deep learning on five tasks: (1) Report generation, (2) Visual question answering, (3) Cross-modal retrieval, (4) Computer-aided diagnosis, and (5) Semantic segmentation. Our results highlight the diverse applications and potential of MDL and suggest directions for future research in the field. We hope our review will facilitate the collaboration of natural language processing (NLP) and medical imaging communities and support the next generation of decision-making and computer-assisted diagnostic system development.
Authors: Sunder Ali Khowaja, Lewis Nkenyereye, Jiseok Yoon, Ik Hyun Lee, Kapal Dev
Facial style transfer has been quite popular among researchers due to the rise of emerging technologies such as eXtended Reality (XR), Metaverse, and Non-Fungible Tokens (NFTs). Furthermore, StyleGAN methods along with transfer-learning strategies have reduced the problem of limited data to some extent. However, most of the StyleGAN methods overfit the styles while adding artifacts to facial images. In this paper, we propose a facial pose awareness and style transfer (Face-PAST) network that preserves facial details and structures while generating high-quality stylized images. Dual StyleGAN inspires our work, but in contrast, our work uses a pre-trained style generation network in an external style pass with a residual modulation block instead of a transform coding block. Furthermore, we use the gated mapping unit and facial structure, identity, and segmentation losses to preserve the facial structure and details. This enables us to train the network with a very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient and flexible style mixing in the generative space. We perform extensive experiments to show the superiority of Face-PAST in comparison to existing state-of-the-art methods.
Authors: Sarah Ibrahimi, Xiaohang Sun, Pichao Wang, Amanmeet Garg, Ashutosh Sanan, Mohamed Omar
Text-to-video retrieval systems have recently made significant progress by utilizing pre-trained models trained on large-scale image-text pairs. However, most of the latest methods primarily focus on the video modality while disregarding the audio signal for this task. Nevertheless, a recent advancement by ECLIPSE has improved long-range text-to-video retrieval by developing an audiovisual video representation. Nonetheless, the objective of the text-to-video retrieval task is to capture the complementary audio and video information that is pertinent to the text query rather than simply achieving better audio and video alignment. To address this issue, we introduce TEFAL, a TExt-conditioned Feature ALignment method that produces both audio and video representations conditioned on the text query. Instead of using only an audiovisual attention block, which could suppress the audio information relevant to the text query, our approach employs two independent cross-modal attention blocks that enable the text to attend to the audio and video representations separately. Our proposed method's efficacy is demonstrated on four benchmark datasets that include audio: MSR-VTT, LSMDC, VATEX, and Charades, and achieves better than state-of-the-art performance consistently across the four datasets. This is attributed to the additional text-query-conditioned audio representation and the complementary information it adds to the text-query-conditioned video representation.
Authors: Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie
In this study, we aim to initiate the development of Radiology Foundation Model, termed as RadFM.We consider the construction of foundational models from the perspectives of dataset construction, model design, and thorough evaluation. Our contribution can be concluded as follows: (i), we construct a large-scale Medical Multi-modal Dataset, MedMD, which consists of 16M 2D and 3D medical scans with high-quality text descriptions or reports across various data formats, modalities, and tasks, covering over 5000 distinct diseases. To the best of our knowledge, this is the first large-scale, high-quality, medical visual-language dataset, with both 2D and 3D scans; (ii ), we propose an architecture that enables visually conditioned generative pre-training, i.e., allowing for integration of text input with 2D or 3D medical scans, and generate responses for diverse radiologic tasks. The model was initially pre-trained on MedMD and subsequently fine-tuned on the domain-specific dataset, which is a radiologic cleaned version of MedMD, containing 3M radiologic visual-language pairs, termed as RadMD; (iii), we propose a new evaluation benchmark, RadBench, that comprises five tasks, including modality recognition, disease diagnosis, visual question answering, report generation and rationale diagnosis, aiming to comprehensively assess the capability of foundation models in handling practical clinical problems. We conduct both automatic and human evaluation on RadBench, in both cases, RadFM significantly outperforms existing multi-modal foundation models. The codes, data, and model checkpoint will all be made publicly available to promote further research and development in the field.
Authors: Jiawen Zhu, Huayi Tang, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Shihao Qiu, Shengming Li, Huchuan Lu
Existing nighttime unmanned aerial vehicle (UAV) trackers follow an "Enhance-then-Track" architecture - first using a light enhancer to brighten the nighttime video, then employing a daytime tracker to locate the object. This separate enhancement and tracking fails to build an end-to-end trainable vision system. To address this, we propose a novel architecture called Darkness Clue-Prompted Tracking (DCPT) that achieves robust UAV tracking at night by efficiently learning to generate darkness clue prompts. Without a separate enhancer, DCPT directly encodes anti-dark capabilities into prompts using a darkness clue prompter (DCP). Specifically, DCP iteratively learns emphasizing and undermining projections for darkness clues. It then injects these learned visual prompts into a daytime tracker with fixed parameters across transformer layers. Moreover, a gated feature aggregation mechanism enables adaptive fusion between prompts and between prompts and the base model. Extensive experiments show state-of-the-art performance for DCPT on multiple dark scenario benchmarks. The unified end-to-end learning of enhancement and tracking in DCPT enables a more trainable system. The darkness clue prompting efficiently injects anti-dark knowledge without extra modules. Code is available at https://github.com/bearyi26/DCPT.
Authors: Nana Yu, Hong Shi, Yahong Han
Low-light image enhancement tasks demand an appropriate balance among brightness, color, and illumination. While existing methods often focus on one aspect of the image without considering how to pay attention to this balance, which will cause problems of color distortion and overexposure etc. This seriously affects both human visual perception and the performance of high-level visual models. In this work, a novel synergistic structure is proposed which can balance brightness, color, and illumination more effectively. Specifically, the proposed method, so-called Joint Correcting and Refinement Network (JCRNet), which mainly consists of three stages to balance brightness, color, and illumination of enhancement. Stage 1: we utilize a basic encoder-decoder and local supervision mechanism to extract local information and more comprehensive details for enhancement. Stage 2: cross-stage feature transmission and spatial feature transformation further facilitate color correction and feature refinement. Stage 3: we employ a dynamic illumination adjustment approach to embed residuals between predicted and ground truth images into the model, adaptively adjusting illumination balance. Extensive experiments demonstrate that the proposed method exhibits comprehensive performance advantages over 21 state-of-the-art methods on 9 benchmark datasets. Furthermore, a more persuasive experiment has been conducted to validate our approach the effectiveness in downstream visual tasks (e.g., saliency detection). Compared to several enhancement models, the proposed method effectively improves the segmentation results and quantitative metrics of saliency detection. The source code will be available at https://github.com/woshiyll/JCRNet.
Authors: Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, Qiang Xu
Text-guided diffusion models have revolutionized image generation and editing, offering exceptional realism and diversity. Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt, the process commences by acquiring a noisy latent vector corresponding to the source image via the diffusion model. This vector is subsequently fed into separate source and target diffusion branches for editing. The accuracy of this inversion process significantly impacts the final editing outcome, influencing both essential content preservation of the source image and edit fidelity according to the target prompt. Prior inversion techniques aimed at finding a unified solution in both the source and target diffusion branches. However, our theoretical and empirical analyses reveal that disentangling these branches leads to a distinct separation of responsibilities for preserving essential content and ensuring edit fidelity. Building on this insight, we introduce "Direct Inversion," a novel technique achieving optimal performance of both branches with just three lines of code. To assess image editing performance, we present PIE-Bench, an editing benchmark with 700 images showcasing diverse scenes and editing types, accompanied by versatile annotations and comprehensive evaluation metrics. Compared to state-of-the-art optimization-based inversion techniques, our solution not only yields superior performance across 8 editing methods but also achieves nearly an order of speed-up.
Authors: Zhangsihao Yang, Mengwei Ren, Kaize Ding, Guido Gerig, Yalin Wang
Pretraining CNN models (i.e., UNet) through self-supervision has become a powerful approach to facilitate medical image segmentation under low annotation regimes. Recent contrastive learning methods encourage similar global representations when the same image undergoes different transformations, or enforce invariance across different image/patch features that are intrinsically correlated. However, CNN-extracted global and local features are limited in capturing long-range spatial dependencies that are essential in biological anatomy. To this end, we present a keypoint-augmented fusion layer that extracts representations preserving both short- and long-range self-attention. In particular, we augment the CNN feature map at multiple scales by incorporating an additional input that learns long-range spatial self-attention among localized keypoint features. Further, we introduce both global and local self-supervised pretraining for the framework. At the global scale, we obtain global representations from both the bottleneck of the UNet, and by aggregating multiscale keypoint features. These global features are subsequently regularized through image-level contrastive objectives. At the local scale, we define a distance-based criterion to first establish correspondences among keypoints and encourage similarity between their features. Through extensive experiments on both MRI and CT segmentation tasks, we demonstrate the architectural advantages of our proposed method in comparison to both CNN and Transformer-based UNets, when all architectures are trained with randomly initialized weights. With our proposed pretraining strategy, our method further outperforms existing SSL methods by producing more robust self-attention and achieving state-of-the-art segmentation results. The code is available at https://github.com/zshyang/kaf.git.
Authors: Batu Ozturkler, Chao Liu, Benjamin Eckart, Morteza Mardani, Jiaming Song, Jan Kautz
Diffusion models have recently gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time, and they have been shown to be more robust than unrolled methods under distribution shifts. However, diffusion models require careful tuning of inference hyperparameters on a validation set and are still sensitive to distribution shifts during testing. To address these challenges, we introduce SURE-based MRI Reconstruction with Diffusion models (SMRD), a method that performs test-time hyperparameter tuning to enhance robustness during testing. SMRD uses Stein's Unbiased Risk Estimator (SURE) to estimate the mean squared error of the reconstruction during testing. SURE is then used to automatically tune the inference hyperparameters and to set an early stopping criterion without the need for validation tuning. To the best of our knowledge, SMRD is the first to incorporate SURE into the sampling stage of diffusion models for automatic hyperparameter selection. SMRD outperforms diffusion model baselines on various measurement noise levels, acceleration factors, and anatomies, achieving a PSNR improvement of up to 6 dB under measurement noise. The code is publicly available at https://github.com/NVlabs/SMRD .
Authors: Yanwu Xu, Li Sun, Wei Peng, Shyam Visweswaran, Kayhan Batmanghelich
This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. The results of comparative assessments indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines, airways, and vascular structures. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.
Authors: Jiawei Yao, Chen Wang, Tong Wu, Chuming Li
In this paper, we propose a novel method for 3D scene and object reconstruction from sparse multi-view images. Different from previous methods that leverage extra information such as depth or generalizable features across scenes, our approach leverages the scene properties embedded in the multi-view inputs to create precise pseudo-labels for optimization without any prior training. Specifically, we introduce a geometry-guided approach that improves surface reconstruction accuracy from sparse views by leveraging spherical harmonics to predict the novel radiance while holistically considering all color observations for a point in the scene. Also, our pipeline exploits proxy geometry and correctly handles the occlusion in generating the pseudo-labels of radiance, which previous image-warping methods fail to avoid. Our method, dubbed Ray Augmentation (RayAug), achieves superior results on DTU and Blender datasets without requiring prior training, demonstrating its effectiveness in addressing the problem of sparse view reconstruction. Our pipeline is flexible and can be integrated into other implicit neural reconstruction methods for sparse views.
Authors: Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Aydin Sarraf, Eric Granger
Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However, these maps remain class-agnostic since the model is unsupervised. They often tend to decompose the image into multiple maps containing different objects while being unable to distinguish the object of interest from background noise objects. In this paper, Discriminative Pseudo-label Sampling (DiPS) is introduced to leverage these class-agnostic maps for weakly-supervised object localization (WSOL), where only image-class labels are available. Given multiple attention maps, DiPS relies on a pre-trained classifier to identify the most discriminative regions of each attention map. This ensures that the selected ROIs cover the correct image object while discarding the background ones, and, as such, provides a rich pool of diverse and discriminative proposals to cover different parts of the object. Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks. Unlike standard WSOL methods, DiPS optimizes performance in both tasks by using a transformer encoder and a dedicated output head for each task, each trained using dedicated loss functions. To avoid overfitting a single proposal and promote better object coverage, a single proposal is randomly selected among the top ones for a training image at each training step. Experimental results on the challenging CUB, ILSVRC, OpenImages, and TelDrone datasets indicate that our architecture, in combination with our transformer-based proposals, can yield better localization performance than state-of-the-art methods.
Authors: Yifan Pu, Weicong Liang, Yiduo Hao, Yuhui Yuan, Yukang Yang, Chao Zhang, Han Hu, Gao Huang
Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given input image. A highly performant object detector requires accurate ranking for the bounding box predictions. For DETR-based detectors, the top-ranked bounding boxes suffer from less accurate localization quality due to the misalignment between classification scores and localization accuracy, thus impeding the construction of high-quality detectors. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs, combinedly called Rank-DETR. Our key contributions include: (i) a rank-oriented architecture design that can prompt positive predictions and suppress the negative ones to ensure lower false positive rates, as well as (ii) a rank-oriented loss function and matching cost design that prioritizes predictions of more accurate localization accuracy during ranking to boost the AP under high IoU thresholds. We apply our method to improve the recent SOTA methods (e.g., H-DETR and DINO-DETR) and report strong COCO object detection results when using different backbones such as ResNet-$50$, Swin-T, and Swin-L, demonstrating the effectiveness of our approach. Code is available at \url{https://github.com/LeapLabTHU/Rank-DETR}.
Authors: Kibum Kim, Kanghoon Yoon, Jaehyeong Jeon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard, studies on WSSGG have utilized image captions to obtain unlocalized triplets while primarily focusing on grounding the unlocalized triplets over image regions. However, they have overlooked the two issues involved in the triplet formation process from the captions: 1) Semantic over-simplification issue arises when extracting triplets from captions, where fine-grained predicates in captions are undesirably converted into coarse-grained predicates, resulting in a long-tailed predicate distribution, and 2) Low-density scene graph issue arises when aligning the triplets in the caption with entity/predicate classes of interest, where many triplets are discarded and not used in training, leading to insufficient supervision. To tackle the two issues, we propose a new approach, i.e., Large Language Model for weakly-supervised SGG (LLM4SGG), where we mitigate the two issues by leveraging the LLM's in-depth understanding of language and reasoning ability during the extraction of triplets from captions and alignment of entity/predicate classes with target data. To further engage the LLM in these processes, we adopt the idea of Chain-of-Thought and the in-context few-shot learning strategy. To validate the effectiveness of LLM4SGG, we conduct extensive experiments on Visual Genome and GQA datasets, showing significant improvements in both Recall@K and mean Recall@K compared to the state-of-the-art WSSGG methods. A further appeal is that LLM4SGG is data-efficient, enabling effective model training with a small amount of training images.
Authors: Yu Gu, Jianwei Yang, Naoto Usuyama, Chunyuan Li, Sheng Zhang, Matthew P. Lungren, Jianfeng Gao, Hoifung Poon
Rapid progress has been made in instruction-learning for image editing with natural-language instruction, as exemplified by InstructPix2Pix. In biomedicine, such methods can be applied to counterfactual image generation, which helps differentiate causal structure from spurious correlation and facilitate robust image interpretation for disease progression modeling. However, generic image-editing models are ill-suited for the biomedical domain, and counterfactual biomedical image generation is largely underexplored. In this paper, we present BiomedJourney, a novel method for counterfactual biomedical image generation by instruction-learning from multimodal patient journeys. Given a patient with two biomedical images taken at different time points, we use GPT-4 to process the corresponding imaging reports and generate a natural language description of disease progression. The resulting triples (prior image, progression description, new image) are then used to train a latent diffusion model for counterfactual biomedical image generation. Given the relative scarcity of image time series data, we introduce a two-stage curriculum that first pretrains the denoising network using the much more abundant single image-report pairs (with dummy prior image), and then continues training using the counterfactual triples. Experiments using the standard MIMIC-CXR dataset demonstrate the promise of our method. In a comprehensive battery of tests on counterfactual medical image generation, BiomedJourney substantially outperforms prior state-of-the-art methods in instruction image editing and medical image generation such as InstructPix2Pix and RoentGen. To facilitate future study in counterfactual medical generation, we plan to release our instruction-learning code and pretrained models.
The registration of pathological images plays an important role in medical applications. Despite its significance, most researchers in this field primarily focus on the registration of normal tissue into normal tissue. The negative impact of focal tissue, such as the loss of spatial correspondence information and the abnormal distortion of tissue, are rarely considered. In this paper, we propose GIRNet, a novel unsupervised approach for pathological image registration by incorporating segmentation and inpainting through the principles of Generation, Inpainting, and Registration (GIR). The registration, segmentation, and inpainting modules are trained simultaneously in a co-learning manner so that the segmentation of the focal area and the registration of inpainted pairs can improve collaboratively. Overall, the registration of pathological images is achieved in a completely unsupervised learning framework. Experimental results on multiple datasets, including Magnetic Resonance Imaging (MRI) of T1 sequences, demonstrate the efficacy of our proposed method. Our results show that our method can accurately achieve the registration of pathological images and identify lesions even in challenging imaging modalities. Our unsupervised approach offers a promising solution for the efficient and cost-effective registration of pathological images. Our code is available at https://github.com/brain-intelligence-lab/GIRNet.
Authors: Jun Wu, Sicheng Li, Sihui Ji, Yue Wang, Rong Xiong, Yiyi Liao
Decomposing a target object from a complex background while reconstructing is challenging. Most approaches acquire the perception for object instances through the use of manual labels, but the annotation procedure is costly. The recent advancements in 2D self-supervised learning have brought new prospects to object-aware representation, yet it remains unclear how to leverage such noisy 2D features for clean decomposition. In this paper, we propose a Decomposed Object Reconstruction (DORec) network based on neural implicit representations. Our key idea is to transfer 2D self-supervised features into masks of two levels of granularity to supervise the decomposition, including a binary mask to indicate the foreground regions and a K-cluster mask to indicate the semantically similar regions. These two masks are complementary to each other and lead to robust decomposition. Experimental results show the superiority of DORec in segmenting and reconstructing the foreground object on various datasets.
Authors: Jun Xia, Zhihao Yue, Yingbo Zhou, Zhiwei Ling, Xian Wei, Mingsong Chen
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor attacks are effective in various real scenarios, they still suffer from the problems of both low fidelity of poisoned samples and non-negligible transfer in latent space, which make them easily detectable by existing backdoor detection algorithms. To overcome the weakness, this paper proposes a novel frequency-based backdoor attack method named WaveAttack, which obtains image high-frequency features through Discrete Wavelet Transform (DWT) to generate backdoor triggers. Furthermore, we introduce an asymmetric frequency obfuscation method, which can add an adaptive residual in the training and inference stage to improve the impact of triggers and further enhance the effectiveness of WaveAttack. Comprehensive experimental results show that WaveAttack not only achieves higher stealthiness and effectiveness, but also outperforms state-of-the-art (SOTA) backdoor attack methods in the fidelity of images by up to 28.27\% improvement in PSNR, 1.61\% improvement in SSIM, and 70.59\% reduction in IS.
Authors: Sandipan Choudhuri, Arunabha Sen
Unwanted samples from private source categories in the learning objective of a partial domain adaptation setup can lead to negative transfer and reduce classification performance. Existing methods, such as re-weighting or aggregating target predictions, are vulnerable to this issue, especially during initial training stages, and do not adequately address class-level feature alignment. Our proposed approach seeks to overcome these limitations by delving deeper than just the first-order moments to derive distinct and compact categorical distributions. We employ objectives that optimize the intra and inter-class distributions in a domain-invariant fashion and design a robust pseudo-labeling for efficient target supervision. Our approach incorporates a complement entropy objective module to reduce classification uncertainty and flatten incorrect category predictions. The experimental findings and ablation analysis of the proposed modules demonstrate the superior performance of our proposed model compared to benchmarks.
Authors: Jiyuan Shen, Wenzhuo Yang, Kwok-Yan Lam
Training a large and state-of-the-art machine learning model typically necessitates the use of large-scale datasets, which, in turn, makes the training and parameter-tuning process expensive and time-consuming. Some researchers opt to distil information from real-world datasets into tiny and compact synthetic datasets while maintaining their ability to train a well-performing model, hence proposing a data-efficient method known as Dataset Distillation (DD). Despite recent progress in this field, existing methods still underperform and cannot effectively replace large datasets. In this paper, unlike previous methods that focus solely on improving the efficacy of student distillation, we are the first to recognize the important interplay between expert and student. We argue the significant impact of expert smoothness when employing more potent expert trajectories in subsequent dataset distillation. Based on this, we introduce the integration of clipping loss and gradient penalty to regulate the rate of parameter changes in expert trajectories. Furthermore, in response to the sensitivity exhibited towards randomly initialized variables during distillation, we propose representative initialization for synthetic dataset and balanced inner-loop loss. Finally, we present two enhancement strategies, namely intermediate matching loss and weight perturbation, to mitigate the potential occurrence of cumulative errors. We conduct extensive experiments on datasets of different scales, sizes, and resolutions. The results demonstrate that the proposed method significantly outperforms prior methods.