Authors: Kun Tong, Chengze Jiang, Jie Gui, Yuan Cao
Abstract: Adversarial training (AT) is an effective defense method against gradient-based attacks to enhance the robustness of neural networks. Among them, single-step AT has emerged as a hotspot topic due to its simplicity and efficiency, requiring only one gradient propagation in generating adversarial examples. Nonetheless, the problem of catastrophic overfitting (CO) that causes training collapse remains poorly understood, and there exists a gap between the robust accuracy achieved through single- and multi-step AT. In this paper, we present a surprising finding that the taxonomy of adversarial examples reveals the truth of CO. Based on this conclusion, we propose taxonomy driven fast adversarial training (TDAT) which jointly optimizes learning objective, loss function, and initialization method, thereby can be regarded as a new paradigm of single-step AT. Compared with other fast AT methods, TDAT can boost the robustness of neural networks, alleviate the influence of misclassified examples, and prevent CO during the training process while requiring almost no additional computational and memory resources. Our method achieves robust accuracy improvement of $1.59\%$, $1.62\%$, $0.71\%$, and $1.26\%$ on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet-100 datasets, when against projected gradient descent PGD10 attack with perturbation budget 8/255. Furthermore, our proposed method also achieves state-of-the-art robust accuracy against other attacks. Code is available at https://github.com/bookman233/TDAT.
Authors: Bilel Guetarni, Feryal Windal, Halim Benhabiles, Mahfoud Chaibi, Romain Dubois, Emmanuelle Leteurtre, Dominique Collard
Abstract: Predicting the response of a patient to a cancer treatment is of high interest. Nonetheless, this task is still challenging from a medical point of view due to the complexity of the interaction between the patient organism and the considered treatment. Recent works on foundation models pre-trained with self-supervised learning on large-scale unlabeled histopathology datasets have opened a new direction towards the development of new methods for cancer diagnosis related tasks. In this article, we propose a novel methodology for predicting Diffuse Large B-Cell Lymphoma patients treatment response from Whole Slide Images. Our method exploits several foundation models as feature extractors to obtain a local representation of the image corresponding to a small region of the tissue, then, a global representation of the image is obtained by aggregating these local representations using attention-based Multiple Instance Learning. Our experimental study conducted on a dataset of 152 patients, shows the promising results of our methodology, notably by highlighting the advantage of using foundation models compared to conventional ImageNet pre-training. Moreover, the obtained results clearly demonstrates the potential of foundation models for characterizing histopathology images and generating more suited semantic representation for this task.
Authors: Brendan Reidy, Sepehr Tabrizchi, Mohamadreza Mohammadi, Shaahin Angizi, Arman Roohi, Ramtin Zand
Abstract: With the rise of tiny IoT devices powered by machine learning (ML), many researchers have directed their focus toward compressing models to fit on tiny edge devices. Recent works have achieved remarkable success in compressing ML models for object detection and image classification on microcontrollers with small memory, e.g., 512kB SRAM. However, there remain many challenges prohibiting the deployment of ML systems that require high-resolution images. Due to fundamental limits in memory capacity for tiny IoT devices, it may be physically impossible to store large images without external hardware. To this end, we propose a high-resolution image scaling system for edge ML, called HiRISE, which is equipped with selective region-of-interest (ROI) capability leveraging analog in-sensor image scaling. Our methodology not only significantly reduces the peak memory requirements, but also achieves up to 17.7x reduction in data transfer and energy consumption.
Authors: Zhuofan Zhang, Ziyu Zhu, Pengxiang Li, Tengyu Liu, Xiaojian Ma, Yixin Chen, Baoxiong Jia, Siyuan Huang, Qing Li
Abstract: Grounding natural language in physical 3D environments is essential for the advancement of embodied artificial intelligence. Current datasets and models for 3D visual grounding predominantly focus on identifying and localizing objects from static, object-centric descriptions. These approaches do not adequately address the dynamic and sequential nature of task-oriented grounding necessary for practical applications. In this work, we propose a new task: Task-oriented Sequential Grounding in 3D scenes, wherein an agent must follow detailed step-by-step instructions to complete daily activities by locating a sequence of target objects in indoor scenes. To facilitate this task, we introduce SG3D, a large-scale dataset containing 22,346 tasks with 112,236 steps across 4,895 real-world 3D scenes. The dataset is constructed using a combination of RGB-D scans from various 3D scene datasets and an automated task generation pipeline, followed by human verification for quality assurance. We adapted three state-of-the-art 3D visual grounding models to the sequential grounding task and evaluated their performance on SG3D. Our results reveal that while these models perform well on traditional benchmarks, they face significant challenges with task-oriented sequential grounding, underscoring the need for further research in this area.
Authors: Florian Gr\"otschla, Luca A. Lanzend\"orfer, Marco Calzavara, Roger Wattenhofer
Abstract: Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural considerations. Therefore, understanding the composition and distribution of these datasets has become increasingly crucial. To address the need for intuitive exploration of these datasets, we propose AEye, an extensible and scalable visualization tool tailored to image datasets. AEye utilizes a contrastively trained model to embed images into semantically meaningful high-dimensional representations, facilitating data clustering and organization. To visualize the high-dimensional representations, we project them onto a two-dimensional plane and arrange images in layers so users can seamlessly navigate and explore them interactively. AEye facilitates semantic search functionalities for both text and image queries, enabling users to search for content. We open-source the codebase for AEye, and provide a simple configuration to add datasets.
Authors: Guru Swaroop Bennabhaktula, Enrique Alegre, Nicola Strisciuglio, George Azzopardi
Abstract: We introduce a novel computational unit, termed PushPull-Conv, in the first layer of a ResNet architecture, inspired by the anti-phase inhibition phenomenon observed in the primary visual cortex. This unit redefines the traditional convolutional layer by implementing a pair of complementary filters: a trainable push kernel and its counterpart, the pull kernel. The push kernel (analogous to traditional convolution) learns to respond to specific stimuli, while the pull kernel reacts to the same stimuli but of opposite contrast. This configuration enhances stimulus selectivity and effectively inhibits response in regions lacking preferred stimuli. This effect is attributed to the push and pull kernels, which produce responses of comparable magnitude in such regions, thereby neutralizing each other. The incorporation of the PushPull-Conv into ResNets significantly increases their robustness to image corruption. Our experiments with benchmark corruption datasets show that the PushPull-Conv can be combined with other data augmentation techniques to further improve model robustness. We set a new robustness benchmark on ResNet50 achieving an $mCE$ of 49.95$\%$ on ImageNet-C when combining PRIME augmentation with PushPull inhibition.
Authors: William Y. Zhu, Keren Ye, Junjie Ke, Jiahui Yu, Leonidas Guibas, Peyman Milanfar, Feng Yang
Abstract: Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition, zero-shot visual attribute recognition remains a challenge because CLIP's contrastively-learned vision-language representation cannot effectively capture object-attribute dependencies. In this paper, we target this weakness and propose a sentence generation-based retrieval formulation for attribute recognition that is novel in 1) explicitly modeling a to-be-measured and retrieved object-attribute relation as a conditional probability graph, which converts the recognition problem into a dependency-sensitive language-modeling problem, and 2) applying a large pretrained Vision-Language Model (VLM) on this reformulation and naturally distilling its knowledge of image-object-attribute relations to use towards attribute recognition. Specifically, for each attribute to be recognized on an image, we measure the visual-conditioned probability of generating a short sentence encoding the attribute's relation to objects on the image. Unlike contrastive retrieval, which measures likelihood by globally aligning elements of the sentence to the image, generative retrieval is sensitive to the order and dependency of objects and attributes in the sentence. We demonstrate through experiments that generative retrieval consistently outperforms contrastive retrieval on two visual reasoning datasets, Visual Attribute in the Wild (VAW), and our newly-proposed Visual Genome Attribute Ranking (VGARank).
Authors: Olga Gasparyan, Elena Sirotkina
Abstract: How can we define visual sentiment when viewers systematically disagree on their perspectives? This study introduces a novel approach to visual sentiment analysis by integrating attitudinal differences into visual sentiment classification. Recognizing that societal divides, such as partisan differences, heavily influence sentiment labeling, we developed a dataset that reflects these divides. We then trained a deep learning multi-task multi-class model to predict visual sentiment from different ideological viewpoints. Applied to immigration-related images, our approach captures perspectives from both Democrats and Republicans. By incorporating diverse perspectives into the labeling and model training process, our strategy addresses the limitation of label ambiguity and demonstrates improved accuracy in visual sentiment predictions. Overall, our study advocates for a paradigm shift in decoding visual sentiment toward creating classifiers that more accurately reflect the sentiments generated by humans.
Authors: Blessing Agyei Kyem, Eugene Kofi Okrah Denteh, Joshua Kofi Asamoah, Armstrong Aboah
Abstract: This research introduces the first multimodal approach for pavement condition assessment, providing both quantitative Pavement Condition Index (PCI) predictions and qualitative descriptions. We introduce PaveCap, a novel framework for automated pavement condition assessment. The framework consists of two main parts: a Single-Shot PCI Estimation Network and a Dense Captioning Network. The PCI Estimation Network uses YOLOv8 for object detection, the Segment Anything Model (SAM) for zero-shot segmentation, and a four-layer convolutional neural network to predict PCI. The Dense Captioning Network uses a YOLOv8 backbone, a Transformer encoder-decoder architecture, and a convolutional feed-forward module to generate detailed descriptions of pavement conditions. To train and evaluate these networks, we developed a pavement dataset with bounding box annotations, textual annotations, and PCI values. The results of our PCI Estimation Network showed a strong positive correlation (0.70) between predicted and actual PCIs, demonstrating its effectiveness in automating condition assessment. Also, the Dense Captioning Network produced accurate pavement condition descriptions, evidenced by high BLEU (0.7445), GLEU (0.5893), and METEOR (0.7252) scores. Additionally, the dense captioning model handled complex scenarios well, even correcting some errors in the ground truth data. The framework developed here can greatly improve infrastructure management and decision18 making in pavement maintenance.
Authors: Yi Liu, Chenhao Sun, Hao Ye, Xiangying Liu, Weilong Ju
Abstract: Remote sensing image change detection (CD) is essential for analyzing land surface changes over time, with a significant challenge being the differentiation of actual changes from complex scenes while filtering out pseudo-changes. A primary contributor to this challenge is the intra-class dynamic changes due to phenological characteristics in natural areas. To overcome this, we introduce the InPhea model, which integrates phenological features into a remote sensing image CD framework. The model features a detector with a differential attention module for improved feature representation of change information, coupled with high-resolution feature extraction and spatial pyramid blocks to enhance performance. Additionally, a constrainer with four constraint modules and a multi-stage contrastive learning approach is employed to aid in the model's understanding of phenological characteristics. Experiments on the HRSCD, SECD, and PSCD-Wuhan datasets reveal that InPhea outperforms other models, confirming its effectiveness in addressing phenological pseudo-changes and its overall model superiority.
Authors: Yifan Chen, Xiaozhen Qiao, Zhe Sun, Xuelong Li
Abstract: Contrastive Language-Image Pre-training (CLIP) excels in integrating semantic information between images and text through contrastive learning techniques. It has achieved remarkable performance in various multimodal tasks. However, the deployment of large CLIP models is hindered in resource-limited environments, while smaller models frequently fall short of meeting performance benchmarks necessary for practical applications. In this paper, we propose a novel approach, coined as ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model, which aims to comprehensively distill the knowledge from a large teacher CLIP model into a smaller student model, ensuring comparable performance with significantly reduced parameters. ComKD-CLIP is composed of two key mechanisms: Image Feature Alignment (IFAlign) and Educational Attention (EduAttention). IFAlign makes the image features extracted by the student model closely match those extracted by the teacher model, enabling the student to learn teacher's knowledge of extracting image features. EduAttention explores the cross-relationships between text features extracted by the teacher model and image features extracted by the student model, enabling the student model to learn how the teacher model integrates text-image features. In addition, ComKD-CLIP can refine the knowledge distilled from IFAlign and EduAttention leveraging the results of text-image feature fusion by the teacher model, ensuring student model accurately absorbs the knowledge of teacher model. Extensive experiments conducted on 11 datasets have demonstrated the superiority of the proposed method.
Authors: Jiaqi Wu, Junbiao Pang, Qingming Huang
Abstract: In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance to enhance the reliability of deep neural networks. In this paper, we propose a lightweight, loss-function-free, and architecture-agnostic ensemble learning by the Decorrelating Structure via Adapters (DSA) for various visual tasks. Concretely, the proposed DSA leverages the structure-diverse adapters to decorrelate multiple prediction heads without any tailed regularization or loss. This allows DSA to be easily extensible to architecture-agnostic networks for a range of computer vision tasks. Importantly, the theoretically analysis shows that the proposed DSA has a lower bias and variance than that of the single head based method (which is adopted by most of the state of art approaches). Consequently, the DSA makes deep networks reliable and robust for the various real-world challenges, \textit{e.g.}, data corruption, and label noises. Extensive experiments combining the proposed method with FreeMatch achieved the accuracy improvements of 5.35% on CIFAR-10 dataset with 40 labeled data and 0.71% on CIFAR-100 dataset with 400 labeled data. Besides, combining the proposed method with DualPose achieved the improvements in the Percentage of Correct Keypoints (PCK) by 2.08% on the Sniffing dataset with 100 data (30 labeled data), 5.2% on the FLIC dataset with 100 data (including 50 labeled data), and 2.35% on the LSP dataset with 200 data (100 labeled data).
Authors: Hui Luo, Jiashuang Huang, Hengrong Ju, Tianyi Zhou, Weiping Ding
Abstract: Accurate cancer survival prediction is crucial for assisting clinical doctors in formulating treatment plans. Multimodal data, including histopathological images and genomic data, offer complementary and comprehensive information that can greatly enhance the accuracy of this task. However, the current methods, despite yielding promising results, suffer from two notable limitations: they do not effectively utilize global context and disregard modal uncertainty. In this study, we put forward a neural network model called M2EF-NNs, which leverages multimodal and multi-instance evidence fusion techniques for accurate cancer survival prediction. Specifically, to capture global information in the images, we use a pre-trained Vision Transformer (ViT) model to obtain patch feature embeddings of histopathological images. Then, we introduce a multimodal attention module that uses genomic embeddings as queries and learns the co-attention mapping between genomic and histopathological images to achieve an early interaction fusion of multimodal information and better capture their correlations. Subsequently, we are the first to apply the Dempster-Shafer evidence theory (DST) to cancer survival prediction. We parameterize the distribution of class probabilities using the processed multimodal features and introduce subjective logic to estimate the uncertainty associated with different modalities. By combining with the Dempster-Shafer theory, we can dynamically adjust the weights of class probabilities after multimodal fusion to achieve trusted survival prediction. Finally, Experimental validation on the TCGA datasets confirms the significant improvements achieved by our proposed method in cancer survival prediction and enhances the reliability of the model.
Authors: Jinhui Qin, Yong Ma, Jun Huang, Fan Fan, You Du
Abstract: Non-blind rotary motion deblurring (RMD) aims to recover the latent clear image from a rotary motion blurred (RMB) image. The rotation center is a crucial input parameter in non-blind RMD methods. Existing methods directly estimate the rotation center from the RMB image. However they always suffer significant errors, and the performance of RMD is limited. For the assembled imaging systems, the position of the rotation center remains fixed. Leveraging this prior knowledge, we propose a geometric-based method for rotation center identification and analyze its error range. Furthermore, we construct a RMB imaging system. The experiment demonstrates that our method achieves less than 1-pixel error along a single axis (x-axis or y-axis). We utilize the constructed imaging system to capture real RMB images, and experimental results show that our method can help existing RMD approaches yield better RMD images.
Authors: Xiangcheng Du, Zhao Zhou, Yanlong Wang, Zhuoyao Wang, Yingbin Zheng, Cheng Jin
Abstract: Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping function, a.k.a., color space, during the colorization pipeline. In this paper, we first investigate the modeling of different color spaces, and find each of them exhibiting distinctive characteristics with unique distribution of colors. The complementarity among multiple color spaces leads to benefits for the image colorization task. We present MultiColor, a new learning-based approach to automatically colorize grayscale images that combines clues from multiple color spaces. Specifically, we employ a set of dedicated colorization modules for individual color space. Within each module, a transformer decoder is first employed to refine color query embeddings and then a color mapper produces color channel prediction using the embeddings and semantic features. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images. We conduct extensive experiments on real-world datasets, and the results demonstrate superior performance over the state-of-the-arts.
Authors: Junde Wu, Jiayuan Zhu, Yunli Qi
Abstract: We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities and generating evidence-based results, thereby improving safety and reliability when handling private medical data. Our comprehensive pipeline begins with a hybrid static-semantic approach to document chunking, significantly improving context capture over traditional methods. Extracted entities are used to create a three-tier hierarchical graph structure, linking entities to foundational medical knowledge sourced from medical papers and dictionaries. These entities are then interconnected to form meta-graphs, which are merged based on semantic similarities to develop a comprehensive global graph. This structure supports precise information retrieval and response generation. The retrieval process employs a U-retrieve method to balance global awareness and indexing efficiency of the LLM. Our approach is validated through a comprehensive ablation study comparing various methods for document chunking, graph construction, and information retrieval. The results not only demonstrate that our hierarchical graph construction method consistently outperforms state-of-the-art models on multiple medical Q\&A benchmarks, but also confirms that the responses generated include source documentation, significantly enhancing the reliability of medical LLMs in practical applications. Code will be at: https://github.com/MedicineToken/Medical-Graph-RAG/tree/main
URLs: https://github.com/MedicineToken/Medical-Graph-RAG/tree/main
Authors: Khanh Doan, Long Tung Vuong, Tuan Nguyen, Anh Tuan Bui, Quyen Tran, Thanh-Toan Do, Dinh Phung, Trung Le
Abstract: Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.
Authors: Junbin Xiao, Nanxin Huang, Hangyu Qin, Dongyang Li, Yicong Li, Fengbin Zhu, Zhulin Tao, Jianxing Yu, Liang Lin, Tat-Seng Chua, Angela Yao
Abstract: Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in Video-LLM developing. This work conducts a timely and comprehensive study of Video-LLMs' behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering. Our analyses demonstrate that Video-LLMs excel in VideoQA; they can correlate contextual cues and generate plausible responses to questions about varied video contents. However, models falter in handling video temporality, both in reasoning about temporal content ordering and grounding QA-relevant temporal moments. Moreover, the models behave unintuitively - they are unresponsive to adversarial video perturbations while being sensitive to simple variations of candidate answers and questions. Also, they do not necessarily generalize better. The findings demonstrate Video-LLMs' QA capability in standard condition yet highlight their severe deficiency in robustness and interpretability, suggesting the urgent need on rationales in Video-LLM developing.
Authors: Ahmad Arrabi, Xiaohan Zhang, Waqas Sultan, Chen Chen, Safwan Wshah
Abstract: Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibility. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird's Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multi-modal cross-view dataset, namely VIGORv2 which is built upon VIGOR with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and data will be publicly available.
Authors: Zhifeng Wang, Kaihao Zhang, Ramesh Sankaranarayana
Abstract: This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions.
Authors: Rex Liu, Xin Liu
Abstract: With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data and wearable sensor data presents challenges due to the labor-intensive data annotation, and reliance on external pretrained models or additional data. To address these challenges, we introduce Multimodal Masked Autoencoders-Based One-Shot Learning (Mu-MAE). Mu-MAE integrates a multimodal masked autoencoder with a synchronized masking strategy tailored for wearable sensors. This masking strategy compels the networks to capture more meaningful spatiotemporal features, which enables effective self-supervised pretraining without the need for external data. Furthermore, Mu-MAE leverages the representation extracted from multimodal masked autoencoders as prior information input to a cross-attention multimodal fusion layer. This fusion layer emphasizes spatiotemporal features requiring attention across different modalities while highlighting differences from other classes, aiding in the classification of various classes in metric-based one-shot learning. Comprehensive evaluations on MMAct one-shot classification show that Mu-MAE outperforms all the evaluated approaches, achieving up to an 80.17% accuracy for five-way one-shot multimodal classification, without the use of additional data.
Authors: Xin-Yi Yu, Jun-Xin Yu, Li-Bo Zhou, Yan Wei, Lin-Lin Ou
Abstract: We present InstantStyleGaussian, an innovative 3D style transfer method based on the 3D Gaussian Splatting (3DGS) scene representation. By inputting a target style image, it quickly generates new 3D GS scenes. Our approach operates on pre-reconstructed GS scenes, combining diffusion models with an improved iterative dataset update strategy. It utilizes diffusion models to generate target style images, adds these new images to the training dataset, and uses this dataset to iteratively update and optimize the GS scenes. Extensive experimental results demonstrate that our method ensures high-quality stylized scenes while offering significant advantages in style transfer speed and consistency.
Authors: Fuzhang Li, Chuan Lin
Abstract: Edge detection is crucial in medical image processing, enabling precise extraction of structural information to support lesion identification and image analysis. Traditional edge detection models typically rely on complex Convolutional Neural Networks and Vision Transformer architectures. Due to their numerous parameters and high computational demands, these models are limited in their application on resource-constrained devices. This paper presents an ultra-lightweight edge detection model (UHNet), characterized by its minimal parameter count, rapid computation speed, negligible of pre-training costs, and commendable performance. UHNet boasts impressive performance metrics with 42.3k parameters, 166 FPS, and 0.79G FLOPs. By employing an innovative feature extraction module and optimized residual connection method, UHNet significantly reduces model complexity and computational requirements. Additionally, a lightweight feature fusion strategy is explored, enhancing detection accuracy. Experimental results on the BSDS500, NYUD, and BIPED datasets validate that UHNet achieves remarkable edge detection performance while maintaining high efficiency. This work not only provides new insights into the design of lightweight edge detection models but also demonstrates the potential and application prospects of the UHNet model in engineering applications such as medical image processing. The codes are available at https://github.com/stoneLi20cv/UHNet
Authors: Jonggyu Jang, Hyeonsu Lyu, Seongjin Hwang, Hyun Jong Yang
Abstract: This paper investigates the security vulnerabilities of adversarial-example-based image encryption by executing data reconstruction (DR) attacks on encrypted images. A representative image encryption method is the adversarial visual information hiding (AVIH), which uses type-I adversarial example training to protect gallery datasets used in image recognition tasks. In the AVIH method, the type-I adversarial example approach creates images that appear completely different but are still recognized by machines as the original ones. Additionally, the AVIH method can restore encrypted images to their original forms using a predefined private key generative model. For the best security, assigning a unique key to each image is recommended; however, storage limitations may necessitate some images sharing the same key model. This raises a crucial security question for AVIH: How many images can safely share the same key model without being compromised by a DR attack? To address this question, we introduce a dual-strategy DR attack against the AVIH encryption method by incorporating (1) generative-adversarial loss and (2) augmented identity loss, which prevent DR from overfitting -- an issue akin to that in machine learning. Our numerical results validate this approach through image recognition and re-identification benchmarks, demonstrating that our strategy can significantly enhance the quality of reconstructed images, thereby requiring fewer key-sharing encrypted images. Our source code to reproduce our results will be available soon.
Authors: Azad Singh, Deepak Mishra
Abstract: Self-supervised learning (SSL) has emerged as a promising paradigm for medical image analysis by harnessing unannotated data. Despite their potential, the existing SSL approaches overlook the high anatomical similarity inherent in medical images. This makes it challenging for SSL methods to capture diverse semantic content in medical images consistently. This work introduces a novel and generalized solution that implicitly exploits anatomical similarities by integrating codebooks in SSL. The codebook serves as a concise and informative dictionary of visual patterns, which not only aids in capturing nuanced anatomical details but also facilitates the creation of robust and generalized feature representations. In this context, we propose CoBooM, a novel framework for self-supervised medical image learning by integrating continuous and discrete representations. The continuous component ensures the preservation of fine-grained details, while the discrete aspect facilitates coarse-grained feature extraction through the structured embedding space. To understand the effectiveness of CoBooM, we conduct a comprehensive evaluation of various medical datasets encompassing chest X-rays and fundus images. The experimental results reveal a significant performance gain in classification and segmentation tasks.
Authors: Yiming Zhou, Zixuan Zeng, Andi Chen, Xiaofan Zhou, Haowei Ni, Shiyao Zhang, Panfeng Li, Liangxi Liu, Mengyao Zheng, Xupeng Chen
Abstract: Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with traditional Simultaneous Localization and Mapping (SLAM) systems. Utilizing datasets such as Replica and ScanNet, we assess performance based on tracking accuracy, mapping fidelity, and view synthesis. Findings reveal that NeRF excels in view synthesis, offering unique capabilities in generating new perspectives from existing data, albeit at slower processing speeds. Conversely, Gaussian-based methods provide rapid processing and significant expressiveness but lack comprehensive scene completion. Enhanced by global optimization and loop closure techniques, newer methods like NICE-SLAM and SplaTAM not only surpass older frameworks such as ORB-SLAM2 in terms of robustness but also demonstrate superior performance in dynamic and complex environments. This comparative analysis bridges theoretical research with practical implications, shedding light on future developments in robust 3D scene reconstruction across various real-world applications.
Authors: Yuchen Wang, Ziyi Guo, Haixia Bi, Danfeng Hong, Chen Xu
Abstract: The annotation of polarimetric synthetic aperture radar (PolSAR) images is a labor-intensive and time-consuming process. Therefore, classifying PolSAR images with limited labels is a challenging task in remote sensing domain. In recent years, self-supervised learning approaches have proven effective in PolSAR image classification with sparse labels. However, we observe a lack of research on generative selfsupervised learning in the studied task. Motivated by this, we propose a dual-branch classification model based on generative self-supervised learning in this paper. The first branch is a superpixel-branch, which learns superpixel-level polarimetric representations using a generative self-supervised graph masked autoencoder. To acquire finer classification results, a convolutional neural networks-based pixel-branch is further incorporated to learn pixel-level features. Classification with fused dual-branch features is finally performed to obtain the predictions. Experimental results on the benchmark Flevoland dataset demonstrate that our approach yields promising classification results.
Authors: Wan Li, Xinyun Zhong, Wei Li, Song Zhang, Moheng Rong, Yan Xi, Peng Yuan, Zechen Wang, Xiaolei Jiang, Rongxi Yi, Hui Tang, Yang Chen, Chaohui Tong, Zhan Wu, Feng Wang
Abstract: Currently, lung cancer is a leading cause of global cancer mortality, often necessitating minimally invasive interventions. Microwave ablation (MWA) is extensively utilized for both primary and secondary lung tumors. Although numerous clinical guidelines and standards for MWA have been established, the clinical evaluation of ablation surgery remains challenging and requires long-term patient follow-up for confirmation. In this paper, we propose a method termed respiratory subtraction to evaluate lung tumor ablation therapy performance based on pre- and post-operative image guidance. Initially, preoperative images undergo coarse rigid registration to their corresponding postoperative positions, followed by further non-rigid registration. Subsequently, subtraction images are generated by subtracting the registered preoperative images from the postoperative ones. Furthermore, to enhance the clinical assessment of MWA treatment performance, we devise a quantitative analysis metric to evaluate ablation efficacy by comparing differences between tumor areas and treatment areas. To the best of our knowledge, this is the pioneering work in the field to facilitate the assessment of MWA surgery performance on pulmonary tumors. Extensive experiments involving 35 clinical cases further validate the efficacy of the respiratory subtraction method. The experimental results confirm the effectiveness of the respiratory subtraction method and the proposed quantitative evaluation metric in assessing lung tumor treatment.
Authors: Shixuan Gao, Pingping Zhang, Tianyu Yan, Huchuan Lu
Abstract: Salient Object Detection (SOD) aims to identify and segment the most prominent objects in images. Advanced SOD methods often utilize various Convolutional Neural Networks (CNN) or Transformers for deep feature extraction. However, these methods still deliver low performance and poor generalization in complex cases. Recently, Segment Anything Model (SAM) has been proposed as a visual fundamental model, which gives strong segmentation and generalization capabilities. Nonetheless, SAM requires accurate prompts of target objects, which are unavailable in SOD. Additionally, SAM lacks the utilization of multi-scale and multi-level information, as well as the incorporation of fine-grained details. To address these shortcomings, we propose a Multi-scale and Detail-enhanced SAM (MDSAM) for SOD. Specifically, we first introduce a Lightweight Multi-Scale Adapter (LMSA), which allows SAM to learn multi-scale information with very few trainable parameters. Then, we propose a Multi-Level Fusion Module (MLFM) to comprehensively utilize the multi-level information from the SAM's encoder. Finally, we propose a Detail Enhancement Module (DEM) to incorporate SAM with fine-grained details. Experimental results demonstrate the superior performance of our model on multiple SOD datasets and its strong generalization on other segmentation tasks. The source code is released at https://github.com/BellyBeauty/MDSAM.
Authors: Jayateja Kalla, Soma Biswas
Abstract: This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At inference, all image rotation predictions are aggregated for the final prediction, a strategy we term Aggregated Self-Supervision (AggSS). We observe a shift in the deep neural network's attention towards intrinsic object features as it learns through AggSS strategy. This learning approach significantly enhances class-incremental learning by promoting robust feature learning. AggSS serves as a plug-and-play module that can be seamlessly incorporated into any class-incremental learning framework, leveraging its powerful feature learning capabilities to enhance performance across various class-incremental learning approaches. Extensive experiments conducted on standard incremental learning datasets CIFAR-100 and ImageNet-Subset demonstrate the significant role of AggSS in improving performance within these paradigms.
Authors: Guido Caccianiga, Julian Nubert, Cesar Cadena, Marco Hutter, Katherine J. Kuchenbecker
Abstract: Reconstructing the 3D shape of a deformable environment from the information captured by a moving depth camera is highly relevant to surgery. The underlying challenge is the fact that simultaneously estimating camera motion and tissue deformation in a fully deformable scene is an ill-posed problem, especially from a single arbitrarily moving viewpoint. Current solutions are often organ-specific and lack the robustness required to handle large deformations. Here we propose a multi-viewpoint global optimization framework that can flexibly integrate the output of low-level perception modules (data association, depth, and relative scene flow) with kinematic and scene-modeling priors to jointly estimate multiple camera motions and absolute scene flow. We use simulated noisy data to show three practical examples that successfully constrain the convergence to a unique solution. Overall, our method shows robustness to combined noisy input measures and can process hundreds of points in a few milliseconds. MultiViPerFrOG builds a generalized learning-free scaffolding for spatio-temporal encoding that can unlock advanced surgical scene representations and will facilitate the development of the computer-assisted-surgery technologies of the future.
Authors: Mengya Xu, Ziqi Guo, An Wang, Long Bai, Hongliang Ren
Abstract: As a crucial and intricate task in robotic minimally invasive surgery, reconstructing surgical scenes using stereo or monocular endoscopic video holds immense potential for clinical applications. NeRF-based techniques have recently garnered attention for the ability to reconstruct scenes implicitly. On the other hand, Gaussian splatting-based 3D-GS represents scenes explicitly using 3D Gaussians and projects them onto a 2D plane as a replacement for the complex volume rendering in NeRF. However, these methods face challenges regarding surgical scene reconstruction, such as slow inference, dynamic scenes, and surgical tool occlusion. This work explores and reviews state-of-the-art (SOTA) approaches, discussing their innovations and implementation principles. Furthermore, we replicate the models and conduct testing and evaluation on two datasets. The test results demonstrate that with advancements in these techniques, achieving real-time, high-quality reconstructions becomes feasible.
Authors: Michele Craighero, Sarah Solbiati, Federica Mozzini, Enrico Caiani, Giacomo Boracchi
Abstract: The seismocardiographic signal is a promising alternative to the traditional ECG in the analysis of the cardiac activity. In particular, the systolic complex is known to be the most informative part of the seismocardiogram, thus requiring further analysis. State-of-art solutions to detect the systolic complex are based on Deep Learning models, which have been proven effective in pioneering studies. However, these solutions have only been tested in a controlled scenario considering only clean signals acquired from users maintained still in supine position. On top of that, all these studies consider data coming from a single dataset, ignoring the benefits and challenges related to a cross-dataset scenario. In this work, a cross-dataset experimental analysis was performed considering also data from a real-world scenario. Our findings prove the effectiveness of a deep learning solution, while showing the importance of a personalization step to contrast the domain shift, namely a change in data distribution between training and testing data. Finally, we demonstrate the benefits of a multi-channels approach, leveraging the information extracted from both accelerometers and gyroscopes data.
Authors: Gabriela Csurka, Tyler L. Hayes, Diane Larlus, Riccardo Volpi
Abstract: Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effective solution to predict and describe via natural language potential failure modes of computer vision models. Given a pretrained model and a set of samples, our aim is to find sentences that accurately describe the visual conditions in which the model underperforms. In order to study this important topic and foster future research on it, we formalize the problem of Language-Based Error Explainability (LBEE) and propose a set of metrics to evaluate and compare different methods for this task. We propose solutions that operate in a joint vision-and-language embedding space, and can characterize through language descriptions model failures caused, e.g., by objects unseen during training or adverse visual conditions. We experiment with different tasks, such as classification under the presence of dataset bias and semantic segmentation in unseen environments, and show that the proposed methodology isolates nontrivial sentences associated with specific error causes. We hope our work will help practitioners better understand the behavior of models, increasing their overall safety and interpretability.
Authors: Joanna Kaleta, Kacper Kania, Tomasz Trzcinski, Marek Kowalski
Abstract: Decoupling lighting from geometry using unconstrained photo collections is notoriously challenging. Solving it would benefit many users, as creating complex 3D assets takes days of manual labor. Many previous works have attempted to address this issue, often at the expense of output fidelity, which questions the practicality of such methods. We introduce LumiGauss, a technique that tackles 3D reconstruction of scenes and environmental lighting through 2D Gaussian Splatting. Our approach yields high-quality scene reconstructions and enables realistic lighting synthesis under novel environment maps. We also propose a method for enhancing the quality of shadows, common in outdoor scenes, by exploiting spherical harmonics properties. Our approach facilitates seamless integration with game engines and enables the use of fast precomputed radiance transfer. We validate our method on the NeRF-OSR dataset, demonstrating superior performance over baseline methods. Moreover, LumiGauss can synthesize realistic images when applying novel environment maps.
Authors: Sriram Mandalika, Athira Nambiar
Abstract: Most of the sophisticated AI models utilize huge amounts of annotated data and heavy training to achieve high-end performance. However, there are certain challenges that hinder the deployment of AI models "in-the-wild" scenarios, i.e., inefficient use of unlabeled data, lack of incorporation of human expertise, and lack of interpretation of the results. To mitigate these challenges, we propose a novel Explainable Active Learning (XAL) model, XAL-based semantic segmentation model "SegXAL", that can (i) effectively utilize the unlabeled data, (ii) facilitate the "Human-in-the-loop" paradigm, and (iii) augment the model decisions in an interpretable way. In particular, we investigate the application of the SegXAL model for semantic segmentation in driving scene scenarios. The SegXAL model proposes the image regions that require labeling assistance from Oracle by dint of explainable AI (XAI) and uncertainty measures in a weakly-supervised manner. Specifically, we propose a novel Proximity-aware Explainable-AI (PAE) module and Entropy-based Uncertainty (EBU) module to get an Explainable Error Mask, which enables the machine teachers/human experts to provide intuitive reasoning behind the results and to solicit feedback to the AI system via an active learning strategy. Such a mechanism bridges the semantic gap between man and machine through collaborative intelligence, where humans and AI actively enhance each other's complementary strengths. A novel high-confidence sample selection technique based on the DICE similarity coefficient is also presented within the SegXAL framework. Extensive quantitative and qualitative analyses are carried out in the benchmarking Cityscape dataset. Results show the outperformance of our proposed SegXAL against other state-of-the-art models.
Authors: Vandan Gorade, Onkar Susladkar, Gorkem Durak, Elif Keles, Ertugrul Aktas, Timurhan Cebeci, Alpay Medetalibeyoglu, Daniela Ladner, Debesh Jha, Ulas Bagci
Abstract: Liver cirrhosis, a leading cause of global mortality, requires precise segmentation of ROIs for effective disease monitoring and treatment planning. Existing segmentation models often fail to capture complex feature interactions and generalize across diverse datasets. To address these limitations, we propose a novel synergistic theory that leverages complementary latent spaces for enhanced feature interaction modeling. Our proposed architecture, nnSynergyNet3D integrates continuous and discrete latent spaces for 3D volumes and features auto-configured training. This approach captures both fine-grained and coarse features, enabling effective modeling of intricate feature interactions. We empirically validated nnSynergyNet3D on a private dataset of 628 high-resolution T1 abdominal MRI scans from 339 patients. Our model outperformed the baseline nnUNet3D by approximately 2%. Additionally, zero-shot testing on healthy liver CT scans from the public LiTS dataset demonstrated superior cross-modal generalization capabilities. These results highlight the potential of synergistic latent space models to improve segmentation accuracy and robustness, thereby enhancing clinical workflows by ensuring consistency across CT and MRI modalities.
Authors: Evelyn Navarrete, Ralph Ewerth, Anett Hoppe
Abstract: Identifying the regions of a learning resource that a learner pays attention to is crucial for assessing the material's impact and improving its design and related support systems. Saliency detection in videos addresses the automatic recognition of attention-drawing regions in single frames. In educational settings, the recognition of pertinent regions in a video's visual stream can enhance content accessibility and information retrieval tasks such as video segmentation, navigation, and summarization. Such advancements can pave the way for the development of advanced AI-assisted technologies that support learning with greater efficacy. However, this task becomes particularly challenging for educational videos due to the combination of unique characteristics such as text, voice, illustrations, animations, and more. To the best of our knowledge, there is currently no study that evaluates saliency detection approaches in educational videos. In this paper, we address this gap by evaluating four state-of-the-art saliency detection approaches for educational videos. We reproduce the original studies and explore the replication capabilities for general-purpose (non-educational) datasets. Then, we investigate the generalization capabilities of the models and evaluate their performance on educational videos. We conduct a comprehensive analysis to identify common failure scenarios and possible areas of improvement. Our experimental results show that educational videos remain a challenging context for generic video saliency detection models.
Authors: Daniele Rege Cambrin, Isaac Corley, Paolo Garza
Abstract: Estimating global tree canopy height is crucial for forest conservation and climate change applications. However, capturing high-resolution ground truth canopy height using LiDAR is expensive and not available globally. An efficient alternative is to train a canopy height estimator to operate on single-view remotely sensed imagery. The primary obstacle to this approach is that these methods require significant training data to generalize well globally and across uncommon edge cases. Recent monocular depth estimation foundation models have show strong zero-shot performance even for complex scenes. In this paper we leverage the representations learned by these models to transfer to the remote sensing domain for measuring canopy height. Our findings suggest that our proposed Depth Any Canopy, the result of fine-tuning the Depth Anything v2 model for canopy height estimation, provides a performant and efficient solution, surpassing the current state-of-the-art with superior or comparable performance using only a fraction of the computational resources and parameters. Furthermore, our approach requires less than \$1.30 in compute and results in an estimated carbon footprint of 0.14 kgCO2. Code, experimental results, and model checkpoints are openly available at https://github.com/DarthReca/depth-any-canopy.
Authors: Yongzhi Xu, Yonhon Ng, Yifu Wang, Inkyu Sa, Yunfei Duan, Yang Li, Pan Ji, Hongdong Li
Abstract: 3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating interactive and playable 3D game scenes, all from the user's casual prompts such as a hand-drawn sketch. Sketch-based input offers a natural, and convenient way to convey the user's design intention in the content creation process. To circumvent the data-deficient challenge in learning (i.e. the lack of large training data of 3D scenes), our method leverages a pre-trained 2D denoising diffusion model to generate a 2D image of the scene as the conceptual guidance. In this process, we adopt the isometric projection mode to factor out unknown camera poses while obtaining the scene layout. From the generated isometric image, we use a pre-trained image understanding method to segment the image into meaningful parts, such as off-ground objects, trees, and buildings, and extract the 2D scene layout. These segments and layouts are subsequently fed into a procedural content generation (PCG) engine, such as a 3D video game engine like Unity or Unreal, to create the 3D scene. The resulting 3D scene can be seamlessly integrated into a game development environment and is readily playable. Extensive tests demonstrate that our method can efficiently generate high-quality and interactive 3D game scenes with layouts that closely follow the user's intention.
Authors: Tianrun Chen, Ankang Lu, Lanyun Zhu, Chaotao Ding, Chunan Yu, Deyi Ji, Zejian Li, Lingyun Sun, Papa Mao, Ying Zang
Abstract: The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger training corpus, we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/
Authors: Hongjun Wang, Sagar Vaze, Kai Han
Abstract: Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones. In this paper, we challenge a remaining assumption in this task: that all images share the same domain. Specifically, we introduce a new task and method to handle GCD when the unlabelled data also contains images from different domains to the labelled set. Our proposed `HiLo' networks extract High-level semantic and Low-level domain features, before minimizing the mutual information between the representations. Our intuition is that the clusterings based on domain information and semantic information should be independent. We further extend our method with a specialized domain augmentation tailored for the GCD task, as well as a curriculum learning approach. Finally, we construct a benchmark from corrupted fine-grained datasets as well as a large-scale evaluation on DomainNet with real-world domain shifts, reimplementing a number of GCD baselines in this setting. We demonstrate that HiLo outperforms SoTA category discovery models by a large margin on all evaluations.
Authors: Jieming Yu, An Wang, Wenzhen Dong, Mengya Xu, Mobarakol Islam, Jie Wang, Long Bai, Hongliang Ren
Abstract: The recent Segment Anything Model (SAM) 2 has demonstrated remarkable foundational competence in semantic segmentation, with its memory mechanism and mask decoder further addressing challenges in video tracking and object occlusion, thereby achieving superior results in interactive segmentation for both images and videos. Building upon our previous empirical studies, we further explore the zero-shot segmentation performance of SAM 2 in robot-assisted surgery based on prompts, alongside its robustness against real-world corruption. For static images, we employ two forms of prompts: 1-point and bounding box, while for video sequences, the 1-point prompt is applied to the initial frame. Through extensive experimentation on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 2, when utilizing bounding box prompts, outperforms state-of-the-art (SOTA) methods in comparative evaluations. The results with point prompts also exhibit a substantial enhancement over SAM's capabilities, nearing or even surpassing existing unprompted SOTA methodologies. Besides, SAM 2 demonstrates improved inference speed and less performance degradation against various image corruption. Although slightly unsatisfactory results remain in specific edges or regions, SAM 2's robust adaptability to 1-point prompts underscores its potential for downstream surgical tasks with limited prompt requirements.
Authors: Qirui Jiao, Daoyuan Chen, Yilun Huang, Yaliang Li, Ying Shen
Abstract: High-performance Multimodal Large Language Models (MLLMs) rely heavily on data quality. This study introduces a novel dataset named Img-Diff, designed to enhance fine-grained image recognition in MLLMs by leveraging insights from contrastive learning and image difference captioning. By analyzing object differences between similar images, we challenge models to identify both matching and distinct components. We utilize the Stable-Diffusion-XL model and advanced image editing techniques to create pairs of similar images that highlight object replacements. Our methodology includes a Difference Area Generator for object differences identifying, followed by a Difference Captions Generator for detailed difference descriptions. The result is a relatively small but high-quality dataset of "object replacement" samples. We use the the proposed dataset to fine-tune state-of-the-art (SOTA) MLLMs such as MGM-7B, yielding comprehensive improvements of performance scores over SOTA models that trained with larger-scale datasets, in numerous image difference and Visual Question Answering tasks. For instance, our trained models notably surpass the SOTA models GPT-4V and Gemini on the MMVP benchmark. Besides, we investigate alternative methods for generating image difference data through "object removal" and conduct thorough evaluation to confirm the dataset's diversity, quality, and robustness, presenting several insights on synthesis of such contrastive dataset. To encourage further research and advance the field of multimodal data synthesis and enhancement of MLLMs' fundamental capabilities for image understanding, we release our codes and dataset at https://github.com/modelscope/data-juicer/tree/ImgDiff.
URLs: https://github.com/modelscope/data-juicer/tree/ImgDiff.
Authors: Hefeng Wu, Hao Jiang, Keze Wang, Ziyi Tang, Xianghuan He, Liang Lin
Abstract: While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some works strive to improve both interpretability and performance, but they primarily depend on meticulously imposed conditions. In this paper, we propose a simple yet effective framework that acquires more explainable activation heatmaps and simultaneously increase the model performance, without the need for any extra supervision. Specifically, our concise framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. The explanation consistency metric is utilized to measure the similarity between the model's visual explanations of the original samples and those of semantic-preserved adversarial samples, whose background regions are perturbed by using image adversarial attack techniques. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations (i.e., low explanation consistency), for which the current model cannot provide robust interpretations. Comprehensive experimental results on various benchmarks demonstrate the superiority of our framework in multiple aspects, including higher recognition accuracy, greater data debiasing capability, stronger network robustness, and more precise localization ability on both regular networks and interpretable networks. We also provide extensive ablation studies and qualitative analyses to unveil the detailed contribution of each component.
Authors: Hongze Zhu, Guoyang Xie, Chengbin Hou, Tao Dai, Can Gao, Jinbao Wang, Linlin Shen
Abstract: High-resolution point clouds~(HRPCD) anomaly detection~(AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level; ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation; iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network~(IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network~(IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection~(AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5\% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://github.com/M-3LAB/Group3AD.
Authors: Gracile Astlin Pereira
Abstract: This paper presents the development of an industrial fall detection system utilizing YOLOv8 variants, enhanced by our proposed augmentation pipeline to increase dataset variance and improve detection accuracy. Among the models evaluated, the YOLOv8m model, consisting of 25.9 million parameters and 79.1 GFLOPs, demonstrated a respectable balance between computational efficiency and detection performance, achieving a mean Average Precision (mAP) of 0.971 at 50% Intersection over Union (IoU) across both "Fall Detected" and "Human in Motion" categories. Although the YOLOv8l and YOLOv8x models presented higher precision and recall, particularly in fall detection, their higher computational demands and model size make them less suitable for resource-constrained environments.
Authors: Bhushan Atote, Victor Sanchez
Abstract: Explainable Artificial Intelligence (xAI) has the potential to enhance the transparency and trust of AI-based systems. Although accurate predictions can be made using Deep Neural Networks (DNNs), the process used to arrive at such predictions is usually hard to explain. In terms of perceptibly human-friendly representations, such as word phrases in text or super-pixels in images, prototype-based explanations can justify a model's decision. In this work, we introduce a DNN architecture for image classification, the Enhanced Prototypical Part Network (EPPNet), which achieves strong performance while discovering relevant prototypes that can be used to explain the classification results. This is achieved by introducing a novel cluster loss that helps to discover more relevant human-understandable prototypes. We also introduce a faithfulness score to evaluate the explainability of the results based on the discovered prototypes. Our score not only accounts for the relevance of the learned prototypes but also the performance of a model. Our evaluations on the CUB-200-2011 dataset show that the EPPNet outperforms state-of-the-art xAI-based methods, in terms of both classification accuracy and explainability
Authors: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Abstract: We present Puppet-Master, an interactive video generative model that can serve as a motion prior for part-level dynamics. At test time, given a single image and a sparse set of motion trajectories (i.e., drags), Puppet-Master can synthesize a video depicting realistic part-level motion faithful to the given drag interactions. This is achieved by fine-tuning a large-scale pre-trained video diffusion model, for which we propose a new conditioning architecture to inject the dragging control effectively. More importantly, we introduce the all-to-first attention mechanism, a drop-in replacement for the widely adopted spatial attention modules, which significantly improves generation quality by addressing the appearance and background issues in existing models. Unlike other motion-conditioned video generators that are trained on in-the-wild videos and mostly move an entire object, Puppet-Master is learned from Objaverse-Animation-HQ, a new dataset of curated part-level motion clips. We propose a strategy to automatically filter out sub-optimal animations and augment the synthetic renderings with meaningful motion trajectories. Puppet-Master generalizes well to real images across various categories and outperforms existing methods in a zero-shot manner on a real-world benchmark. See our project page for more results: vgg-puppetmaster.github.io.
Authors: Luca Bartolomei, Matteo Poggi, Andrea Conti, Stefano Mattoccia
Abstract: Event stereo matching is an emerging technique to estimate depth from neuromorphic cameras; however, events are unlikely to trigger in the absence of motion or the presence of large, untextured regions, making the correspondence problem extremely challenging. Purposely, we propose integrating a stereo event camera with a fixed-frequency active sensor -- e.g., a LiDAR -- collecting sparse depth measurements, overcoming the aforementioned limitations. Such depth hints are used by hallucinating -- i.e., inserting fictitious events -- the stacks or raw input streams, compensating for the lack of information in the absence of brightness changes. Our techniques are general, can be adapted to any structured representation to stack events and outperform state-of-the-art fusion methods applied to event-based stereo.
Authors: Daniil Gurgurov, Aleksey Morshnev
Abstract: In this project, we train a vision encoder-decoder model to generate LaTeX code from images of mathematical formulas and text. Utilizing a diverse collection of image-to-LaTeX data, we build two models: a base model with a Swin Transformer encoder and a GPT-2 decoder, trained on machine-generated images, and a fine-tuned version enhanced with Low-Rank Adaptation (LoRA) trained on handwritten formulas. We then compare the BLEU performance of our specialized model on a handwritten test set with other similar models, such as Pix2Text, TexTeller, and Sumen. Through this project, we contribute open-source models for converting images to LaTeX and provide from-scratch code for building these models with distributed training and GPU optimizations.
Authors: Mohamed Hassan, Aleksander Vakanski, Min Xian
Abstract: Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of the loss landscape. Among the optimization approaches that explicitly minimize sharpness, Sharpness-Aware Minimization (SAM) has shown potential in enhancing generalization performance on general domain image datasets. This success has led to the development of several advanced sharpness-based algorithms aimed at addressing the limitations of SAM, such as Adaptive SAM, surrogate-Gap SAM, Weighted SAM, and Curvature Regularized SAM. These sharpness-based optimizers have shown improvements in model generalization compared to conventional stochastic gradient descent optimizers and their variants on general domain image datasets, but they have not been thoroughly evaluated on medical images. This work provides a review of recent sharpness-based methods for improving the generalization of deep learning networks and evaluates the methods performance on medical breast ultrasound images. Our findings indicate that the initial SAM method successfully enhances the generalization of various deep learning models. While Adaptive SAM improves generalization of convolutional neural networks, it fails to do so for vision transformers. Other sharpness-based optimizers, however, do not demonstrate consistent results. The results reveal that, contrary to findings in the non-medical domain, SAM is the only recommended sharpness-based optimizer that consistently improves generalization in medical image analysis, and further research is necessary to refine the variants of SAM to enhance generalization performance in this field
Authors: Anna Kravchenko, Andrey A. Bagrov, Mikhail I. Katsnelson, Veronica Dudarev
Abstract: While intuitive for humans, the concept of visual complexity is hard to define and quantify formally. We suggest adopting the multi-scale structural complexity (MSSC) measure, an approach that defines structural complexity of an object as the amount of dissimilarities between distinct scales in its hierarchical organization. In this work, we apply MSSC to the case of visual stimuli, using an open dataset of images with subjective complexity scores obtained from human participants (SAVOIAS). We demonstrate that MSSC correlates with subjective complexity on par with other computational complexity measures, while being more intuitive by definition, consistent across categories of images, and easier to compute. We discuss objective and subjective elements inherently present in human perception of complexity and the domains where the two are more likely to diverge. We show how the multi-scale nature of MSSC allows further investigation of complexity as it is perceived by humans.
Authors: Xin Tian, Nantheera Anantrasirichai, Lindsay Nicholson, Alin Achim
Abstract: Optical coherence tomography (OCT) and confocal microscopy are pivotal in retinal imaging, offering distinct advantages and limitations. In vivo OCT offers rapid, non-invasive imaging but can suffer from clarity issues and motion artifacts, while ex vivo confocal microscopy, providing high-resolution, cellular-detailed color images, is invasive and raises ethical concerns. To bridge the benefits of both modalities, we propose a novel framework based on unsupervised 3D CycleGAN for translating unpaired in vivo OCT to ex vivo confocal microscopy images. This marks the first attempt to exploit the inherent 3D information of OCT and translate it into the rich, detailed color domain of confocal microscopy. We also introduce a unique dataset, OCT2Confocal, comprising mouse OCT and confocal retinal images, facilitating the development of and establishing a benchmark for cross-modal image translation research. Our model has been evaluated both quantitatively and qualitatively, achieving Fr\'echet Inception Distance (FID) scores of 0.766 and Kernel Inception Distance (KID) scores as low as 0.153, and leading subjective Mean Opinion Scores (MOS). Our model demonstrated superior image fidelity and quality with limited data over existing methods. Our approach effectively synthesizes color information from 3D confocal images, closely approximating target outcomes and suggesting enhanced potential for diagnostic and monitoring applications in ophthalmology.
Authors: Panagiotis Fytas, Anna Breger, Ian Selby, Simon Baker, Shahab Shahipasand, Anna Korhonen
Abstract: Developing imaging models capable of detecting pathologies from chest X-rays can be cost and time-prohibitive for large datasets as it requires supervision to attain state-of-the-art performance. Instead, labels extracted from radiology reports may serve as distant supervision since these are routinely generated as part of clinical practice. Despite their widespread use, current rule-based methods for label extraction rely on extensive rule sets that are limited in their robustness to syntactic variability. To alleviate these limitations, we introduce RadPert, a rule-based system that integrates an uncertainty-aware information schema with a streamlined set of rules, enhancing performance. Additionally, we have developed RadPrompt, a multi-turn prompting strategy that leverages RadPert to bolster the zero-shot predictive capabilities of large language models, achieving a statistically significant improvement in weighted average F1 score over GPT-4 Turbo. Most notably, RadPrompt surpasses both its underlying models, showcasing the synergistic potential of LLMs with rule-based models. We have evaluated our methods on two English Corpora: the MIMIC-CXR gold-standard test set and a gold-standard dataset collected from the Cambridge University Hospitals.
Authors: Xiaole Zhao, Linze Li, Chengxing Xie, Xiaoming Zhang, Ting Jiang, Wenjie Lin, Shuaicheng Liu, Tianrui Li
Abstract: Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models.
Authors: Frank Nielsen, Alexander Soen
Abstract: A Bregman manifold is a synonym for a dually flat space in information geometry which admits as a canonical divergence a Bregman divergence. Bregman manifolds are induced by smooth strictly convex functions like the cumulant or partition functions of regular exponential families, the negative entropy of mixture families, or the characteristic functions of regular cones just to list a few such convex Bregman generators. We describe the design of pyBregMan, a library which implements generic operations on Bregman manifolds and instantiate several common Bregman manifolds used in information sciences. At the core of the library is the notion of Legendre-Fenchel duality inducing a canonical pair of dual potential functions and dual Bregman divergences. The library also implements the Fisher-Rao manifolds of categorical/multinomial distributions and multivariate normal distributions. To demonstrate the use of the pyBregMan kernel manipulating those Bregman and Fisher-Rao manifolds, the library also provides several core algorithms for various applications in statistics, machine learning, information fusion, and so on.
Authors: Sourya Sengupta, Satrajit Chakrabarty, Ravi Soni
Abstract: Segment Anything Model (SAM) demonstrated impressive performance in zero-shot promptable segmentation on natural images. The recently released Segment Anything Model 2 (SAM 2) model claims to have better performance than SAM on images while extending the model's capabilities to video segmentation. It is important to evaluate the recent model's ability in medical image segmentation in a zero-shot promptable manner. In this work, we performed extensive studies with multiple datasets from different imaging modalities to compare the performance between SAM and SAM 2. We used two point prompt strategies: (i) single positive prompt near the centroid of the target structure and (ii) additional positive prompts placed randomly within the target structure. The evaluation included 21 unique organ-modality combinations including abdominal structures, cardiac structures, and fetal head images acquired from publicly available MRI, CT, and Ultrasound datasets. The preliminary results, based on 2D images, indicate that while SAM 2 may perform slightly better in a few cases, but it does not in general surpass SAM for medical image segmentation. Especially when the contrast is lower like in CT, Ultrasound images, SAM 2 performs poorly than SAM. For MRI images, SAM 2 performs at par or better than SAM. Similar to SAM, SAM 2 also suffers from over-segmentation issue especially when the boundaries of the to-be-segmented organ is fuzzy in nature.
Authors: Ziran Zhang, Yuhang Tang, Zhigang Wang, Yueting Chen, Bin Zhao
Abstract: Infrared imaging and turbulence strength measurements are in widespread demand in many fields. This paper introduces a Physical Prior Guided Cooperative Learning (P2GCL) framework to jointly enhance atmospheric turbulence strength estimation and infrared image restoration. P2GCL involves a cyclic collaboration between two models, i.e., a TMNet measures turbulence strength and outputs the refractive index structure constant (Cn2) as a physical prior, a TRNet conducts infrared image sequence restoration based on Cn2 and feeds the restored images back to the TMNet to boost the measurement accuracy. A novel Cn2-guided frequency loss function and a physical constraint loss are introduced to align the training process with physical theories. Experiments demonstrate P2GCL achieves the best performance for both turbulence strength estimation (improving Cn2 MAE by 0.0156, enhancing R2 by 0.1065) and image restoration (enhancing PSNR by 0.2775 dB), validating the significant impact of physical prior guided cooperative learning.
Authors: Linhan Cao, Wei Sun, Xiongkuo Min, Jun Jia, Zicheng Zhang, Zijian Chen, Yucheng Zhu, Lizhou Liu, Qiubo Chen, Jing Chen, Guangtao Zhai
Abstract: Just noticeable distortion (JND), representing the threshold of distortion in an image that is minimally perceptible to the human visual system (HVS), is crucial for image compression algorithms to achieve a trade-off between transmission bit rate and image quality. However, traditional JND prediction methods only rely on pixel-level or sub-band level features, lacking the ability to capture the impact of image content on JND. To bridge this gap, we propose a Semantic-Guided JND (SG-JND) network to leverage semantic information for JND prediction. In particular, SG-JND consists of three essential modules: the image preprocessing module extracts semantic-level patches from images, the feature extraction module extracts multi-layer features by utilizing the cross-scale attention layers, and the JND prediction module regresses the extracted features into the final JND value. Experimental results show that SG-JND achieves the state-of-the-art performance on two publicly available JND datasets, which demonstrates the effectiveness of SG-JND and highlight the significance of incorporating semantic information in JND assessment.
Authors: Alireza Saber, Pouria Parhami, Alimihammad Siahkarzadeh, Amirreza Fateh
Abstract: Pneumonia, a severe respiratory disease, poses significant diagnostic challenges, especially in underdeveloped regions. Traditional diagnostic methods, such as chest X-rays, suffer from variability in interpretation among radiologists, necessitating reliable automated tools. In this study, we propose a novel approach combining deep learning and transformer-based attention mechanisms to enhance pneumonia detection from chest X-rays. Our method begins with lung segmentation using a TransUNet model that integrates our specialized transformer module, which has fewer parameters compared to common transformers while maintaining performance. This model is trained on the "Chest Xray Masks and Labels" dataset and then applied to the Kermany and Cohen datasets to isolate lung regions, enhancing subsequent classification tasks. For classification, we employ pre-trained ResNet models (ResNet-50 and ResNet-101) to extract multi-scale feature maps, processed through our modified transformer module. By employing our specialized transformer, we attain superior results with significantly fewer parameters compared to common transformer models. Our approach achieves high accuracy rates of 92.79% on the Kermany dataset and 95.11% on the Cohen dataset, ensuring robust and efficient performance suitable for resource-constrained environments. "https://github.com/amirrezafateh/Multi-Scale-Transformer-Pneumonia"
URLs: https://github.com/amirrezafateh/Multi-Scale-Transformer-Pneumonia
Authors: Jingfu Yang, Peng Huang, Jing Hu, Shu Hu, Siwei Lyu, Xin Wang, Jun Guo, Xi Wu
Abstract: The CNN has achieved excellent results in the automatic classification of medical images. In this study, we propose a novel deep residual 3D attention non-local network (NL-RAN) to classify CT images included COVID-19, common pneumonia, and normal to perform rapid and explainable COVID-19 diagnosis. We built a deep residual 3D attention non-local network that could achieve end-to-end training. The network is embedded with a nonlocal module to capture global information, while a 3D attention module is embedded to focus on the details of the lesion so that it can directly analyze the 3D lung CT and output the classification results. The output of the attention module can be used as a heat map to increase the interpretability of the model. 4079 3D CT scans were included in this study. Each scan had a unique label (novel coronavirus pneumonia, common pneumonia, and normal). The CT scans cohort was randomly split into a training set of 3263 scans, a validation set of 408 scans, and a testing set of 408 scans. And compare with existing mainstream classification methods, such as CovNet, CBAM, ResNet, etc. Simultaneously compare the visualization results with visualization methods such as CAM. Model performance was evaluated using the Area Under the ROC Curve(AUC), precision, and F1-score. The NL-RAN achieved the AUC of 0.9903, the precision of 0.9473, and the F1-score of 0.9462, surpass all the classification methods compared. The heat map output by the attention module is also clearer than the heat map output by CAM. Our experimental results indicate that our proposed method performs significantly better than existing methods. In addition, the first attention module outputs a heat map containing detailed outline information to increase the interpretability of the model. Our experiments indicate that the inference of our model is fast. It can provide real-time assistance with diagnosis.
Authors: Yassine Habchi, Hamza Kheddar, Yassine Himeur, Abdelkrim Boukabou, Shadi Atalla, Wathiq Mansoor, Hussain Al-Ahmad
Abstract: Many incurable diseases prevalent across global societies stem from various influences, including lifestyle choices, economic conditions, social factors, and genetics. Research predominantly focuses on these diseases due to their widespread nature, aiming to decrease mortality, enhance treatment options, and improve healthcare standards. Among these, kidney disease stands out as a particularly severe condition affecting men and women worldwide. Nonetheless, there is a pressing need for continued research into innovative, early diagnostic methods to develop more effective treatments for such diseases. Recently, automatic diagnosis of Kidney Cancer has become an important challenge especially when using deep learning (DL) due to the importance of training medical datasets, which in most cases are difficult and expensive to obtain. Furthermore, in most cases, algorithms require data from the same domain and a powerful computer with efficient storage capacity. To overcome this issue, a new type of learning known as transfer learning (TL) has been proposed that can produce impressive results based on other different pre-trained data. This paper presents, to the best of the authors' knowledge, the first comprehensive survey of DL-based TL frameworks for kidney cancer diagnosis. This is a strong contribution to help researchers understand the current challenges and perspectives of this topic. Hence, the main limitations and advantages of each framework are identified and detailed critical analyses are provided. Looking ahead, the article identifies promising directions for future research. Moving on, the discussion is concluded by reflecting on the pivotal role of TL in the development of precision medicine and its effects on clinical practice and research in oncology.
Authors: Aliki Anagnostopoulou, Thiago Gouvea, Daniel Sonntag
Abstract: Large language models (LLMs) and large multimodal models (LMMs) have significantly impacted the AI community, industry, and various economic sectors. In journalism, integrating AI poses unique challenges and opportunities, particularly in enhancing the quality and efficiency of news reporting. This study explores how LLMs and LMMs can assist journalistic practice by generating contextualised captions for images accompanying news articles. We conducted experiments using the GoodNews dataset to evaluate the ability of LMMs (BLIP-2, GPT-4v, or LLaVA) to incorporate one of two types of context: entire news articles, or extracted named entities. In addition, we compared their performance to a two-stage pipeline composed of a captioning model (BLIP-2, OFA, or ViT-GPT2) with post-hoc contextualisation with LLMs (GPT-4 or LLaMA). We assess a diversity of models, and we find that while the choice of contextualisation model is a significant factor for the two-stage pipelines, this is not the case in the LMMs, where smaller, open-source models perform well compared to proprietary, GPT-powered ones. Additionally, we found that controlling the amount of provided context enhances performance. These results highlight the limitations of a fully automated approach and underscore the necessity for an interactive, human-in-the-loop strategy.
Authors: Subhasis Dasgupta, Arshi Naaz, Jayeeta Choudhury, Nancy Lahiri
Abstract: Road accidents are quite common in almost every part of the world, and, in majority, fatal accidents are attributed to over speeding of vehicles. The tendency to over speeding is usually tried to be controlled using check points at various parts of the road but not all traffic police have the device to check speed with existing speed estimating devices such as LIDAR based, or Radar based guns. The current project tries to address the issue of vehicle speed estimation with handheld devices such as mobile phones or wearable cameras with network connection to estimate the speed using deep learning frameworks.
Authors: Ryan Dempsey, Jonathan Ethier
Abstract: Path loss prediction for wireless communications is highly dependent on the local environment. Propagation models including clutter information have been shown to significantly increase model accuracy. This paper explores the application of deep learning to satellite imagery to identify environmental clutter types automatically. Recognizing these clutter types has numerous uses, but our main application is to use clutter information to enhance propagation prediction models. Knowing the type of obstruction (tree, building, and further classifications) can improve the prediction accuracy of key propagation metrics such as path loss.
Authors: Ravi Ramamoorthi
Abstract: Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep learning has enabled revolutionary advances in this area, classically known as image-based rendering. However, previous approaches require intractably dense view sampling or provide little or no guidance for how users should sample views of a scene to reliably render high-quality novel views. Local light field fusion proposes an algorithm for practical view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image scene representation, then renders novel views by blending adjacent local light fields. Crucially, we extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. We achieve the perceptual quality of Nyquist rate view sampling while using up to 4000x fewer views. Subsequent developments have led to new scene representations for deep learning with view synthesis, notably neural radiance fields, but the problem of sparse view synthesis from a small number of images has only grown in importance. We reprise some of the recent results on sparse and even single image view synthesis, while posing the question of whether prescriptive sampling guidelines are feasible for the new generation of image-based rendering algorithms.
Authors: Kate \v{C}evora, Ben Glocker, Wenjia Bai
Abstract: Deep learning-based medical image segmentation has seen tremendous progress over the last decade, but there is still relatively little transfer into clinical practice. One of the main barriers is the challenge of domain generalisation, which requires segmentation models to maintain high performance across a wide distribution of image data. This challenge is amplified by the many factors that contribute to the diverse appearance of medical images, such as acquisition conditions and patient characteristics. The impact of shifting patient characteristics such as age and sex on segmentation performance remains relatively under-studied, especially for abdominal organs, despite that this is crucial for ensuring the fairness of the segmentation model. We perform the first study to determine the impact of population shift with respect to age and sex on abdominal CT image segmentation, by leveraging two large public datasets, and introduce a novel metric to quantify the impact. We find that population shift is a challenge similar in magnitude to cross-dataset shift for abdominal organ segmentation, and that the effect is asymmetric and dataset-dependent. We conclude that dataset diversity in terms of known patient characteristics is not necessarily equivalent to dataset diversity in terms of image features. This implies that simple population matching to ensure good generalisation and fairness may be insufficient, and we recommend that fairness research should be directed towards better understanding and quantifying medical image dataset diversity in terms of performance-relevant characteristics such as organ morphology.
Authors: Danlu Chen, Freda Shi, Aditi Agarwal, Jacobo Myerston, Taylor Berg-Kirkpatrick
Abstract: Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an extremely labor intensive process that requires expert knowledge. At present, a large portion of logographic data persists in a purely visual form due to the absence of transcription -- this issue poses a bottleneck for researchers seeking to apply NLP toolkits to study ancient logographic languages: most of the relevant data are images of writing. This paper investigates whether direct processing of visual representations of language offers a potential solution. We introduce LogogramNLP, the first benchmark enabling NLP analysis of ancient logographic languages, featuring both transcribed and visual datasets for four writing systems along with annotations for tasks like classification, translation, and parsing. Our experiments compare systems that employ recent visual and text encoding strategies as backbones. The results demonstrate that visual representations outperform textual representations for some investigated tasks, suggesting that visual processing pipelines may unlock a large amount of cultural heritage data of logographic languages for NLP-based analyses.
Authors: {\L}ukasz Borchmann, Micha{\l} Pietruszka, Wojciech Ja\'skowski, Dawid Jurkiewicz, Piotr Halama, Pawe{\l} J\'oziak, {\L}ukasz Garncarek, Pawe{\l} Liskowski, Karolina Szyndler, Andrzej Gretkowski, Julita O{\l}tusek, Gabriela Nowakowska, Artur Zaw{\l}ocki, {\L}ukasz Duhr, Pawe{\l} Dyda, Micha{\l} Turski
Abstract: The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments.
Authors: Shouchang Guo, Valentin Deschaintre, Douglas Noll, Arthur Roullier
Abstract: We present a novel U-Attention vision Transformer for universal texture synthesis. We exploit the natural long-range dependencies enabled by the attention mechanism to allow our approach to synthesize diverse textures while preserving their structures in a single inference. We propose a hierarchical hourglass backbone that attends to the global structure and performs patch mapping at varying scales in a coarse-to-fine-to-coarse stream. Completed by skip connection and convolution designs that propagate and fuse information at different scales, our hierarchical U-Attention architecture unifies attention to features from macro structures to micro details, and progressively refines synthesis results at successive stages. Our method achieves stronger 2$\times$ synthesis than previous work on both stochastic and structured textures while generalizing to unseen textures without fine-tuning. Ablation studies demonstrate the effectiveness of each component of our architecture.
Authors: Qiaomu Miao, Sinhwa Kang, Stacy Marsella, Steve DiPaola, Chao Wang, Ari Shapiro
Abstract: There is strong interest in the generation of synthetic video imagery of people talking for various purposes, including entertainment, communication, training, and advertisement. With the development of deep fake generation models, synthetic video imagery will soon be visually indistinguishable to the naked eye from a naturally capture video. In addition, many methods are continuing to improve to avoid more careful, forensic visual analysis. Some deep fake videos are produced through the use of facial puppetry, which directly controls the head and face of the synthetic image through the movements of the actor, allow the actor to 'puppet' the image of another. In this paper, we address the question of whether one person's movements can be distinguished from the original speaker by controlling the visual appearance of the speaker but transferring the behavior signals from another source. We conduct a study by comparing synthetic imagery that: 1) originates from a different person speaking a different utterance, 2) originates from the same person speaking a different utterance, and 3) originates from a different person speaking the same utterance. Our study shows that synthetic videos in all three cases are seen as less real and less engaging than the original source video. Our results indicate that there could be a behavioral signature that is detectable from a person's movements that is separate from their visual appearance, and that this behavioral signature could be used to distinguish a deep fake from a properly captured video.
Authors: Yue Han, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Yong Liu, Lu Qi, Xiangtai Li, Ming-Hsuan Yang
Abstract: Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses novel class objects; 2) Dual-branch models require complex spatial correlation strategies to prevent spatial information loss when generating class prototypes. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS and related tasks. Our three main contributions are: 1) A novel transformer-based baseline that avoids overfitting, offering a new direction for FSIS; 2) Demonstrating that support object queries encode key factors after base training, allowing query features to be enhanced twice at both feature and query levels using simple cross-attention, thus avoiding complex spatial correlation interaction; 3) Introducing a class-enhanced base knowledge distillation loss to address the issue of DETR-like models struggling with incremental settings due to the input projection layer, enabling easy extension to incremental FSIS. Extensive experimental evaluations on the COCO dataset under three FSIS settings demonstrate that our method performs favorably against existing approaches across different shots, \eg, $+8.2/+9.4$ performance gain over state-of-the-art methods with 10/30-shots. Source code and models will be available at https://github.com/hanyue1648/RefT.
Authors: Egor Chistov, Nikita Alutis, Dmitriy Vatolin
Abstract: Stereoscopic videos can contain color mismatches between the left and right views due to minor variations in camera settings, lenses, and even object reflections captured from different positions. The presence of color mismatches can lead to viewer discomfort and headaches. This problem can be solved by transferring color between stereoscopic views, but traditional methods often lack quality, while neural-network-based methods can easily overfit on artificial data. The scarcity of stereoscopic videos with real-world color mismatches hinders the evaluation of different methods' performance. Therefore, we filmed a video dataset, which includes both distorted frames with color mismatches and ground-truth data, using a beam-splitter. Our second contribution is a deep multiscale neural network that solves the color-mismatch-correction task by leveraging stereo correspondences. The experimental results demonstrate the effectiveness of the proposed method on a conventional dataset, but there remains room for improvement on challenging real-world data.
Authors: Tianhao Lin
Abstract: Object detection has been used in a wide range of industries. For example, in autonomous driving, the task of object detection is to accurately and efficiently identify and locate a large number of predefined classes of object instances (vehicles, pedestrians, traffic signs, etc.) from videos of roads. In robotics, the industry robot needs to recognize specific machine elements. In the security field, the camera should accurately recognize each face of people. With the wide application of deep learning, the accuracy and efficiency of object detection have been greatly improved, but object detection based on deep learning still faces challenges. Different applications of object detection have different requirements, including highly accurate detection, multi-category object detection, real-time detection, robustness to occlusions, etc. To address the above challenges, based on extensive literature research, this paper analyzes methods for improving and optimizing mainstream object detection algorithms from the perspective of evolution of one-stage and two-stage object detection algorithms. Furthermore, this article proposes methods for improving object detection accuracy from the perspective of changing receptive fields. The new model is based on the original YOLOv5 (You Look Only Once) with some modifications. The structure of the head part of YOLOv5 is modified by adding asymmetrical pooling layers. As a result, the accuracy of the algorithm is improved while ensuring the speed. The performances of the new model in this article are compared with original YOLOv5 model and analyzed from several parameters. And the evaluation of the new model is presented in four situations. Moreover, the summary and outlooks are made on the problems to be solved and the research directions in the future.
Authors: Linli Yao, Yuanmeng Zhang, Ziheng Wang, Xinglin Hou, Tiezheng Ge, Yuning Jiang, Xu Sun, Qin Jin
Abstract: Automatically narrating videos in natural language complying with user requests, i.e. Controllable Video Captioning task, can help people manage massive videos with desired intentions. However, existing works suffer from two shortcomings: 1) the control signal is single-grained which can not satisfy diverse user intentions; 2) the video description is generated in a single round which can not be further edited to meet dynamic needs. In this paper, we propose a novel \textbf{V}ideo \textbf{C}aption \textbf{E}diting \textbf{(VCE)} task to automatically revise an existing video description guided by multi-grained user requests. Inspired by human writing-revision habits, we design the user command as a pivotal triplet \{\textit{operation, position, attribute}\} to cover diverse user needs from coarse-grained to fine-grained. To facilitate the VCE task, we \textit{automatically} construct an open-domain benchmark dataset named VATEX-EDIT and \textit{manually} collect an e-commerce dataset called EMMAD-EDIT. We further propose a specialized small-scale model (i.e., OPA) compared with two generalist Large Multi-modal Models to perform an exhaustive analysis of the novel task. For evaluation, we adopt comprehensive metrics considering caption fluency, command-caption consistency, and video-caption alignment. Experiments reveal the task challenges of fine-grained multi-modal semantics understanding and processing. Our datasets, codes, and evaluation tools are available at https://github.com/yaolinli/VCE.
Authors: Yulong Dou, Lanzhuju Mei, Dinggang Shen, Zhiming Cui
Abstract: Orthodontics focuses on rectifying misaligned teeth (i.e., malocclusions), affecting both masticatory function and aesthetics. However, orthodontic treatment often involves complex, lengthy procedures. As such, generating a 2D photograph depicting aligned teeth prior to orthodontic treatment is crucial for effective dentist-patient communication and, more importantly, for encouraging patients to accept orthodontic intervention. In this paper, we propose a 3D structure-guided tooth alignment network that takes 2D photographs as input (e.g., photos captured by smartphones) and aligns the teeth within the 2D image space to generate an orthodontic comparison photograph featuring aesthetically pleasing, aligned teeth. Notably, while the process operates within a 2D image space, our method employs 3D intra-oral scanning models collected in clinics to learn about orthodontic treatment, i.e., projecting the pre- and post-orthodontic 3D tooth structures onto 2D tooth contours, followed by a diffusion model to learn the mapping relationship. Ultimately, the aligned tooth contours are leveraged to guide the generation of a 2D photograph with aesthetically pleasing, aligned teeth and realistic textures. We evaluate our network on various facial photographs, demonstrating its exceptional performance and strong applicability within the orthodontic industry.
Authors: Oriane Sim\'eoni, \'Eloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick P\'erez
Abstract: 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.
URLs: https://github.com/valeoai/Awesome-Unsupervised-Object-Localization.
Authors: McKell Woodland, Austin Castelo, Mais Al Taie, Jessica Albuquerque Marques Silva, Mohamed Eltaher, Frank Mohn, Alexander Shieh, Suprateek Kundu, Joshua P. Yung, Ankit B. Patel, Kristy K. Brock
Abstract: Fr\'echet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images. Our study challenges this practice by demonstrating that ImageNet-based extractors are more consistent and aligned with human judgment than their RadImageNet counterparts. We evaluated sixteen StyleGAN2 networks across four medical imaging modalities and four data augmentation techniques with Fr\'echet distances (FDs) computed using eleven ImageNet or RadImageNet-trained feature extractors. Comparison with human judgment via visual Turing tests revealed that ImageNet-based extractors produced rankings consistent with human judgment, with the FD derived from the ImageNet-trained SwAV extractor significantly correlating with expert evaluations. In contrast, RadImageNet-based rankings were volatile and inconsistent with human judgment. Our findings challenge prevailing assumptions, providing novel evidence that medical image-trained feature extractors do not inherently improve FDs and can even compromise their reliability. Our code is available at https://github.com/mckellwoodland/fid-med-eval.
Authors: Jian Gao, Chun Gu, Youtian Lin, Zhihao Li, Hao Zhu, Xun Cao, Li Zhang, Yao Yao
Abstract: In this paper, we present a novel differentiable point-based rendering framework to achieve photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla 3D Gaussians by associating extra properties, including normal vectors, BRDF parameters, and incident lighting from various directions. From a collection of multi-view images, the 3D scene is optimized through 3D Gaussian Splatting while BRDF and lighting are decomposed by physically based differentiable rendering. To produce plausible shadow effects in photo-realistic relighting, we introduce an innovative point-based ray tracing with the bounding volume hierarchies for efficient visibility pre-computation. Extensive experiments demonstrate our improved BRDF estimation, novel view synthesis and relighting results compared to state-of-the-art approaches. The proposed framework showcases the potential to revolutionize the mesh-based graphics pipeline with a point-based pipeline enabling editing, tracing, and relighting.
Authors: Bin-Shih Wu, Hong-En Chen, Sheng-Yu Huang, Yu-Chiang Frank Wang
Abstract: Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based models would still be desirable for fast 3D generation. In this work, we propose Triplane Attention for text-guided 3D generation (TPA3D), an end-to-end trainable GAN-based deep learning model for fast text-to-3D generation. With only 3D shape data and their rendered 2D images observed during training, our TPA3D is designed to retrieve detailed visual descriptions for synthesizing the corresponding 3D mesh data. This is achieved by the proposed attention mechanisms on the extracted sentence and word-level text features. In our experiments, we show that TPA3D generates high-quality 3D textured shapes aligned with fine-grained descriptions, while impressive computation efficiency can be observed.
Authors: Jiachen Lu, Ze Huang, Zeyu Yang, Jiahui Zhang, Li Zhang
Abstract: Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data. Due to the limitations in diversity and challenges in handling lighting conditions, traditional rendering-based methods are increasingly being supplanted by diffusion-based methods. However, a significant challenge in diffusion-based methods is ensuring that the generated sensor data preserve both intra-world consistency and inter-sensor coherence. To address these challenges, we combine an additional explicit world volume and propose the World Volume-aware Multi-camera Driving Scene Generator (WoVoGen). This system is specifically designed to leverage 4D world volume as a foundational element for video generation. Our model operates in two distinct phases: (i) envisioning the future 4D temporal world volume based on vehicle control sequences, and (ii) generating multi-camera videos, informed by this envisioned 4D temporal world volume and sensor interconnectivity. The incorporation of the 4D world volume empowers WoVoGen not only to generate high-quality street-view videos in response to vehicle control inputs but also to facilitate scene editing tasks.
Authors: Yabo Chen, Jiemin Fang, Yuyang Huang, Taoran Yi, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian
Abstract: Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a single-view source image and the camera pose as condition information. However, due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views, especially for complex objects. To tackle this issue, we propose to supply more condition information for the generation model but in a self-prompt way. A cascade framework is constructed with two Zero-1-to-3 models, named Cascade-Zero123, which progressively extract 3D information from the source image. Specifically, several nearby views are first generated by the first model and then fed into the second-stage model along with the source image as generation conditions. With amplified self-prompted condition images, our Cascade-Zero123 generates more consistent novel-view images than Zero-1-to-3. Experiment results demonstrate remarkable promotion, especially for various complex and challenging scenes, involving insects, humans, transparent objects, and stacked multiple objects etc. More demos and code are available at https://cascadezero123.github.io.
Authors: Yifeng Ma, Shiwei Zhang, Jiayu Wang, Xiang Wang, Yingya Zhang, Zhidong Deng
Abstract: Emotional talking head generation has attracted growing attention. Previous methods, which are mainly GAN-based, still struggle to consistently produce satisfactory results across diverse emotions and cannot conveniently specify personalized emotions. In this work, we leverage powerful diffusion models to address the issue and propose DreamTalk, a framework that employs meticulous design to unlock the potential of diffusion models in generating emotional talking heads. Specifically, DreamTalk consists of three crucial components: a denoising network, a style-aware lip expert, and a style predictor. The diffusion-based denoising network can consistently synthesize high-quality audio-driven face motions across diverse emotions. To enhance lip-motion accuracy and emotional fullness, we introduce a style-aware lip expert that can guide lip-sync while preserving emotion intensity. To more conveniently specify personalized emotions, a diffusion-based style predictor is utilized to predict the personalized emotion directly from the audio, eliminating the need for extra emotion reference. By this means, DreamTalk can consistently generate vivid talking faces across diverse emotions and conveniently specify personalized emotions. Extensive experiments validate DreamTalk's effectiveness and superiority. The code is available at https://github.com/ali-vilab/dreamtalk.
Authors: Hefeng Wu, Guangzhi Ye, Ziyang Zhou, Ling Tian, Qing Wang, Liang Lin
Abstract: Learning to recognize novel concepts from just a few image samples is very challenging as the learned model is easily overfitted on the few data and results in poor generalizability. One promising but underexplored solution is to compensate the novel classes by generating plausible samples. However, most existing works of this line exploit visual information only, rendering the generated data easy to be distracted by some challenging factors contained in the few available samples. Being aware of the semantic information in the textual modality that reflects human concepts, this work proposes a novel framework that exploits semantic relations to guide dual-view data hallucination for few-shot image recognition. The proposed framework enables generating more diverse and reasonable data samples for novel classes through effective information transfer from base classes. Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes. Meanwhile, a prototype-view data hallucination module exploits semantic-aware measure to estimate the prototype of a novel class and the associated distribution from the few samples, which thereby harvests the prototype as a more stable sample and enables resampling a large number of samples. We conduct extensive experiments and comparisons with state-of-the-art methods on several popular few-shot benchmarks to verify the effectiveness of the proposed framework.
Authors: Xianfu Cheng, Weixiao Zhou, Xiang Li, Jian Yang, Hang Zhang, Tao Sun, Wei Zhang, Yuying Mai, Tongliang Li, Xiaoming Chen, Zhoujun Li
Abstract: Scene Text Recognition (STR) is an important and challenging upstream task for building structured information databases, that involves recognizing text within images of natural scenes. Although current state-of-the-art (SOTA) models for STR exhibit high performance, they typically suffer from low inference efficiency due to their reliance on hybrid architectures comprised of visual encoders and sequence decoders. In this work, we propose a VIsion Permutable extractor for fast and efficient Scene Text Recognition (SVIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR. Specifically, SVIPTR leverages a visual-semantic extractor with a pyramid structure, characterized by the Permutation and combination of local and global self-attention layers. This design results in a lightweight and efficient model and its inference is insensitive to input length. Extensive experimental results on various standard datasets for both Chinese and English scene text recognition validate the superiority of SVIPTR. Notably, the SVIPTR-T (Tiny) variant delivers highly competitive accuracy on par with other lightweight models and achieves SOTA inference speeds. Meanwhile, the SVIPTR-L (Large) attains SOTA accuracy in single-encoder-type models, while maintaining a low parameter count and favorable inference speed. Our proposed method provides a compelling solution for the STR challenge, which greatly benefits real-world applications requiring fast and efficient STR. The code is publicly available at https://github.com/cxfyxl/VIPTR.
Authors: Linrui Tian, Qi Wang, Bang Zhang, Liefeng Bo
Abstract: In this work, we tackle the challenge of enhancing the realism and expressiveness in talking head video generation by focusing on the dynamic and nuanced relationship between audio cues and facial movements. We identify the limitations of traditional techniques that often fail to capture the full spectrum of human expressions and the uniqueness of individual facial styles. To address these issues, we propose EMO, a novel framework that utilizes a direct audio-to-video synthesis approach, bypassing the need for intermediate 3D models or facial landmarks. Our method ensures seamless frame transitions and consistent identity preservation throughout the video, resulting in highly expressive and lifelike animations. Experimental results demonsrate that EMO is able to produce not only convincing speaking videos but also singing videos in various styles, significantly outperforming existing state-of-the-art methodologies in terms of expressiveness and realism.
Authors: Shuangjian Li, Tao Zhu, Mingxing Nie, Huansheng Ning, Zhenyu Liu, Liming Chen
Abstract: Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data. This limits their usefulness in many fields such as healthcare and assisted living, where real-time understanding of ongoing and upcoming activities is crucial. This paper introduces P2LHAP, a novel Patch-to-Label Seq2Seq framework that tackles all three tasks in a efficient single-task model. P2LHAP divides sensor data streams into a sequence of "patches", served as input tokens, and outputs a sequence of patch-level activity labels including the predicted future activities. A unique smoothing technique based on surrounding patch labels, is proposed to identify activity boundaries accurately. Additionally, P2LHAP learns patch-level representation by sensor signal channel-independent Transformer encoders and decoders. All channels share embedding and Transformer weights across all sequences. Evaluated on three public datasets, P2LHAP significantly outperforms the state-of-the-art in all three tasks, demonstrating its effectiveness and potential for real-world applications.
Authors: Jiazhi Yang, Shenyuan Gao, Yihang Qiu, Li Chen, Tianyu Li, Bo Dai, Kashyap Chitta, Penghao Wu, Jia Zeng, Ping Luo, Jun Zhang, Andreas Geiger, Yu Qiao, Hongyang Li
Abstract: In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline. To eliminate the restriction of high-cost data collection and empower the generalization ability of our model, we acquire massive data from the web and pair it with diverse and high-quality text descriptions. The resultant dataset accumulates over 2000 hours of driving videos, spanning areas all over the world with diverse weather conditions and traffic scenarios. Inheriting the merits from recent latent diffusion models, our model, dubbed GenAD, handles the challenging dynamics in driving scenes with novel temporal reasoning blocks. We showcase that it can generalize to various unseen driving datasets in a zero-shot manner, surpassing general or driving-specific video prediction counterparts. Furthermore, GenAD can be adapted into an action-conditioned prediction model or a motion planner, holding great potential for real-world driving applications.
Authors: Shuangjian Li, Tao Zhu, Furong Duan, Liming Chen, Huansheng Ning, Christopher Nugent, Yaping Wan
Abstract: Wearable sensor-based human activity recognition (HAR) is a critical research domain in activity perception. However, achieving high efficiency and long sequence recognition remains a challenge. Despite the extensive investigation of temporal deep learning models, such as CNNs, RNNs, and transformers, their extensive parameters often pose significant computational and memory constraints, rendering them less suitable for resource-constrained mobile health applications. This study introduces HARMamba, an innovative light-weight and versatile HAR architecture that combines selective bidirectional State Spaces Model and hardware-aware design. To optimize real-time resource consumption in practical scenarios, HARMamba employs linear recursive mechanisms and parameter discretization, allowing it to selectively focus on relevant input sequences while efficiently fusing scan and recompute operations. The model employs independent channels to process sensor data streams, dividing each channel into patches and appending classification tokens to the end of the sequence. It utilizes position embedding to represent the sequence order. The patch sequence is subsequently processed by HARMamba Block, and the classification head finally outputs the activity category. The HARMamba Block serves as the fundamental component of the HARMamba architecture, enabling the effective capture of more discriminative activity sequence features. HARMamba outperforms contemporary state-of-the-art frameworks, delivering comparable or better accuracy with significantly reducing computational and memory demands. It's effectiveness has been extensively validated on 4 publically available datasets namely PAMAP2, WISDM, UNIMIB SHAR and UCI. The F1 scores of HARMamba on the four datasets are 99.74%, 99.20%, 88.23% and 97.01%, respectively.
Authors: Rudolf Herdt, Maximilian Schmidt, Daniel Otero Baguer, Peter Maa{\ss}
Abstract: In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We evaluate the faithfulness of those methods using insertion and deletion metrics, finding that saliency maps computed in hidden layers perform better compared to both the input layer and GradCAM. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and in-house real-world digital pathology scans of stained tissue samples. Our results show that the checkerboard noise in the gradient gets reduced, resulting in smoother and therefore easier to interpret saliency maps.
Authors: Hanchi Sun, Xiaohong Liu, Xinyang Jiang, Yifei Shen, Dongsheng Li, Xiongkuo Min, Guangtao Zhai
Abstract: This paper focuses on the task of quality enhancement for compressed videos. Although deep network-based video restorers achieve impressive progress, most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. Since the quality degradation of the video is primarily induced by the compression algorithm, a new paradigm is urgently needed for a more ``conscious'' process of quality enhancement. As a result, we propose the Compression-Realized Deep Structural Network (CRDS), introducing three inductive biases aligned with the three primary processes in the classic compression codec, merging the strengths of classical encoder architecture with deep network capabilities. Inspired by the residual extraction and domain transformation process in the codec, a pre-trained Latent Degradation Residual Auto-Encoder is proposed to transform video frames into a latent feature space, and the mutual neighborhood attention mechanism is integrated for precise motion estimation and residual extraction. Furthermore, drawing inspiration from the quantization noise distribution of the codec, CRDS proposes a novel Progressive Denoising framework with intermediate supervision that decomposes the quality enhancement into a series of simpler denoising sub-tasks. Experimental results on datasets like LDV 2.0 and MFQE 2.0 indicate our approach surpasses state-of-the-art models.
Authors: Yan He, Bing Tu, Bo Liu, Jun Li, Antonio Plaza
Abstract: Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual dependencies. However, these architectures suffer from limited receptive fields and quadratic computational complexity, respectively. Fortunately, recent Mamba architectures built upon the State Space Model integrate the advantages of long-range sequence modeling and linear computational efficiency, exhibiting substantial potential in low-dimensional scenarios. Motivated by this, we propose a novel 3D-Spectral-Spatial Mamba (3DSS-Mamba) framework for HSI classification, allowing for global spectral-spatial relationship modeling with greater computational efficiency. Technically, a spectral-spatial token generation (SSTG) module is designed to convert the HSI cube into a set of 3D spectral-spatial tokens. To overcome the limitations of traditional Mamba, which is confined to modeling causal sequences and inadaptable to high-dimensional scenarios, a 3D-Spectral-Spatial Selective Scanning (3DSS) mechanism is introduced, which performs pixel-wise selective scanning on 3D hyperspectral tokens along the spectral and spatial dimensions. Five scanning routes are constructed to investigate the impact of dimension prioritization. The 3DSS scanning mechanism combined with conventional mapping operations forms the 3D-spectral-spatial mamba block (3DMB), enabling the extraction of global spectral-spatial semantic representations. Experimental results and analysis demonstrate that the proposed method outperforms the state-of-the-art methods on HSI classification benchmarks.
Authors: Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang
Abstract: Diffusion-based text-to-image generation models trained on extensive text-image pairs have shown the capacity to generate photorealistic images consistent with textual descriptions. However, a significant limitation of these models is their slow sample generation, which requires iterative refinement through the same network. In this paper, we enhance Score identity Distillation (SiD) by developing long and short classifier-free guidance (LSG) to efficiently distill pretrained Stable Diffusion models without using real training data. SiD aims to optimize a model-based explicit score matching loss, utilizing a score-identity-based approximation alongside the proposed LSG for practical computation. By training exclusively with fake images synthesized with its one-step generator, SiD equipped with LSG rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Specifically, its data-free distillation of Stable Diffusion 1.5 achieves a record low FID of 8.15 on the COCO-2014 validation set, with a CLIP score of 0.304 at an LSG scale of 1.5, and an FID of 9.56 with a CLIP score of 0.313 at an LSG scale of 2. Our code and distilled one-step text-to-image generators are available at https://github.com/mingyuanzhou/SiD-LSG.
Authors: Yuzhou Ji, He Zhu, Junshu Tang, Wuyi Liu, Zhizhong Zhang, Yuan Xie, Xin Tan
Abstract: The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, efficiency and zero-shot ability at the same time with semantics in radiance fields. In this work, we present FastLGS, an approach that supports real-time open-vocabulary query within 3D Gaussian Splatting (3DGS) under high resolution. We propose the semantic feature grid to save multi-view CLIP features which are extracted based on Segment Anything Model (SAM) masks, and map the grids to low dimensional features for semantic field training through 3DGS. Once trained, we can restore pixel-aligned CLIP embeddings through feature grids from rendered features for open-vocabulary queries. Comparisons with other state-of-the-art methods prove that FastLGS can achieve the first place performance concerning both speed and accuracy, where FastLGS is 98x faster than LERF and 4x faster than LangSplat. Meanwhile, experiments show that FastLGS is adaptive and compatible with many downstream tasks, such as 3D segmentation and 3D object inpainting, which can be easily applied to other 3D manipulation systems.
Authors: Da Li, Guoqiang Zhao, Houjun Sun, Jiacheng Bao
Abstract: Multi-baseline SAR 3D imaging faces significant challenges due to data sparsity. In recent years, deep learning techniques have achieved notable success in enhancing the quality of sparse SAR 3D imaging. However, previous work typically rely on full-aperture high-resolution radar images to supervise the training of deep neural networks (DNNs), utilizing only single-modal information from radar data. Consequently, imaging performance is limited, and acquiring full-aperture data for multi-baseline SAR is costly and sometimes impractical in real-world applications. In this paper, we propose a Cross-Modal Reconstruction Network (CMR-Net), which integrates differentiable render and cross-modal supervision with optical images to reconstruct highly sparse multi-baseline SAR 3D images of vehicle targets into visually structured and high-resolution images. We meticulously designed the network architecture and training strategies to enhance network generalization capability. Remarkably, CMR-Net, trained solely on simulated data, demonstrates high-resolution reconstruction capabilities on both publicly available simulation datasets and real measured datasets, outperforming traditional sparse reconstruction algorithms based on compressed sensing and other learning-based methods. Additionally, using optical images as supervision provides a cost-effective way to build training datasets, reducing the difficulty of method dissemination. Our work showcases the broad prospects of deep learning in multi-baseline SAR 3D imaging and offers a novel path for researching radar imaging based on cross-modal learning theory.
Authors: Yufan He, Pengfei Guo, Yucheng Tang, Andriy Myronenko, Vishwesh Nath, Ziyue Xu, Dong Yang, Can Zhao, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu, Wenqi Li
Abstract: Medical image segmentation is a core component of precision medicine, and 3D computed tomography (CT) is one of the most important imaging techniques. A highly accurate and clinically applicable segmentation foundation model will greatly facilitate clinicians and researchers using CT images. Although existing foundation models have attracted great interest, none are adequate for 3D CT, either because they lack accurate automatic segmentation for large cohort analysis or the ability to segment novel classes. An ideal segmentation solution should possess two features: accurate out-of-the-box performance covering major organ classes, and effective adaptation or zero-shot ability to novel structures. To achieve this goal, we introduce Versatile Imaging SegmenTation and Annotation model (VISTA3D). VISTA3D is trained systematically on 11454 volumes and provides accurate out-of-the-box segmentation for 127 common types of human anatomical structures and various lesions. Additionally, VISTA3D supports 3D interactive segmentation, allowing convenient editing of automatic results and achieving state-of-the-art annotation results on unseen classes. The novel model design and training recipe represent a promising step toward developing a versatile medical image foundation model and will serve as a valuable foundation for CT image analysis. Code and model weights are available at https://github.com/Project-MONAI/VISTA
Authors: Andrea Burns, Kate Saenko, Bryan A. Plummer
Abstract: Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current UI and local action taken. Our approach requires joint reasoning over elements and entire screens, resulting in improved UI features: on generation tasks, UI agents trained with Textual Foresight outperform state-of-the-art by 2% with 28x fewer images. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning. OpenApp enables new baselines, and we find Textual Foresight improves average task performance over them by 5.7% while having access to 2x less data.
Authors: Fengyi Zhang, Yadan Luo, Tianjun Zhang, Lin Zhang, Zi Huang
Abstract: The field of novel-view synthesis has recently witnessed the emergence of 3D Gaussian Splatting, which represents scenes in a point-based manner and renders through rasterization. This methodology, in contrast to Radiance Fields that rely on ray tracing, demonstrates superior rendering quality and speed. However, the explicit and unstructured nature of 3D Gaussians poses a significant storage challenge, impeding its broader application. To address this challenge, we introduce the Gaussian-Forest modeling framework, which hierarchically represents a scene as a forest of hybrid 3D Gaussians. Each hybrid Gaussian retains its unique explicit attributes while sharing implicit ones with its sibling Gaussians, thus optimizing parameterization with significantly fewer variables. Moreover, adaptive growth and pruning strategies are designed, ensuring detailed representation in complex regions and a notable reduction in the number of required Gaussians. Extensive experiments demonstrate that Gaussian-Forest not only maintains comparable speed and quality but also achieves a compression rate surpassing 10 times, marking a significant advancement in efficient scene modeling. Codes will be available at https://github.com/Xian-Bei/GaussianForest.
Authors: Yufan Zhou, Ruiyi Zhang, Kaizhi Zheng, Nanxuan Zhao, Jiuxiang Gu, Zichao Wang, Xin Eric Wang, Tong Sun
Abstract: In subject-driven text-to-image generation, recent works have achieved superior performance by training the model on synthetic datasets containing numerous image pairs. Trained on these datasets, generative models can produce text-aligned images for specific subject from arbitrary testing image in a zero-shot manner. They even outperform methods which require additional fine-tuning on testing images. However, the cost of creating such datasets is prohibitive for most researchers. To generate a single training pair, current methods fine-tune a pre-trained text-to-image model on the subject image to capture fine-grained details, then use the fine-tuned model to create images for the same subject based on creative text prompts. Consequently, constructing a large-scale dataset with millions of subjects can require hundreds of thousands of GPU hours. To tackle this problem, we propose Toffee, an efficient method to construct datasets for subject-driven editing and generation. Specifically, our dataset construction does not need any subject-level fine-tuning. After pre-training two generative models, we are able to generate infinite number of high-quality samples. We construct the first large-scale dataset for subject-driven image editing and generation, which contains 5 million image pairs, text prompts, and masks. Our dataset is 5 times the size of previous largest dataset, yet our cost is tens of thousands of GPU hours lower. To test the proposed dataset, we also propose a model which is capable of both subject-driven image editing and generation. By simply training the model on our proposed dataset, it obtains competitive results, illustrating the effectiveness of the proposed dataset construction framework.
Authors: Dunyuan Xu, Xi Wang, Jingyang Zhang, Pheng-Ann Heng
Abstract: The ability to learn sequentially from different data sites is crucial for a deep network in solving practical medical image diagnosis problems due to privacy restrictions and storage limitations. However, adapting on incoming site leads to catastrophic forgetting on past sites and decreases generalizablity on unseen sites. Existing Continual Learning (CL) and Domain Generalization (DG) methods have been proposed to solve these two challenges respectively, but none of them can address both simultaneously. Recognizing this limitation, this paper proposes a novel training paradigm, learning towards Synchronous Memorizability and Generalizability (SMG-Learning). To achieve this, we create the orientational gradient alignment to ensure memorizability on previous sites, and arbitrary gradient alignment to enhance generalizability on unseen sites. This approach is named as Parallel Gradient Alignment (PGA). Furthermore, we approximate the PGA as dual meta-objectives using the first-order Taylor expansion to reduce computational cost of aligning gradients. Considering that performing gradient alignments, especially for previous sites, is not feasible due to the privacy constraints, we design a Site-Modulated Diffusion (SMD) model to generate images with site-specific learnable prompts, replaying images have similar data distributions as previous sites. We evaluate our method on two medical image segmentation tasks, where data from different sites arrive sequentially. Experimental results show that our method efficiently enhances both memorizability and generalizablity better than other state-of-the-art methods, delivering satisfactory performance across all sites. Our code will be available at: https://github.com/dyxu-cuhkcse/SMG-Learning.
Authors: Xiaozhong Ji, Chuming Lin, Zhonggan Ding, Ying Tai, Junwei Zhu, Xiaobin Hu, Donghao Luo, Yanhao Ge, Chengjie Wang
Abstract: Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity expression-to-face renderer. In the first component, we consider both identity and intra-personal variation features related to speaking lip movements. By incorporating cross-modal attention on the enriched facial priors, we can effectively align lip movements with audio, thus attaining greater precision in expression prediction. In the second component, we design a lightweight facial identity alignment (FIA) module which includes a lip-shape control structure and a face texture reference structure. This novel design allows us to generate fine details in real-time, without depending on sophisticated and inefficient feature alignment modules. Our experimental results, both quantitative and qualitative, on public datasets demonstrate the clear advantages of our method in terms of lip-speech synchronization and generation quality. Furthermore, our method is efficient and requires fewer computational resources, making it well-suited to meet the needs of practical applications.
Authors: Arthur Aubret, C\'eline Teuli\`ere, Jochen Triesch
Abstract: Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning. When learning about an object, humans often purposefully turn or move around objects and research suggests that these interactions can substantially enhance their learning. Here we explore whether such object-related actions can boost SSL. For this, we extract the actions performed to change from one ego-centric view of an object to another in four video datasets. We then introduce a new loss function to learn visual and action embeddings by aligning the performed action with the representations of two images extracted from the same clip. This permits the performed actions to structure the latent visual representation. Our experiments show that our method consistently outperforms previous methods on downstream category recognition. In our analysis, we find that the observed improvement is associated with a better viewpoint-wise alignment of different objects from the same category. Overall, our work demonstrates that embodied interactions with objects can improve SSL of object categories.
Authors: Yechan Kim, JongHyun Park, SooYeon Kim, Moongu Jeon
Abstract: Recently, numerous methods have achieved impressive performance in remote sensing object detection, relying on convolution or transformer architectures. Such detectors typically have a feature backbone to extract useful features from raw input images. For the remote sensing domain, a common practice among current detectors is to initialize the backbone with pre-training on ImageNet consisting of natural scenes. Fine-tuning the backbone is then typically required to generate features suitable for remote-sensing images. However, this could hinder the extraction of basic visual features in long-term training, thus restricting performance improvement. To mitigate this issue, we propose a novel method named DBF (Dynamic Backbone Freezing) for feature backbone fine-tuning on remote sensing object detection. Our method aims to handle the dilemma of whether the backbone should extract low-level generic features or possess specific knowledge of the remote sensing domain, by introducing a module called 'Freezing Scheduler' to dynamically manage the update of backbone features during training. Extensive experiments on DOTA and DIOR-R show that our approach enables more accurate model learning while substantially reducing computational costs. Our method can be seamlessly adopted without additional effort due to its straightforward design.
Authors: Yike Zhang, Dingjie Su, Eduardo Davalos, Jack H. Noble
Abstract: Cochlear Implant (CI) procedures involve inserting an array of electrodes into the cochlea located inside the inner ear. Mastoidectomy is a surgical procedure that uses a high-speed drill to remove part of the mastoid region of the temporal bone, providing safe access to the cochlea through the middle and inner ear. We aim to develop an intraoperative navigation system that registers plans created using 3D preoperative Computerized Tomography (CT) volumes with the 2D surgical microscope view. Herein, we propose a method to synthesize the mastoidectomy volume using only the preoperative CT scan, where the mastoid is intact. We introduce an unsupervised learning framework designed to synthesize mastoidectomy. For model training purposes, this method uses postoperative CT scans to avoid manual data cleaning or labeling, even when the region removed during mastoidectomy is visible but affected by metal artifacts, low signal-to-noise ratio, or electrode wiring. Our approach estimates mastoidectomy regions with a mean dice score of 70.0%. This approach represents a major step forward for CI intraoperative navigation by predicting realistic mastoidectomy-removed regions in preoperative planning that can be used to register the pre-surgery plan to intraoperative microscopy.
Authors: Chengan He, Xin Sun, Zhixin Shu, Fujun Luan, S\"oren Pirk, Jorge Alejandro Amador Herrera, Dominik L. Michels, Tuanfeng Y. Wang, Meng Zhang, Holly Rushmeier, Yi Zhou
Abstract: We present Perm, a learned parametric model of human 3D hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair shape and local strand details, we propose to disentangle them using a PCA-based strand representation in the frequency domain, thereby allowing more precise editing and output control. Specifically, we leverage our strand representation to fit and decompose hair geometry textures into low- to high-frequency hair structures. These decomposed textures are later parameterized with different generative models, emulating common stages in the hair modeling process. We conduct extensive experiments to validate the architecture design of \textsc{Perm}, and finally deploy the trained model as a generic prior to solve task-agnostic problems, further showcasing its flexibility and superiority in tasks such as 3D hair parameterization, hairstyle interpolation, single-view hair reconstruction, and hair-conditioned image generation. Our code, data, and supplemental can be found at our project page: https://cs.yale.edu/homes/che/projects/perm/
Authors: Yushi Huang, Ruihao Gong, Xianglong Liu, Jing Liu, Yuhang Li, Jiwen Lu, Dacheng Tao
Abstract: The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues. However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising. Typically, each time-step is encoded into a hypersensitive temporal feature by several modules. Despite this, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory, as well as reduced compression efficiency. To address these challenges, we introduce a novel quantization framework that includes three strategies: 1) TIB-based Maintenance: Based on our innovative Temporal Information Block (TIB) definition, Temporal Information-aware Reconstruction (TIAR) and Finite Set Calibration (FSC) are developed to efficiently align original temporal features. 2) Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3) Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection between the two maintenance strategies for further disturbance reduction. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets, diffusion models and hardware confirms our superior performance and acceleration..
Authors: Fangming Cui, Xun Yang, Chao Wu, Liang Xiao, Xinmei Tian
Abstract: Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization performance due to the invalidity of the learned text embeddings for unseen tasks. A straightforward approach to bridge this gap is to freeze the text embeddings in prompts, which results in a lack of capacity to adapt VLMs for downstream tasks. To address this dilemma, we propose a paradigm called EnPrompt with a novel External Layer (EnLa). Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks. The learnable external layer is built upon valid embeddings of pre-trained CLIP. This design considers the balance of learning capabilities between the two branches. To align the textual and visual features, we propose a novel two-pronged approach: i) we introduce the optimal transport as the discrepancy metric to align the vision and text modalities, and ii) we introduce a novel strengthening feature to enhance the interaction between these two modalities. Four representative experiments (i.e., base-to-novel generalization, few-shot learning, cross-dataset generalization, domain shifts generalization) across 15 datasets demonstrate that our method outperforms the existing prompt learning method.
Authors: Chaolei Tan, Zihang Lin, Junfu Pu, Zhongang Qi, Wei-Yi Pei, Zhi Qu, Yexin Wang, Ying Shan, Wei-Shi Zheng, Jian-Fang Hu
Abstract: Video grounding is a fundamental problem in multimodal content understanding, aiming to localize specific natural language queries in an untrimmed video. However, current video grounding datasets merely focus on simple events and are either limited to shorter videos or brief sentences, which hinders the model from evolving toward stronger multimodal understanding capabilities. To address these limitations, we present a large-scale video grounding dataset named SynopGround, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-written synopses. Each paragraph in the synopsis serves as a language query and is manually annotated with precise temporal boundaries in the long video. These paragraph queries are tightly correlated to each other and contain a wealth of abstract expressions summarizing video storylines and specific descriptions portraying event details, which enables the model to learn multimodal perception on more intricate concepts over longer context dependencies. Based on the dataset, we further introduce a more complex setting of video grounding dubbed Multi-Paragraph Video Grounding (MPVG), which takes as input multiple paragraphs and a long video for grounding each paragraph query to its temporal interval. In addition, we propose a novel Local-Global Multimodal Reasoner (LGMR) to explicitly model the local-global structures of long-term multimodal inputs for MPVG. Our method provides an effective baseline solution to the multi-paragraph video grounding problem. Extensive experiments verify the proposed model's effectiveness as well as its superiority in long-term multi-paragraph video grounding over prior state-of-the-arts. Dataset and code are publicly available. Project page: https://synopground.github.io/.
Authors: Jing Wu, Rixiang Ni, Feng Huang, Zhaobing Qiu, Liqiong Chen, Changhai Luo, Yunxiang Li, Youli Li
Abstract: Infrared small target detection (IRSTD) tasks are extremely challenging for two main reasons: 1) it is difficult to obtain accurate labelling information that is critical to existing methods, and 2) infrared (IR) small target information is easily lost in deep networks. To address these issues, we propose a single-point supervised high-resolution dynamic network (SSHD-Net). In contrast to existing methods, we achieve state-of-the-art (SOTA) detection performance using only single-point supervision. Specifically, we first design a high-resolution cross-feature extraction module (HCEM), that achieves bi-directional feature interaction through stepped feature cascade channels (SFCC). It balances network depth and feature resolution to maintain deep IR small-target information. Secondly, the effective integration of global and local features is achieved through the dynamic coordinate fusion module (DCFM), which enhances the anti-interference ability in complex backgrounds. In addition, we introduce the high-resolution multilevel residual module (HMRM) to enhance the semantic information extraction capability. Finally, we design the adaptive target localization detection head (ATLDH) to improve detection accuracy. Experiments on the publicly available datasets NUDT-SIRST and IRSTD-1k demonstrate the effectiveness of our method. Compared to other SOTA methods, our method can achieve better detection performance with only a single point of supervision.
Authors: He Wang, Lei Xie
Abstract: This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP (Team 237) in the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), engaging in all four tracks, including the fixed and open tracks of Single-Speaker VSR Task and Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multiscale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR model adopts an end-to-end architecture with joint CTC/attention loss, introducing Enhanced ResNet3D visual frontend, E-Branchformer encoder, and Bi-directional Transformer decoder. Our approach yields a 30.47% CER for the Single-Speaker Task and 34.30% CER for the Multi-Speaker Task, securing second place in the open track of the Single-Speaker Task and first place in the other three tracks.
Authors: He Yao, Yongjun Zhang, Huachun Jian, Li Zhang, Ruzhong Cheng
Abstract: The significance of background information is frequently overlooked in contemporary research concerning channel attention mechanisms. This study addresses the issue of suboptimal single-spectral nighttime pedestrian detection performance under low-light conditions by incorporating background information into the channel attention mechanism. Despite numerous studies focusing on the development of efficient channel attention mechanisms, the relevance of background information has been largely disregarded. By adopting a contrast learning approach, we reexamine channel attention with regard to pedestrian objects and background information for nighttime pedestrian detection, resulting in the proposed Fore-Background Contrast Attention (FBCA). FBCA possesses two primary attributes: (1) channel descriptors form remote dependencies with global spatial feature information; (2) the integration of background information enhances the distinction between channels concentrating on low-light pedestrian features and those focusing on background information. Consequently, the acquired channel descriptors exhibit a higher semantic level and spatial accuracy. Experimental outcomes demonstrate that FBCA significantly outperforms existing methods in single-spectral nighttime pedestrian detection, achieving state-of-the-art results on the NightOwls and TJU-DHD-pedestrian datasets. Furthermore, this methodology also yields performance improvements for the multispectral LLVIP dataset. These findings indicate that integrating background information into the channel attention mechanism effectively mitigates detector performance degradation caused by illumination factors in nighttime scenarios.
Authors: Gyeongho Kim
Abstract: This work proposes an overview of the recent semi-supervised learning approaches and related works. Despite the remarkable success of neural networks in various applications, there exist a few formidable constraints, including the need for a large amount of labeled data. Therefore, semi-supervised learning, which is a learning scheme in which scarce labels and a larger amount of unlabeled data are utilized to train models (e.g., deep neural networks), is getting more important. Based on the key assumptions of semi-supervised learning, which are the manifold assumption, cluster assumption, and continuity assumption, the work reviews the recent semi-supervised learning approaches. In particular, the methods in regard to using deep neural networks in a semi-supervised learning setting are primarily discussed. In addition, the existing works are first classified based on the underlying idea and explained, then the holistic approaches that unify the aforementioned ideas are detailed.
Authors: Johannes Thalhammer, Manuel Schultheiss, Tina Dorosti, Tobias Lasser, Franz Pfeiffer, Daniela Pfeiffer, Florian Schaff
Abstract: This is a preprint. The latest version has been published here: https://pubs.rsna.org/doi/10.1148/ryai.230275 Purpose: Sparse-view computed tomography (CT) is an effective way to reduce dose by lowering the total number of views acquired, albeit at the expense of image quality, which, in turn, can impact the ability to detect diseases. We explore deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Methods: We trained a U-Net for artefact reduction on simulated sparse-view cranial CT scans from 3000 patients obtained from a public dataset and reconstructed with varying levels of sub-sampling. Additionally, we trained a convolutional neural network on fully sampled CT data from 17,545 patients for automated hemorrhage detection. We evaluated the classification performance using the area under the receiver operator characteristic curves (AUC-ROCs) with corresponding 95% confidence intervals (CIs) and the DeLong test, along with confusion matrices. The performance of the U-Net was compared to an analytical approach based on total variation (TV). Results: The U-Net performed superior compared to unprocessed and TV-processed images with respect to image quality and automated hemorrhage diagnosis. With U-Net post-processing, the number of views can be reduced from 4096 (AUC-ROC: 0.974; 95% CI: 0.972-0.976) views to 512 views (0.973; 0.971-0.975) with minimal decrease in hemorrhage detection (P<.001) and to 256 views (0.967; 0.964-0.969) with a slight performance decrease (P<.001). Conclusion: The results suggest that U-Net based artifact reduction substantially enhances automated hemorrhage detection in sparse-view cranial CTs. Our findings highlight that appropriate post-processing is crucial for optimal image quality and diagnostic accuracy while minimizing radiation dose.
Authors: Juan Terven, Diana M. Cordova-Esparza, Alfonso Ramirez-Pedraza, Edgar A. Chavez-Urbiola, Julio A. Romero-Gonzalez
Abstract: When training or evaluating deep learning models, two essential parts are picking the proper loss function and deciding on performance metrics. In this paper, we provide a comprehensive overview of the most common loss functions and metrics used across many different types of deep learning tasks, from general tasks such as regression and classification to more specific tasks in Computer Vision and Natural Language Processing. We introduce the formula for each loss and metric, discuss their strengths and limitations, and describe how these methods can be applied to various problems within deep learning. We hope this work serves as a reference for researchers and practitioners in the field, helping them make informed decisions when selecting the most appropriate loss function and performance metrics for their deep learning projects.
Authors: Weidong Huang, Jiaming Ji, Chunhe Xia, Borong Zhang, Yaodong Yang
Abstract: The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based methods into world model planning processes within the superior Dreamer framework. Our method achieves nearly zero-cost performance on various tasks, spanning low-dimensional and vision-only input, within the Safety-Gymnasium benchmark, showcasing its efficacy in balancing performance and safety in RL tasks. Further details can be found in the code repository: \url{https://github.com/PKU-Alignment/SafeDreamer}.
Authors: Jing Xu
Abstract: The online shopping behavior has the characteristics of rich granularity dimension and data sparsity and previous researches on user behavior prediction did not seriously discuss feature selection and ensemble design. In this paper, we proposed a SE-Stacking model based on information fusion and ensemble learning for user purchase behavior prediction. After successfully utilizing the ensemble feature selection method to screen purchase-related factors, we used the Stacking algorithm for user purchase behavior prediction. In our efforts to avoid the deviation of prediction results, we optimized the model by selecting ten different kinds of models as base learners and modifying relevant parameters specifically for them. The experiments conducted on a publicly-available dataset shows that the SE-Stacking model can achieve a 98.40% F1-score, about 0.09% higher than the optimal base models. The SE-Stacking model not only has a good application in the prediction of user purchase behavior but also has practical value combining with the actual e-commerce scene. At the same time, it has important significance for academic research and the development of this field.
Authors: Kiana Ehsani, Tanmay Gupta, Rose Hendrix, Jordi Salvador, Luca Weihs, Kuo-Hao Zeng, Kunal Pratap Singh, Yejin Kim, Winson Han, Alvaro Herrasti, Ranjay Krishna, Dustin Schwenk, Eli VanderBilt, Aniruddha Kembhavi
Abstract: Reinforcement learning (RL) with dense rewards and imitation learning (IL) with human-generated trajectories are the most widely used approaches for training modern embodied agents. RL requires extensive reward shaping and auxiliary losses and is often too slow and ineffective for long-horizon tasks. While IL with human supervision is effective, collecting human trajectories at scale is extremely expensive. In this work, we show that imitating shortest-path planners in simulation produces agents that, given a language instruction, can proficiently navigate, explore, and manipulate objects in both simulation and in the real world using only RGB sensors (no depth map or GPS coordinates). This surprising result is enabled by our end-to-end, transformer-based, SPOC architecture, powerful visual encoders paired with extensive image augmentation, and the dramatic scale and diversity of our training data: millions of frames of shortest-path-expert trajectories collected inside approximately 200,000 procedurally generated houses containing 40,000 unique 3D assets. Our models, data, training code, and newly proposed 10-task benchmarking suite CHORES are available in https://spoc-robot.github.io.
Authors: Jing Xu
Abstract: Chest X-ray is one of the most common radiological examination types for the diagnosis of chest diseases. Nowadays, the automatic classification technology of radiological images has been widely used in clinical diagnosis and treatment plans. However, each disease has its own different response characteristic receptive field region, which is the main challenge for chest disease classification tasks. Besides, the imbalance of sample data categories further increases the difficulty of tasks. To solve these problems, we propose a new multi-label chest disease image classification scheme based on a multi-scale attention network. In this scheme, multi-scale information is iteratively fused to focus on regions with a high probability of disease, to effectively mine more meaningful information from data, and the classification performance can be improved only by image level annotation. We also designed a new loss function to improve the rationality of visual perception and the performance of multi-label image classification by forcing the consistency of attention regions before and after image transformation. A comprehensive experiment was carried out on the public Chest X-Ray14 and CheXpert datasets to achieve state of the art results, which verified the effectiveness of this method in chest X-ray image classification.
Authors: Vandan Gorade, Sparsh Mittal, Debesh Jha, Rekha Singhal, Ulas Bagci
Abstract: Deep learning has demonstrated remarkable achievements in medical image segmentation. However, prevailing deep learning models struggle with poor generalization due to (i) intra-class variations, where the same class appears differently in different samples, and (ii) inter-class independence, resulting in difficulties capturing intricate relationships between distinct objects, leading to higher false negative cases. This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation. We introduce the innovative Spectral Correlation Coefficient objective to improve the model's capacity to capture middle-order features and contextual long-range dependencies. This objective complements traditional spatial objectives by incorporating valuable spectral information. Extensive experiments reveal that optimizing this objective with existing architectures like UNet and TransUNet significantly enhances generalization, interpretability, and noise robustness, producing more confident predictions. For instance, in cardiac segmentation, we observe a 0.81 pp and 1.63 pp (pp = percentage point) improvement in DSC over UNet and TransUNet, respectively. Our interpretability study demonstrates that, in most tasks, objectives optimized with UNet outperform even TransUNet by introducing global contextual information alongside local details. These findings underscore the versatility and effectiveness of our proposed method across diverse imaging modalities and medical domains.
Authors: Jos\'e Morano, Guilherme Aresta, Hrvoje Bogunovi\'c
Abstract: The caliber and configuration of retinal blood vessels serve as important biomarkers for various diseases and medical conditions. A thorough analysis of the retinal vasculature requires the segmentation of the blood vessels and their classification into arteries and veins, typically performed on color fundus images obtained by retinography. However, manually performing these tasks is labor-intensive and prone to human error. While several automated methods have been proposed to address this task, the current state of art faces challenges due to manifest classification errors affecting the topological consistency of segmentation maps. In this work, we introduce RRWNet, a novel end-to-end deep learning framework that addresses this limitation. The framework consists of a fully convolutional neural network that recursively refines semantic segmentation maps, correcting manifest classification errors and thus improving topological consistency. In particular, RRWNet is composed of two specialized subnetworks: a Base subnetwork that generates base segmentation maps from the input images, and a Recursive Refinement subnetwork that iteratively and recursively improves these maps. Evaluation on three different public datasets demonstrates the state-of-the-art performance of the proposed method, yielding more topologically consistent segmentation maps with fewer manifest classification errors than existing approaches. In addition, the Recursive Refinement module within RRWNet proves effective in post-processing segmentation maps from other methods, further demonstrating its potential. The model code, weights, and predictions will be publicly available at https://github.com/j-morano/rrwnet.
Authors: Phillip Rust, Bowen Shi, Skyler Wang, Necati Cihan Camg\"oz, Jean Maillard
Abstract: A major impediment to the advancement of sign language translation (SLT) is data scarcity. Much of the sign language data currently available on the web cannot be used for training supervised models due to the lack of aligned captions. Furthermore, scaling SLT using large-scale web-scraped datasets bears privacy risks due to the presence of biometric information, which the responsible development of SLT technologies should account for. In this work, we propose a two-stage framework for privacy-aware SLT at scale that addresses both of these issues. We introduce SSVP-SLT, which leverages self-supervised video pretraining on anonymized and unannotated videos, followed by supervised SLT finetuning on a curated parallel dataset. SSVP-SLT achieves state-of-the-art finetuned and zero-shot gloss-free SLT performance on the How2Sign dataset, outperforming the strongest respective baselines by over 3 BLEU-4. Based on controlled experiments, we further discuss the advantages and limitations of self-supervised pretraining and anonymization via facial obfuscation for SLT.
Authors: Jinxu Zhang
Abstract: Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly, ignoring the source document's evidence and lacking interpretability. In this work, we address the lack of step-wise capabilities through data augmentation and extension. Specifically, We use Multi-modal Large Language Models (MLLMs), which have strong visual understanding and reasoning abilities, as data generators to generate step-wise question-and-answer pairs for document images and use a high-performance LLM as the error detector to filter out noisy data. This step-wise data generation pipeline is implemented using both template-based and few-shot methods. We then use the generated high-quality data to train a humanized document understanding and reasoning model, specifically designed to solve complex questions that require reasoning or multi-hop question answering, dubbed DocAssistant. Experimental results demonstrate the effectiveness and application value of step-wise generation, showing a 5 improvement on InfoVQA with complex layouts and a 7 improvement on ChartQA with complex reasoning, compared to directly generated answers. We hope our work highlights the potential of synthetic data and encourages further exploration of multi-modal document reasoning capabilities.
Authors: Yu Xiang, Sai Haneesh Allu, Rohith Peddi, Tyler Summers, Vibhav Gogate
Abstract: We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is represented by a point cloud that can be obtained from depth sensors. Using the point-cloud representation, goal reaching in grasping can be formulated as point matching, while collision avoidance can be efficiently achieved by querying the signed distance values of the robot points in the signed distance field of the scene points. Consequently, a constrained nonlinear optimization problem is formulated to solve the joint motion and grasp planning problem. The advantage of our method is that the point-cloud representation is general to be used with any robot in any environment. We demonstrate the effectiveness of our method by performing experiments on a tabletop scene and a shelf scene for grasping with a Fetch mobile manipulator and a Franka Panda arm. The project page is available at \url{https://irvlutd.github.io/GraspTrajOpt}
Authors: Alireza Furutanpey, Qiyang Zhang, Philipp Raith, Tobias Pfandzelter, Shangguang Wang, Schahram Dustdar
Abstract: Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks. This work presents FOOL, an OEC-native and task-agnostic feature compression method that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks.
Authors: Trevor J. Chan, Aarush Sahni, Yijin Fang, Jie Li, Alisha Luthra, Alison Pouch, Chamith S. Rajapakse
Abstract: We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model. We achieve fast and accurate segmentations in 3D images with a four-step strategy involving: user prompting with 3D polylines, volume slicing along multiple axes, slice-wide inference with a pretrained model, and recomposition and refinement in 3D. We evaluated SAM3D performance qualitatively on an array of imaging modalities and anatomical structures and quantify performance for specific structures in abdominal pelvic CT and brain MRI. Notably, our method achieves good performance with zero model training or finetuning, making it particularly useful for tasks with a scarcity of preexisting labeled data. By enabling users to create 3D segmentations of unseen data quickly and with dramatically reduced manual input, these methods have the potential to aid surgical planning and education, diagnostic imaging, and scientific research.
Authors: Qing Xu, Jiaxuan Li, Xiangjian He, Ziyu Liu, Zhen Chen, Wenting Duan, Chenxin Li, Maggie M. He, Fiseha B. Tesema, Wooi P. Cheah, Yi Wang, Rong Qu, Jonathan M. Garibaldi
Abstract: The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent Segment Anything Model (SAM) has demonstrated its potential in both settings. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalizability and applicability in clinical scenarios. To address these issues, we propose an efficient self-prompting SAM for universal domain-generalized medical image segmentation, named ESP-MedSAM. Specifically, we first devise the Multi-Modal Decoupled Knowledge Distillation (MMDKD) strategy to construct a lightweight semi-parameter sharing image encoder that produces discriminative visual features for diverse modalities. Further, we introduce the Self-Patch Prompt Generator (SPPG) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the Query-Decoupled Modality Decoder (QDMD) that leverages a one-to-one strategy to provide an independent decoding channel for every modality. Extensive experiments indicate that ESP-MedSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, ESP-MedSAM uses only 4.5\% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/ESP-MedSAM.
Authors: Pengcheng Chen, Jin Ye, Guoan Wang, Yanjun Li, Zhongying Deng, Wei Li, Tianbin Li, Haodong Duan, Ziyan Huang, Yanzhou Su, Benyou Wang, Shaoting Zhang, Bin Fu, Jianfei Cai, Bohan Zhuang, Eric J Seibel, Junjun He, Yu Qiao
Abstract: Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals, and can be applied in various fields. In the medical field, LVLMs have a high potential to offer substantial assistance for diagnosis and treatment. Before that, it is crucial to develop benchmarks to evaluate LVLMs' effectiveness in various medical applications. Current benchmarks are often built upon specific academic literature, mainly focusing on a single domain, and lacking varying perceptual granularities. Thus, they face specific challenges, including limited clinical relevance, incomplete evaluations, and insufficient guidance for interactive LVLMs. To address these limitations, we developed the GMAI-MMBench, the most comprehensive general medical AI benchmark with well-categorized data structure and multi-perceptual granularity to date. It is constructed from 285 datasets across 39 medical image modalities, 18 clinical-related tasks, 18 departments, and 4 perceptual granularities in a Visual Question Answering (VQA) format. Additionally, we implemented a lexical tree structure that allows users to customize evaluation tasks, accommodating various assessment needs and substantially supporting medical AI research and applications. We evaluated 50 LVLMs, and the results show that even the advanced GPT-4o only achieves an accuracy of 52%, indicating significant room for improvement. Moreover, we identified five key insufficiencies in current cutting-edge LVLMs that need to be addressed to advance the development of better medical applications. We believe that GMAI-MMBench will stimulate the community to build the next generation of LVLMs toward GMAI. Project Page: https://uni-medical.github.io/GMAI-MMBench.github.io/