Authors: Joey Litalien, Milo\v{s} Ha\v{s}an, Fujun Luan, Krishna Mullia, Iliyan Georgiev
Abstract: Achieving high efficiency in modern photorealistic rendering hinges on using Monte Carlo sampling distributions that closely approximate the illumination integral estimated for every pixel. Samples are typically generated from a set of simple distributions, each targeting a different factor in the integrand, which are combined via multiple importance sampling. The resulting mixture distribution can be far from the actual product of all factors, leading to sub-optimal variance even for direct-illumination estimation. We present a learning-based method that uses normalizing flows to efficiently importance sample illumination product integrals, e.g., the product of environment lighting and material terms. Our sampler composes a flow head warp with an emitter tail warp. The small conditional head warp is represented by a neural spline flow, while the large unconditional tail is discretized per environment map and its evaluation is instant. If the conditioning is low-dimensional, the head warp can be also discretized to achieve even better performance. We demonstrate variance reduction over prior methods on a range of applications comprising complex geometry, materials and illumination.
Authors: Mahtab Dahaghin, Myrna Castillo, Kourosh Riahidehkordi, Matteo Toso, Alessio Del Bue
Abstract: The creation of digital replicas of physical objects has valuable applications for the preservation and dissemination of tangible cultural heritage. However, existing methods are often slow, expensive, and require expert knowledge. We propose a pipeline to generate a 3D replica of a scene using only RGB images (e.g. photos of a museum) and then extract a model for each item of interest (e.g. pieces in the exhibit). We do this by leveraging the advancements in novel view synthesis and Gaussian Splatting, modified to enable efficient 3D segmentation. This approach does not need manual annotation, and the visual inputs can be captured using a standard smartphone, making it both affordable and easy to deploy. We provide an overview of the method and baseline evaluation of the accuracy of object segmentation. The code is available at https://mahtaabdn.github.io/gaussian_heritage.github.io/.
URLs: https://mahtaabdn.github.io/gaussian_heritage.github.io/.
Authors: Kotaro Kikuchi, Naoto Inoue, Mayu Otani, Edgar Simo-Serra, Kota Yamaguchi
Abstract: This paper presents multimodal markup document models (MarkupDM) that can generate both markup language and images within interleaved multimodal documents. Unlike existing vision-and-language multimodal models, our MarkupDM tackles unique challenges critical to graphic design tasks: generating partial images that contribute to the overall appearance, often involving transparency and varying sizes, and understanding the syntax and semantics of markup languages, which play a fundamental role as a representational format of graphic designs. To address these challenges, we design an image quantizer to tokenize images of diverse sizes with transparency and modify a code language model to process markup languages and incorporate image modalities. We provide in-depth evaluations of our approach on three graphic design completion tasks: generating missing attribute values, images, and texts in graphic design templates. Results corroborate the effectiveness of our MarkupDM for graphic design tasks. We also discuss the strengths and weaknesses in detail, providing insights for future research on multimodal document generation.
Authors: Diogo Gl\'oria-Silva, David Semedo, Jo\~ao Magalh\~aes
Abstract: Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance. However, existing works on plan-following language models (LMs) often are not capable of multimodal input and output. In this work, we present MM-PlanLLM, the first multimodal LLM designed to assist users in executing instructional tasks by leveraging both textual plans and visual information. Specifically, we bring cross-modality through two key tasks: Conversational Video Moment Retrieval, where the model retrieves relevant step-video segments based on user queries, and Visually-Informed Step Generation, where the model generates the next step in a plan, conditioned on an image of the user's current progress. MM-PlanLLM is trained using a novel multitask-multistage approach, designed to gradually expose the model to multimodal instructional-plans semantic layers, achieving strong performance on both multimodal and textual dialogue in a plan-grounded setting. Furthermore, we show that the model delivers cross-modal temporal and plan-structure representations aligned between textual plan steps and instructional video moments.
Authors: Salaheldin Mohamed, Dong Han, Yong Li
Abstract: Text-to-image (T2I) models have significantly advanced the development of artificial intelligence, enabling the generation of high-quality images in diverse contexts based on specific text prompts. However, existing T2I-based methods often struggle to accurately reproduce the appearance of individuals from a reference image and to create novel representations of those individuals in various settings. To address this, we leverage the pre-trained UNet from Stable Diffusion to incorporate the target face image directly into the generation process. Our approach diverges from prior methods that depend on fixed encoders or static face embeddings, which often fail to bridge encoding gaps. Instead, we capitalize on UNet's sophisticated encoding capabilities to process reference images across multiple scales. By innovatively altering the cross-attention layers of the UNet, we effectively fuse individual identities into the generative process. This strategic integration of facial features across various scales not only enhances the robustness and consistency of the generated images but also facilitates efficient multi-reference and multi-identity generation. Our method sets a new benchmark in identity-preserving image generation, delivering state-of-the-art results in similarity metrics while maintaining prompt alignment.
Authors: Yize Li, Yihua Zhang, Sijia Liu, Xue Lin
Abstract: Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient diffusion training has often been overlooked. In this work, we investigate efficient diffusion training from the perspective of dataset pruning. Inspired by the principles of data-efficient training for generative models such as generative adversarial networks (GANs), we first extend the data selection scheme used in GANs to DM training, where data features are encoded by a surrogate model, and a score criterion is then applied to select the coreset. To further improve the generation performance, we employ a class-wise reweighting approach, which derives class weights through distributionally robust optimization (DRO) over a pre-trained reference DM. For a pixel-wise DM (DDPM) on CIFAR-10, experiments demonstrate the superiority of our methodology over existing approaches and its effectiveness in image synthesis comparable to that of the original full-data model while achieving the speed-up between 2.34 times and 8.32 times. Additionally, our method could be generalized to latent DMs (LDMs), e.g., Masked Diffusion Transformer (MDT) and Stable Diffusion (SD), and achieves competitive generation capability on ImageNet.Code is available here (https://github.com/Yeez-lee/Data-Selection-and-Reweighting-for-Diffusion-Models).
URLs: https://github.com/Yeez-lee/Data-Selection-and-Reweighting-for-Diffusion-Models).
Authors: Chunzhi Gu, Shigeru Kuriyama, Katsuya Hotta
Abstract: Speech-driven facial animation aims to synthesize lip-synchronized 3D talking faces following the given speech signal. Prior methods to this task mostly focus on pursuing realism with deterministic systems, yet characterizing the potentially stochastic nature of facial motions has been to date rarely studied. While generative modeling approaches can easily handle the one-to-many mapping by repeatedly drawing samples, ensuring a diverse mode coverage of plausible facial motions on small-scale datasets remains challenging and less explored. In this paper, we propose predicting multiple samples conditioned on the same audio signal and then explicitly encouraging sample diversity to address diverse facial animation synthesis. Our core insight is to guide our model to explore the expressive facial latent space with a diversity-promoting loss such that the desired latent codes for diversification can be ideally identified. To this end, building upon the rich facial prior learned with vector-quantized variational auto-encoding mechanism, our model temporally queries multiple stochastic codes which can be flexibly decoded into a diverse yet plausible set of speech-faithful facial motions. To further allow for control over different facial parts during generation, the proposed model is designed to predict different facial portions of interest in a sequential manner, and compose them to eventually form full-face motions. Our paradigm realizes both diverse and controllable facial animation synthesis in a unified formulation. We experimentally demonstrate that our method yields state-of-the-art performance both quantitatively and qualitatively, especially regarding sample diversity.
Authors: Qiming Wu
Abstract: Crowd Counting is a fundamental topic, aiming to estimate the number of individuals in the crowded images or videos fed from surveillance cameras. Recent works focus on improving counting accuracy, while ignoring the certified robustness of counting models. In this paper, we propose a novel Bound Tightening Network (BTN) for Robust Crowd Counting. It consists of three parts: base model, smooth regularization module and certify bound module. The core idea is to propagate the interval bound through the base model (certify bound module) and utilize the layer weights (smooth regularization module) to guide the network learning. Experiments on different benchmark datasets for counting demonstrate the effectiveness and efficiency of BTN.
Authors: Tong Liu, Zhixin Lai, Gengyuan Zhang, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu
Abstract: Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a novel type of jailbreak, which triggers T2I models to generate the image with visual text, where the image and the text, although considered to be safe in isolation, combine to form unsafe content. To systematically explore this phenomenon, we propose a dataset to evaluate the current diffusion-based text-to-image (T2I) models under such jailbreak. We benchmark nine representative T2I models, including two close-source commercial models. Experimental results reveal a concerning tendency to produce unsafe content: all tested models suffer from such type of jailbreak, with rates of unsafe generation ranging from 8\% to 74\%. In real-world scenarios, various filters such as keyword blocklists, customized prompt filters, and NSFW image filters, are commonly employed to mitigate these risks. We evaluate the effectiveness of such filters against our jailbreak and found that, while current classifiers may be effective for single modality detection, they fail to work against our jailbreak. Our work provides a foundation for further development towards more secure and reliable T2I models.
Authors: Bardienus Duisterhof, Lojze Zust, Philippe Weinzaepfel, Vincent Leroy, Yohann Cabon, Jerome Revaud
Abstract: Structure-from-Motion (SfM), a task aiming at jointly recovering camera poses and 3D geometry of a scene given a set of images, remains a hard problem with still many open challenges despite decades of significant progress. The traditional solution for SfM consists of a complex pipeline of minimal solvers which tends to propagate errors and fails when images do not sufficiently overlap, have too little motion, etc. Recent methods have attempted to revisit this paradigm, but we empirically show that they fall short of fixing these core issues. In this paper, we propose instead to build upon a recently released foundation model for 3D vision that can robustly produce local 3D reconstructions and accurate matches. We introduce a low-memory approach to accurately align these local reconstructions in a global coordinate system. We further show that such foundation models can serve as efficient image retrievers without any overhead, reducing the overall complexity from quadratic to linear. Overall, our novel SfM pipeline is simple, scalable, fast and truly unconstrained, i.e. it can handle any collection of images, ordered or not. Extensive experiments on multiple benchmarks show that our method provides steady performance across diverse settings, especially outperforming existing methods in small- and medium-scale settings.
Authors: Hamid Gadirov, Jos B. T. M. Roerdink, Steffen Frey
Abstract: We present FLINT (learning-based FLow estimation and temporal INTerpolation), a novel deep learning-based approach to estimate flow fields for 2D+time and 3D+time scientific ensemble data. FLINT can flexibly handle different types of scenarios with (1) a flow field being partially available for some members (e.g., omitted due to space constraints) or (2) no flow field being available at all (e.g., because it could not be acquired during an experiment). The design of our architecture allows to flexibly cater to both cases simply by adapting our modular loss functions, effectively treating the different scenarios as flow-supervised and flow-unsupervised problems, respectively (with respect to the presence or absence of ground-truth flow). To the best of our knowledge, FLINT is the first approach to perform flow estimation from scientific ensembles, generating a corresponding flow field for each discrete timestep, even in the absence of original flow information. Additionally, FLINT produces high-quality temporal interpolants between scalar fields. FLINT employs several neural blocks, each featuring several convolutional and deconvolutional layers. We demonstrate performance and accuracy for different usage scenarios with scientific ensembles from both simulations and experiments.
Authors: I. B. Barcelos, F. de C. Bel\'em, L. de M. Jo\~ao, Z. K. G. do Patroc\'inio Jr., A. X. Falc\~ao, S. J. F. Guimar\~aes
Abstract: Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 20 strategies based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in pixel clustering and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark.
URLs: https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark.
Authors: Amber Yijia Zheng, Chiao-An Yang, Raymond A. Yeh
Abstract: Advancements in open-source pre-trained backbones make it relatively easy to fine-tune a model for new tasks. However, this lowered entry barrier poses potential risks, e.g., bad actors developing models for harmful applications. A question arises: Is possible to develop a pre-trained model that is difficult to fine-tune for certain downstream tasks? To begin studying this, we focus on few-shot classification (FSC). Specifically, we investigate methods to make FSC more challenging for a set of restricted classes while maintaining the performance of other classes. We propose to meta-learn over the pre-trained backbone in a manner that renders it a ''poor initialization''. Our proposed Learning to Obstruct (LTO) algorithm successfully obstructs four FSC methods across three datasets, including ImageNet and CIFAR100 for image classification, as well as CelebA for attribute classification.
Authors: Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, Hyein Hwang, Soohyun Hwang, Junuk Cha, Jaewook Han, Seungryul Baek
Abstract: This report describes our 1st place solution to the 8th HANDS workshop challenge (ARCTIC track) in conjunction with ECCV 2024. In this challenge, we address the task of bimanual category-agnostic hand-object interaction reconstruction, which aims to generate 3D reconstructions of both hands and the object from a monocular video, without relying on predefined templates. This task is particularly challenging due to the significant occlusion and dynamic contact between the hands and the object during bimanual manipulation. We worked to resolve these issues by introducing a mask loss and a 3D contact loss, respectively. Moreover, we applied 3D Gaussian Splatting (3DGS) to this task. As a result, our method achieved a value of 38.69 in the main metric, CD$_h$, on the ARCTIC test set.
Authors: Zhilong Li, Kejun Wu, Qiong Liu, You Yang
Abstract: Optical imaging systems are generally limited by the depth of field because of the nature of the optics. Therefore, extending depth of field (EDoF) is a fundamental task for meeting the requirements of emerging visual applications. To solve this task, the common practice is using multi-focus images from a single viewpoint. This method can obtain acceptable quality of EDoF under the condition of fixed field of view, but it is only applicable to static scenes and the field of view is limited and fixed. An emerging data type, varifocal multiview images have the potential to become a new paradigm for solving the EDoF, because the data contains more field of view information than multi-focus images. To realize EDoF of varifocal multiview images, we propose an end-to-end method for the EDoF, including image alignment, image optimization and image fusion. Experimental results demonstrate the efficiency of the proposed method.
Authors: Ke Liu, Jiankai Tang, Zhang Jiang, Yuntao Wang, Xiaojing Liu, Dong Li, Yuanchun Shi
Abstract: Video photoplethysmography (vPPG) is an emerging method for non-invasive and convenient measurement of physiological signals, utilizing two primary approaches: remote video PPG (rPPG) and contact video PPG (cPPG). Monitoring vitals in high-altitude environments, where heart rates tend to increase and blood oxygen levels often decrease, presents significant challenges. To address these issues, we introduce the SUMS dataset comprising 80 synchronized non-contact facial and contact finger videos from 10 subjects during exercise and oxygen recovery scenarios, capturing PPG, respiration rate (RR), and SpO2. This dataset is designed to validate video vitals estimation algorithms and compare facial rPPG with finger cPPG. Additionally, fusing videos from different positions (i.e., face and finger) reduces the mean absolute error (MAE) of SpO2 predictions by 7.6\% and 10.6\% compared to only face and only finger, respectively. In cross-subject evaluation, we achieve an MAE of less than 0.5 BPM for HR estimation and 2.5\% for SpO2 estimation, demonstrating the precision of our multi-camera fusion techniques. Our findings suggest that simultaneous training on multiple indicators, such as PPG and blood oxygen, can reduce MAE in SpO2 estimation by 17.8\%.
Authors: Tao Liu, Runze Yuan, Yi'ang Ju, Xun Xu, Jiaqi Yang, Xiangting Meng, Xavier Lagorce, Laurent Kneip
Abstract: Reliable self-localization is a foundational skill for many intelligent mobile platforms. This paper explores the use of event cameras for motion tracking thereby providing a solution with inherent robustness under difficult dynamics and illumination. In order to circumvent the challenge of event camera-based mapping, the solution is framed in a cross-modal way. It tracks a map representation that comes directly from frame-based cameras. Specifically, the proposed method operates on top of gaussian splatting, a state-of-the-art representation that permits highly efficient and realistic novel view synthesis. The key of our approach consists of a novel pose parametrization that uses a reference pose plus first order dynamics for local differential image rendering. The latter is then compared against images of integrated events in a staggered coarse-to-fine optimization scheme. As demonstrated by our results, the realistic view rendering ability of gaussian splatting leads to stable and accurate tracking across a variety of both publicly available and newly recorded data sequences.
Authors: Weimin Lyu, Lu Pang, Tengfei Ma, Haibin Ling, Chao Chen
Abstract: The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation. Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic preserving loss is proposed to ensure the semantic integrity of the original image content. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of TrojVLM in maintaining original semantic content while triggering specific target text outputs. This study not only uncovers a critical security risk in VLMs and image-to-text generation but also sets a foundation for future research on securing multimodal models against such sophisticated threats.
Authors: Jiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen, Xinbo Gao
Abstract: While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DSRL) method for weakly supervised VVD to utilize the strength of both Euclidean and hyperbolic geometries, capturing the visual features of events while also exploring the intrinsic relations between events, thereby enhancing the discriminative capacity of the features. DSRL employs a novel information aggregation strategy to progressively learn event context in hyperbolic spaces, which selects aggregation nodes through layer-sensitive hyperbolic association degrees constrained by hyperbolic Dirichlet energy. Furthermore, DSRL attempts to break the cyber-balkanization of different spaces, utilizing cross-space attention to facilitate information interactions between Euclidean and hyperbolic space to capture better discriminative features for final violence detection. Comprehensive experiments demonstrate the effectiveness of our proposed DSRL.
Authors: Kazuki Matsuda, Yuiga Wada, Komei Sugiura
Abstract: In this work, we address the challenge of developing automatic evaluation metrics for image captioning, with a particular focus on robustness against hallucinations. Existing metrics are often inadequate for handling hallucinations, primarily due to their limited ability to compare candidate captions with multifaceted reference captions. To address this shortcoming, we propose DENEB, a novel supervised automatic evaluation metric specifically robust against hallucinations. DENEB incorporates the Sim-Vec Transformer, a mechanism that processes multiple references simultaneously, thereby efficiently capturing the similarity between an image, a candidate caption, and reference captions. To train DENEB, we construct the diverse and balanced Nebula dataset comprising 32,978 images, paired with human judgments provided by 805 annotators. We demonstrated that DENEB achieves state-of-the-art performance among existing LLM-free metrics on the FOIL, Composite, Flickr8K-Expert, Flickr8K-CF, Nebula, and PASCAL-50S datasets, validating its effectiveness and robustness against hallucinations.
Authors: Song Zhang, Daoliang Li, Ran Zhao
Abstract: Majority of deep learning methods utilize vanilla convolution for enhancing underwater images. While vanilla convolution excels in capturing local features and learning the spatial hierarchical structure of images, it tends to smooth input images, which can somewhat limit feature expression and modeling. A prominent characteristic of underwater degraded images is blur, and the goal of enhancement is to make the textures and details (high-frequency features) in the images more visible. Therefore, we believe that leveraging high-frequency features can improve enhancement performance. To address this, we introduce Pixel Difference Convolution (PDC), which focuses on gradient information with significant changes in the image, thereby improving the modeling of enhanced images. We propose an underwater image enhancement network, PDCFNet, based on PDC and cross-level feature fusion. Specifically, we design a detail enhancement module based on PDC that employs parallel PDCs to capture high-frequency features, leading to better detail and texture enhancement. The designed cross-level feature fusion module performs operations such as concatenation and multiplication on features from different levels, ensuring sufficient interaction and enhancement between diverse features. Our proposed PDCFNet achieves a PSNR of 27.37 and an SSIM of 92.02 on the UIEB dataset, attaining the best performance to date. Our code is available at https://github.com/zhangsong1213/PDCFNet.
Authors: Yucheng Xie, Fu Feng, Ruixiao Shi, Jing Wang, Xin Geng
Abstract: Diffusion models often face slow convergence, and existing efficient training techniques, such as Parameter-Efficient Fine-Tuning (PEFT), are primarily designed for fine-tuning pre-trained models. However, these methods are limited in adapting models to variable sizes for real-world deployment, where no corresponding pre-trained models exist. To address this, we introduce FINE, a method based on the Learngene framework, to initializing downstream networks leveraging pre-trained models, while considering both model sizes and task-specific requirements. FINE decomposes pre-trained knowledge into the product of matrices (i.e., $U$, $\Sigma$, and $V$), where $U$ and $V$ are shared across network blocks as ``learngenes'', and $\Sigma$ remains layer-specific. During initialization, FINE trains only $\Sigma$ using a small subset of data, while keeping the learngene parameters fixed, marking it the first approach to integrate both size and task considerations in initialization. We provide a comprehensive benchmark for learngene-based methods in image generation tasks, and extensive experiments demonstrate that FINE consistently outperforms direct pre-training, particularly for smaller models, achieving state-of-the-art results across variable model sizes. FINE also offers significant computational and storage savings, reducing training steps by approximately $3N\times$ and storage by $5\times$, where $N$ is the number of models. Additionally, FINE's adaptability to tasks yields an average performance improvement of 4.29 and 3.30 in FID and sFID across multiple downstream datasets, highlighting its versatility and efficiency.
Authors: Jihai Zhang, Xiaoye Qu, Tong Zhu, Yu Cheng
Abstract: In recent years, Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies have identified that the information loss in the CLIP encoding process is substantial, and CLIP tends to capture only coarse-grained features from the input. This deficiency significantly limits the ability of a single CLIP model to handle images rich in visual detail. In this work, we propose a simple yet effective model-agnostic strategy, Diversified Multiplet Upcycling (DMU), for CLIP. DMU efficiently fine-tunes a series of CLIP models that capture different feature spaces, from a dense pre-trained CLIP checkpoint, sharing parameters except for the Feed-Forward Network (FFN). These models can then be transformed into a CLIP-MoE with a larger model capacity, leading to significantly enhanced performance with minimal computational overhead. To the best of our knowledge, Diversified Multiplet Upcycling is the first approach to introduce sparsely activated MoE into CLIP foundation models. Extensive experiments demonstrate the significant performance of CLIP-MoE across various zero-shot retrieval, zero-shot image classification tasks, and downstream Multimodal Large Language Model (MLLM) benchmarks by serving as a vision encoder. Furthermore, Diversified Multiplet Upcycling enables the conversion of any dense CLIP model into CLIP-MoEs, which can seamlessly replace CLIP in a plug-and-play manner without requiring further adaptation in downstream frameworks. Through Diversified Multiplet Upcycling, we aim to provide valuable insights for future research on developing more efficient and effective multimodal learning systems.
Authors: Ahmad Khaliq, Ming Xu, Stephen Hausler, Michael Milford, Sourav Garg
Abstract: Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the `burstiness' problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/.
Authors: Yuanchao Yue, Hui Yuan, Suai Li, Qi Jiang
Abstract: Multisensor fusion is essential for autonomous vehicles to accurately perceive, analyze, and plan their trajectories within complex environments. This typically involves the integration of data from LiDAR sensors and cameras, which necessitates high-precision and real-time registration. Current methods for registering LiDAR point clouds with images face significant challenges due to inherent modality differences and computational overhead. To address these issues, we propose EEPNet, an advanced network that leverages reflectance maps obtained from point cloud projections to enhance registration accuracy. The introduction of point cloud projections substantially mitigates cross-modality differences at the network input level, while the inclusion of reflectance data improves performance in scenarios with limited spatial information of point cloud within the camera's field of view. Furthermore, by employing edge pixels for feature matching and incorporating an efficient matching optimization layer, EEPNet markedly accelerates real-time registration tasks. Experimental validation demonstrates that EEPNet achieves superior accuracy and efficiency compared to state-of-the-art methods. Our contributions offer significant advancements in autonomous perception systems, paving the way for robust and efficient sensor fusion in real-world applications.
Authors: Yubo Huang, Wenhao Feng, Xin Lai, Zixi Wang, Jingzehua Xu, Shuai Zhang, Hongjie He, Fan Chen
Abstract: Advanced facial recognition technologies and recommender systems with inadequate privacy technologies and policies for facial interactions increase concerns about bioprivacy violations. With the proliferation of video and live-streaming websites, public-face video distribution and interactions pose greater privacy risks. Existing techniques typically address the risk of sensitive biometric information leakage through various privacy enhancement methods but pose a higher security risk by corrupting the information to be conveyed by the interaction data, or by leaving certain biometric features intact that allow an attacker to infer sensitive biometric information from them. To address these shortcomings, in this paper, we propose a neural network framework, CausalVE. We obtain cover images by adopting a diffusion model to achieve face swapping with face guidance and use the speech sequence features and spatiotemporal sequence features of the secret video for dynamic video inference and prediction to obtain a cover video with the same number of frames as the secret video. In addition, we hide the secret video by using reversible neural networks for video hiding so that the video can also disseminate secret data. Numerous experiments prove that our CausalVE has good security in public video dissemination and outperforms state-of-the-art methods from a qualitative, quantitative, and visual point of view.
Authors: Potito Aghilar, Vito Walter Anelli, Michelantonio Trizio, Tommaso Di Noia
Abstract: In recent years, 3D models have gained popularity in various fields, including entertainment, manufacturing, and simulation. However, manually creating these models can be a time-consuming and resource-intensive process, making it impractical for large-scale industrial applications. To address this issue, researchers are exploiting Artificial Intelligence and Machine Learning algorithms to automatically generate 3D models effortlessly. In this paper, we present a novel cloud-native pipeline that can automatically reconstruct 3D models from monocular 2D images captured using a smartphone camera. Our goal is to provide an efficient and easily-adoptable solution that meets the Industry 4.0 standards for creating a Digital Twin model, which could enhance personnel expertise through accelerated training. We leverage machine learning models developed by NVIDIA Research Labs alongside a custom-designed pose recorder with a unique pose compensation component based on the ARCore framework by Google. Our solution produces a reusable 3D model, with embedded materials and textures, exportable and customizable in any external 3D modelling software or 3D engine. Furthermore, the whole workflow is implemented by adopting the microservices architecture standard, enabling each component of the pipeline to operate as a standalone replaceable module.
Authors: Hao Chen, Wei Zhao, Yingli Li, Tianyang Zhong, Yisong Wang, Youlan Shang, Lei Guo, Junwei Han, Tianming Liu, Jun Liu, Tuo Zhang
Abstract: Medical image analysis is crucial in modern radiological diagnostics, especially given the exponential growth in medical imaging data. The demand for automated report generation systems has become increasingly urgent. While prior research has mainly focused on using machine learning and multimodal language models for 2D medical images, the generation of reports for 3D medical images has been less explored due to data scarcity and computational complexities. This paper introduces 3D-CT-GPT, a Visual Question Answering (VQA)-based medical visual language model specifically designed for generating radiology reports from 3D CT scans, particularly chest CTs. Extensive experiments on both public and private datasets demonstrate that 3D-CT-GPT significantly outperforms existing methods in terms of report accuracy and quality. Although current methods are few, including the partially open-source CT2Rep and the open-source M3D, we ensured fair comparison through appropriate data conversion and evaluation methodologies. Experimental results indicate that 3D-CT-GPT enhances diagnostic accuracy and report coherence, establishing itself as a robust solution for clinical radiology report generation. Future work will focus on expanding the dataset and further optimizing the model to enhance its performance and applicability.
Authors: Pinxue Guo, Wanyun Li, Hao Huang, Lingyi Hong, Xinyu Zhou, Zhaoyu Chen, Jinglun Li, Kaixun Jiang, Wei Zhang, Wenqiang Zhang
Abstract: Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such as extreme illumination, rapid motion, and background distraction. Existing approaches often involve designing specific additional branches and performing full-parameter fine-tuning for fusion in each task. However, this paradigm not only duplicates research efforts and hardware costs but also risks model collapse with the limited multi-modal annotated data. In this paper, we propose a universal framework named X-Prompt for all multi-modal video object segmentation tasks, designated as RGB+X. The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data. Within the X-Prompt framework, we introduce the Multi-modal Visual Prompter (MVP), which allows prompting foundation model with the various modalities to segment objects precisely. We further propose the Multi-modal Adaptation Experts (MAEs) to adapt the foundation model with pluggable modality-specific knowledge without compromising the generalization capacity. To evaluate the effectiveness of the X-Prompt framework, we conduct extensive experiments on 3 tasks across 4 benchmarks. The proposed universal X-Prompt framework consistently outperforms the full fine-tuning paradigm and achieves state-of-the-art performance. Code: https://github.com/PinxueGuo/X-Prompt.git
Authors: Zhuyun Zhou, Zongwei Wu, Florian Bolli, R\'emi Boutteau, Fan Yang, Radu Timofte, Dominique Ginhac, Tobi Delbruck
Abstract: Autonomous racing has rapidly gained research attention. Traditionally, racing cars rely on 2D LiDAR as their primary visual system. In this work, we explore the integration of an event camera with the existing system to provide enhanced temporal information. Our goal is to fuse the 2D LiDAR data with event data in an end-to-end learning framework for steering prediction, which is crucial for autonomous racing. To the best of our knowledge, this is the first study addressing this challenging research topic. We start by creating a multisensor dataset specifically for steering prediction. Using this dataset, we establish a benchmark by evaluating various SOTA fusion methods. Our observations reveal that existing methods often incur substantial computational costs. To address this, we apply low-rank techniques to propose a novel, efficient, and effective fusion design. We introduce a new fusion learning policy to guide the fusion process, enhancing robustness against misalignment. Our fusion architecture provides better steering prediction than LiDAR alone, significantly reducing the RMSE from 7.72 to 1.28. Compared to the second-best fusion method, our work represents only 11% of the learnable parameters while achieving better accuracy. The source code, dataset, and benchmark will be released to promote future research.
Authors: Minqiang Zou, Zhi Lv, Riqiang Jin, Tian Zhan, Mochen Yu, Yao Tang, Jiajun Liang
Abstract: Multi-view egocentric hand tracking is a challenging task and plays a critical role in VR interaction. In this report, we present a method that uses multi-view input images and camera extrinsic parameters to estimate both hand shape and pose. To reduce overfitting to the camera layout, we apply crop jittering and extrinsic parameter noise augmentation. Additionally, we propose an offline neural smoothing post-processing method to further improve the accuracy of hand position and pose. Our method achieves 13.92mm MPJPE on the Umetrack dataset and 21.66mm MPJPE on the HOT3D dataset.
Authors: Zheyuan Zhan, Defang Chen, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, Can Wang
Abstract: Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis, leading to exponential growth in the literature. However, the complexity of diffusion-based modeling, the wide range of image synthesis tasks, and the diversity of conditioning mechanisms present significant challenges for researchers to keep up with rapid developments and understand the core concepts on this topic. In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i.e., the denoising network and the sampling process. We specifically highlight the underlying principles, advantages, and potential challenges of various conditioning approaches in the training, re-purposing, and specialization stages to construct a desired denoising network. We also summarize six mainstream conditioning mechanisms in the essential sampling process. All discussions are centered around popular applications. Finally, we pinpoint some critical yet still open problems to be solved in the future and suggest some possible solutions. Our reviewed works are itemized at https://github.com/zju-pi/Awesome-Conditional-Diffusion-Models.
URLs: https://github.com/zju-pi/Awesome-Conditional-Diffusion-Models.
Authors: Chu-Jie Qin, Rui-Qi Wu, Zikun Liu, Xin Lin, Chun-Le Guo, Hyun Hee Park, Chongyi Li
Abstract: All-in-one image restoration aims to handle multiple degradation types using one model. This paper proposes a simple pipeline for all-in-one blind image restoration to Restore Anything with Masks (RAM). We focus on the image content by utilizing Mask Image Modeling to extract intrinsic image information rather than distinguishing degradation types like other methods. Our pipeline consists of two stages: masked image pre-training and fine-tuning with mask attribute conductance. We design a straightforward masking pre-training approach specifically tailored for all-in-one image restoration. This approach enhances networks to prioritize the extraction of image content priors from various degradations, resulting in a more balanced performance across different restoration tasks and achieving stronger overall results. To bridge the gap of input integrity while preserving learned image priors as much as possible, we selectively fine-tuned a small portion of the layers. Specifically, the importance of each layer is ranked by the proposed Mask Attribute Conductance (MAC), and the layers with higher contributions are selected for finetuning. Extensive experiments demonstrate that our method achieves state-of-the-art performance. Our code and model will be released at \href{https://github.com/Dragonisss/RAM}{https://github.com/Dragonisss/RAM}.
URLs: https://github.com/Dragonisss/RAM, https://github.com/Dragonisss/RAM
Authors: Yun Chen, Jingkang Wang, Ze Yang, Sivabalan Manivasagam, Raquel Urtasun
Abstract: Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per scene, which is expensive and slow, and exhibit noticeable artifacts under large view changes due to overfitting. Generalizable approaches or large reconstruction models are fast, but primarily work for small scenes/objects and often produce lower quality rendering results. In this work, we introduce G3R, a generalizable reconstruction approach that can efficiently predict high-quality 3D scene representations for large scenes. We propose to learn a reconstruction network that takes the gradient feedback signals from differentiable rendering to iteratively update a 3D scene representation, combining the benefits of high photorealism from per-scene optimization with data-driven priors from fast feed-forward prediction methods. Experiments on urban-driving and drone datasets show that G3R generalizes across diverse large scenes and accelerates the reconstruction process by at least 10x while achieving comparable or better realism compared to 3DGS, and also being more robust to large view changes.
Authors: Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Noel E. O'Connor
Abstract: Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications due to their aligned latent space. However, this practice has left powerful unimodal encoders for both vision and language underutilized in multimodal applications which raises a key question: Is there a plausible way to connect unimodal backbones for zero-shot vision-language tasks? To this end, we propose a novel approach that aligns vision and language modalities using only projection layers on pretrained, frozen unimodal encoders. Our method exploits the high semantic similarity between embedding spaces of well-trained vision and language models. It involves selecting semantically similar encoders in the latent space, curating a concept-rich dataset of image-caption pairs, and training simple MLP projectors. We evaluated our approach on 12 zero-shot classification datasets and 2 image-text retrieval datasets. Our best model, utilizing DINOv2 and All-Roberta-Large text encoder, achieves 76\(\%\) accuracy on ImageNet with a 20-fold reduction in data and 65 fold reduction in compute requirements. The proposed framework enhances the accessibility of model development while enabling flexible adaptation across diverse scenarios, offering an efficient approach to building multimodal models by utilizing existing unimodal architectures. Code and datasets will be released soon.
Authors: Hao Chen, Saining Xie, Ser-Nam Lim, Abhinav Shrivastava
Abstract: Despite the abundant availability and content richness for video data, its high-dimensionality poses challenges for video research. Recent advancements have explored the implicit representation for videos using neural networks, demonstrating strong performance in applications such as video compression and enhancement. However, the prolonged encoding time remains a persistent challenge for video Implicit Neural Representations (INRs). In this paper, we focus on improving the speed of video encoding and decoding within implicit representations. We introduce two key components: NeRV-Enc, a transformer-based hyper-network for fast encoding; and NeRV-Dec, a parallel decoder for efficient video loading. NeRV-Enc achieves an impressive speed-up of $\mathbf{10^4\times}$ by eliminating gradient-based optimization. Meanwhile, NeRV-Dec simplifies video decoding, outperforming conventional codecs with a loading speed $\mathbf{11\times}$ faster, and surpassing RAM loading with pre-decoded videos ($\mathbf{2.5\times}$ faster while being $\mathbf{65\times}$ smaller in size).
Authors: Mohammed Talha Alam, Raza Imam, Mohammad Areeb Qazi, Asim Ukaye, Karthik Nandakumar
Abstract: Advancements in generative modeling are pushing the state-of-the-art in synthetic medical image generation. These synthetic images can serve as an effective data augmentation method to aid the development of more accurate machine learning models for medical image analysis. While the fidelity of these synthetic images has progressively increased, the diversity of these images is an understudied phenomenon. In this work, we propose the SDICE index, which is based on the characterization of similarity distributions induced by a contrastive encoder. Given a synthetic dataset and a reference dataset of real images, the SDICE index measures the distance between the similarity score distributions of original and synthetic images, where the similarity scores are estimated using a pre-trained contrastive encoder. This distance is then normalized using an exponential function to provide a consistent metric that can be easily compared across domains. Experiments conducted on the MIMIC-chest X-ray and ImageNet datasets demonstrate the effectiveness of SDICE index in assessing synthetic medical dataset diversity.
Authors: Andy V. Huynh, Lauren E. Gillespie, Jael Lopez-Saucedo, Claire Tang, Rohan Sikand, Mois\'es Exp\'osito-Alonso
Abstract: Multimodal image-text contrastive learning has shown that joint representations can be learned across modalities. Here, we show how leveraging multiple views of image data with contrastive learning can improve downstream fine-grained classification performance for species recognition, even when one view is absent. We propose ContRastive Image-remote Sensing Pre-training (CRISP)$\unicode{x2014}$a new pre-training task for ground-level and aerial image representation learning of the natural world$\unicode{x2014}$and introduce Nature Multi-View (NMV), a dataset of natural world imagery including $>3$ million ground-level and aerial image pairs for over 6,000 plant taxa across the ecologically diverse state of California. The NMV dataset and accompanying material are available at hf.co/datasets/andyvhuynh/NatureMultiView.
Authors: Maor Ashkenazi, Eran Treister
Abstract: Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applications such as interpolating new coordinates and signal compression, their black-box nature makes it difficult to modify them post-training. In this paper we explore the idea of editable INRs, and specifically focus on the widely used cropping operation. To this end, we present Local-Global SIRENs -- a novel INR architecture that supports cropping by design. Local-Global SIRENs are based on combining local and global feature extraction for signal encoding. What makes their design unique is the ability to effortlessly remove specific portions of an encoded signal, with a proportional weight decrease. This is achieved by eliminating the corresponding weights from the network, without the need for retraining. We further show how this architecture can be used to support the straightforward extension of previously encoded signals. Beyond signal editing, we examine how the Local-Global approach can accelerate training, enhance encoding of various signals, improve downstream performance, and be applied to modern INRs such as INCODE, highlighting its potential and flexibility. Code is available at https://github.com/maorash/Local-Global-INRs.
Authors: Diego A. B. Moreira, Alef Iury Ferreira, Gabriel Oliveira dos Santos, Luiz Pereira, Jo\~ao Medrado Gondim, Gustavo Bonil, Helena Maia, N\'adia da Silva, Simone Tiemi Hashiguti, Jefersson A. dos Santos, Helio Pedrini, Sandra Avila
Abstract: Despite significant advancements and pervasive use of vision-language models, a paucity of studies has addressed their ethical implications. These models typically require extensive training data, often from hastily reviewed text and image datasets, leading to highly imbalanced datasets and ethical concerns. Additionally, models initially trained in English are frequently fine-tuned for other languages, such as the CLIP model, which can be expanded with more data to enhance capabilities but can add new biases. The CAPIVARA, a CLIP-based model adapted to Portuguese, has shown strong performance in zero-shot tasks. In this paper, we evaluate four different types of discriminatory practices within visual-language models and introduce FairPIVARA, a method to reduce them by removing the most affected dimensions of feature embeddings. The application of FairPIVARA has led to a significant reduction of up to 98% in observed biases while promoting a more balanced word distribution within the model. Our model and code are available at: https://github.com/hiaac-nlp/FairPIVARA.
Authors: Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, Yiming Xiao
Abstract: Segmentation of anatomical structures and pathological regions in medical images is essential for modern clinical diagnosis, disease research, and treatment planning. While significant advancements have been made in deep learning-based segmentation techniques, many of these methods still suffer from limitations in data efficiency, generalizability, and interactivity. As a result, developing precise segmentation methods that require fewer labeled datasets remains a critical challenge in medical image analysis. Recently, the introduction of foundation models like CLIP and Segment-Anything-Model (SAM), with robust cross-domain representations, has paved the way for interactive and universal image segmentation. However, further exploration of these models for data-efficient segmentation in medical imaging is still needed and highly relevant. In this paper, we introduce MedCLIP-SAMv2, a novel framework that integrates the CLIP and SAM models to perform segmentation on clinical scans using text prompts, in both zero-shot and weakly supervised settings. Our approach includes fine-tuning the BiomedCLIP model with a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss, and leveraging the Multi-modal Information Bottleneck (M2IB) to create visual prompts for generating segmentation masks from SAM in the zero-shot setting. We also investigate using zero-shot segmentation labels within a weakly supervised paradigm to enhance segmentation quality further. Extensive testing across four diverse segmentation tasks and medical imaging modalities (breast tumor ultrasound, brain tumor MRI, lung X-ray, and lung CT) demonstrates the high accuracy of our proposed framework. Our code is available at https://github.com/HealthX-Lab/MedCLIP-SAMv2.
Authors: Xiao Wang, Jianlong Wu, Zijia Lin, Fuzheng Zhang, Di Zhang, Liqiang Nie
Abstract: Recently, video-language understanding has achieved great success through large-scale pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively reveals an "impossible trinity" among data quantity, diversity, and quality in pre-training datasets. Recent efforts seek to refine large-scale, diverse ASR datasets compromised by low quality through synthetic annotations. These methods successfully leverage useful information in multimodal video content (frames, tags, ASR transcripts, etc.) to refine the original annotations. Nevertheless, they struggle to mitigate noise within synthetic annotations and lack scalability as the dataset size expands. To address these issues, we introduce the Video DataFlywheel framework, which iteratively refines video annotations with improved noise control methods. For iterative refinement, we first leverage a video-language model to generate synthetic annotations, resulting in a refined dataset. Then, we pre-train on it and fine-tune on human refinement examples for a stronger model. These processes are repeated for continuous improvement. For noise control, we present AdaTaiLr, a novel noise control method that requires weaker assumptions on noise distribution, thereby proving more effective in large datasets with theoretical guarantees. The combination of iterative refinement and AdaTaiLr can achieve better scalability in video-language understanding. Extensive experiments show that our framework outperforms existing data refinement baselines, delivering a 3% performance boost and improving dataset quality with minimal diversity loss. Furthermore, our refined dataset facilitates significant improvements in various video-language understanding tasks, including video question answering and text-video retrieval.
Authors: Haolin Li, Yuhang Zhou, Ziheng Zhao, Siyuan Du, Jiangchao Yao, Weidi Xie, Ya Zhang, Yanfeng Wang
Abstract: The widespread adoption of large-scale pre-training techniques has significantly advanced the development of medical foundation models, enabling them to serve as versatile tools across a broad range of medical tasks. However, despite their strong generalization capabilities, medical foundation models pre-trained on large-scale datasets tend to suffer from domain gaps between heterogeneous data, leading to suboptimal performance on specific tasks compared to specialist models, as evidenced by previous studies. In this paper, we explore a new perspective called "Knowledge Decomposition" to improve the performance on specific medical tasks, which deconstructs the foundation model into multiple lightweight expert models, each dedicated to a particular anatomical region, with the aim of enhancing specialization and simultaneously reducing resource consumption. To accomplish the above objective, we propose a novel framework named Low-Rank Knowledge Decomposition (LoRKD), which explicitly separates gradients from different tasks by incorporating low-rank expert modules and efficient knowledge separation convolution. The low-rank expert modules resolve gradient conflicts between heterogeneous data from different anatomical regions, providing strong specialization at lower costs. The efficient knowledge separation convolution significantly improves algorithm efficiency by achieving knowledge separation within a single forward propagation. Extensive experimental results on segmentation and classification tasks demonstrate that our decomposed models not only achieve state-of-the-art performance but also exhibit superior transferability on downstream tasks, even surpassing the original foundation models in task-specific evaluations. The code is available at here.
Authors: Wenlve Zhou, Zhiheng Zhou, Junyuan Shang, Chang Niu, Mingyue Zhang, Xiyuan Tao, Tianlei Wang
Abstract: Unsupervised Domain Adaptation (UDA) leverages a labeled source domain to solve tasks in an unlabeled target domain. While Transformer-based methods have shown promise in UDA, their application is limited to plain Transformers, excluding Convolutional Neural Networks (CNNs) and hierarchical Transformers. To address this issues, we propose Bidirectional Probability Calibration (BiPC) from a probability space perspective. We demonstrate that the probability outputs from a pre-trained head, after extensive pre-training, are robust against domain gaps and can adjust the probability distribution of the task head. Moreover, the task head can enhance the pre-trained head during adaptation training, improving model performance through bidirectional complementation. Technically, we introduce Calibrated Probability Alignment (CPA) to adjust the pre-trained head's probabilities, such as those from an ImageNet-1k pre-trained classifier. Additionally, we design a Calibrated Gini Impurity (CGI) loss to refine the task head, with calibrated coefficients learned from the pre-trained classifier. BiPC is a simple yet effective method applicable to various networks, including CNNs and Transformers. Experimental results demonstrate its remarkable performance across multiple UDA tasks. Our code will be available at: https://github.com/Wenlve-Zhou/BiPC.
Authors: Sikai Yang
Abstract: As human eyes serve as conduits of rich information, unveiling emotions, intentions, and even aspects of an individual's health and overall well-being, gaze tracking also enables various human-computer interaction applications, as well as insights in psychological and medical research. However, existing gaze tracking solutions fall short at handling free user movement, and also require laborious user effort in system calibration. We introduce Tri-Cam, a practical deep learning-based gaze tracking system using three affordable RGB webcams. It features a split network structure for efficient training, as well as designated network designs to handle the separated gaze tracking tasks. Tri-Cam is also equipped with an implicit calibration module, which makes use of mouse click opportunities to reduce calibration overhead on the user's end. We evaluate Tri-Cam against Tobii, the state-of-the-art commercial eye tracker, achieving comparable accuracy, while supporting a wider free movement area. In conclusion, Tri-Cam provides a user-friendly, affordable, and robust gaze tracking solution that could practically enable various applications.
Authors: Xuan Tan, Xun Gong, Yang Xiang
Abstract: Contrastive Language-Image Pre-Training (CLIP) model excels in traditional person re-identification (ReID) tasks due to its inherent advantage in generating textual descriptions for pedestrian images. However, applying CLIP directly to intra-camera supervised person re-identification (ICS ReID) presents challenges. ICS ReID requires independent identity labeling within each camera, without associations across cameras. This limits the effectiveness of text-based enhancements. To address this, we propose a novel framework called CLIP-based Camera-Agnostic Feature Learning (CCAFL) for ICS ReID. Accordingly, two custom modules are designed to guide the model to actively learn camera-agnostic pedestrian features: Intra-Camera Discriminative Learning (ICDL) and Inter-Camera Adversarial Learning (ICAL). Specifically, we first establish learnable textual prompts for intra-camera pedestrian images to obtain crucial semantic supervision signals for subsequent intra- and inter-camera learning. Then, we design ICDL to increase inter-class variation by considering the hard positive and hard negative samples within each camera, thereby learning intra-camera finer-grained pedestrian features. Additionally, we propose ICAL to reduce inter-camera pedestrian feature discrepancies by penalizing the model's ability to predict the camera from which a pedestrian image originates, thus enhancing the model's capability to recognize pedestrians from different viewpoints. Extensive experiments on popular ReID datasets demonstrate the effectiveness of our approach. Especially, on the challenging MSMT17 dataset, we arrive at 58.9\% in terms of mAP accuracy, surpassing state-of-the-art methods by 7.6\%. Code will be available at: https://github.com/Trangle12/CCAFL.
Authors: Yong Liu, Ruihao Xu, Yansong Tang
Abstract: This paper focuses on the Referring Image Segmentation (RIS) task, which aims to segment objects from an image based on a given language description. The critical problem of RIS is achieving fine-grained alignment between different modalities to recognize and segment the target object. Recent advances using the attention mechanism for cross-modal interaction have achieved excellent progress. However, current methods tend to lack explicit principles of interaction design as guidelines, leading to inadequate cross-modal comprehension. Additionally, most previous works use a single-modal mask decoder for prediction, losing the advantage of full cross-modal alignment. To address these challenges, we present a Fully Aligned Network (FAN) that follows four cross-modal interaction principles. Under the guidance of reasonable rules, our FAN achieves state-of-the-art performance on the prevalent RIS benchmarks (RefCOCO, RefCOCO+, G-Ref) with a simple architecture.
Authors: Shuhang Liu, Zhenrong Zhang, Pengfei Hu, Jiefeng Ma, Jun Du, Qing Wang, Jianshu Zhang, Chenyu Liu
Abstract: In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which often introduces significant latency, computational overhead, and errors. Current advanced image-to-text approaches, which bypass OCR, typically yield plain text outputs without corresponding vision grounding. In this paper, we introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision grounding. Distinctively, STNet utilizes a unique
Authors: Zhongcong Xu, Chaoyue Song, Guoxian Song, Jianfeng Zhang, Jun Hao Liew, Hongyi Xu, You Xie, Linjie Luo, Guosheng Lin, Jiashi Feng, Mike Zheng Shou
Abstract: Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in crucial areas such as the face and hands, and neglect the explicit modeling for motion blur, leading to unrealistic low-quality synthesis. To address these limitations, we first leverage regional supervision for detailed regions to enhance face and hand faithfulness. Second, we model the motion blur explicitly to further improve the appearance quality. Third, we explore novel training strategies for high-resolution human animation to improve the overall fidelity. Experimental results demonstrate that our proposed method outperforms state-of-the-art approaches, achieving significant improvements upon the strongest baseline by more than 21.0% and 57.4% in terms of reconstruction precision (L1) and perceptual quality (FVD) on HumanDance dataset. Code and model will be made available.
Authors: Shukesh Reddy, Nishit Poddar, Srijan Das, Abhijit Das
Abstract: In this work, we explore Self-supervised Learning (SSL) as an auxiliary task to blend the texture-based local descriptors into feature modelling for efficient face analysis. Combining a primary task and a self-supervised auxiliary task is beneficial for robust representation. Therefore, we used the SSL task of mask auto-encoder (MAE) as an auxiliary task to reconstruct texture features such as local patterns along with the primary task for robust and unbiased face analysis. We experimented with our hypothesis on three major paradigms of face analysis: face attribute and face-based emotion analysis, and deepfake detection. Our experiment results exhibit that better feature representation can be gleaned from our proposed model for fair and bias-less face analysis.
Authors: Kun Cheng, Lei Yu, Zhijun Tu, Xiao He, Liyu Chen, Yong Guo, Mingrui Zhu, Nannan Wang, Xinbo Gao, Jie Hu
Abstract: Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, which have demonstrated remarkable performance in image generation. In this work, we design an effective diffusion transformer for image super-resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner. In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks across different stages. The former facilitates multi-scale hierarchical feature extraction, while the latter reallocates the computational resources to critical layers to further enhance performance. Moreover, we thoroughly analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module, enhancing the model's capacity to process distinct frequency information at different time steps. Extensive experiments demonstrate that DiT-SR outperforms the existing training-from-scratch diffusion-based SR methods significantly, and even beats some of the prior-based methods on pretrained Stable Diffusion, proving the superiority of diffusion transformer in image super-resolution.
Authors: Ruiqing Mao, Haotian Wu, Yukuan Jia, Zhaojun Nan, Yuxuan Sun, Sheng Zhou, Deniz G\"und\"uz, Zhisheng Niu
Abstract: Collaborative perception (CP) is emerging as a promising solution to the inherent limitations of stand-alone intelligence. However, current wireless communication systems are unable to support feature-level and raw-level collaborative algorithms due to their enormous bandwidth demands. In this paper, we propose DiffCP, a novel CP paradigm that utilizes a specialized diffusion model to efficiently compress the sensing information of collaborators. By incorporating both geometric and semantic conditions into the generative model, DiffCP enables feature-level collaboration with an ultra-low communication cost, advancing the practical implementation of CP systems. This paradigm can be seamlessly integrated into existing CP algorithms to enhance a wide range of downstream tasks. Through extensive experimentation, we investigate the trade-offs between communication, computation, and performance. Numerical results demonstrate that DiffCP can significantly reduce communication costs by 14.5-fold while maintaining the same performance as the state-of-the-art algorithm.
Authors: Chen Hu, Yian Huang, Kexuan Li, Luping Zhang, Yiming Zhu, Yufei Peng, Tian Pu, Zhenming Peng
Abstract: Infrared small target detection (IRSTD) is widely used in civilian and military applications. However, IRSTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Gradient Network (GaNet), which aims to extract and preserve edge and gradient information of small targets. GaNet employs the Gradient Transformer (GradFormer) module, simulating central difference convolutions (CDC) to extract and integrate gradient features with deeper features. Furthermore, we propose a global feature extraction model (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the background information. We compare the network with state-of-the-art (SOTA) approaches, and the results demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/Gradient-Transformer.
Authors: Zechen Bai, Tong He, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, Lei Liu, Zheng Zhang, Mike Zheng Shou
Abstract: We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA addresses these challenges by integrating a Sparse Dense Sampling strategy into the video-LLM, which balances temporal context and spatial detail within computational constraints. Additionally, we propose a One-Token-Seg-All approach using a specially designed
Authors: Yifan Duan, Jian Zhao, pengcheng, Junyuan Mao, Hao Wu, Jingyu Xu, shilong wang, Caoyuan Ma, Kai Wang, Kun Wang, Xuelong Li
Abstract: Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that are excessively customized and devoid of causal connections further undermine the generalizability and interpretability. To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Going beyond this process, we utilize the back-door adjustment to specifically address the sub-regions identified as non-causal in the upstream phase. Specifically, we employ a novel image inpainting technique. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts, offering the possibility of reliable extrapolation for potential data distributions. CaPaint overcomes the high complexity dilemma of optimal ST causal discovery models by reducing the data generation complexity from exponential to quasi-linear levels. Extensive experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%. Moreover, compared to traditional mainstream ST augmenters, CaPaint underscores the potential of diffusion models in ST enhancement, offering a novel paradigm for this field. Our project is available at https://anonymous.4open.science/r/12345-DFCC.
Authors: Qianxiong Xu, Xuanyi Liu, Lanyun Zhu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao
Abstract: Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.
Authors: Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa, Richa Singh
Abstract: Deep learning models, such as those used for face recognition and attribute prediction, are susceptible to manipulations like adversarial noise and unintentional noise, including Gaussian and impulse noise. This paper introduces CIAI, a Class-Independent Adversarial Intent detection network built on a modified vision transformer with detection layers. CIAI employs a novel loss function that combines Maximum Mean Discrepancy and Center Loss to detect both intentional (adversarial attacks) and unintentional noise, regardless of the image class. It is trained in a multi-step fashion. We also introduce the aspect of intent during detection that can act as an added layer of security. We further showcase the performance of our proposed detector on CelebA, CelebA-HQ, LFW, AgeDB, and CIFAR-10 datasets. Our detector is able to detect both intentional (like FGSM, PGD, and DeepFool) and unintentional (like Gaussian and Salt & Pepper noises) perturbations.
Authors: Yuhang Ma, Wenting Xu, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Zeng Zhao, Changjie Fan, Zhipeng Hu
Abstract: Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly representing their postures and backgrounds. The ID-Injector utilize a Shuffling Reference Strategy (SRS) to integrate ID features into specific locations, enhancing ID-based consistent character generation. Additionally, to facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images. This dataset contains single and multiple-character sets in diverse environments, layouts, and gestures with detailed descriptions. Experimental results indicate that Storynizor demonstrates superior coherent story generation with high-fidelity character consistency, flexible postures, and vivid backgrounds compared to other character-specific methods.
Authors: Chaohui Xu, Si Wang, Chip-Hong Chang
Abstract: Precise future human motion prediction over subsecond horizons from past observations is crucial for various safety-critical applications. To date, only one study has examined the vulnerability of human motion prediction to evasion attacks. In this paper, we propose BadHMP, the first backdoor attack that targets specifically human motion prediction. Our approach involves generating poisoned training samples by embedding a localized backdoor trigger in one arm of the skeleton, causing selected joints to remain relatively still or follow predefined motion in historical time steps. Subsequently, the future sequences are globally modified to the target sequences, and the entire training dataset is traversed to select the most suitable samples for poisoning. Our carefully designed backdoor triggers and targets guarantee the smoothness and naturalness of the poisoned samples, making them stealthy enough to evade detection by the model trainer while keeping the poisoned model unobtrusive in terms of prediction fidelity to untainted sequences. The target sequences can be successfully activated by the designed input sequences even with a low poisoned sample injection ratio. Experimental results on two datasets (Human3.6M and CMU-Mocap) and two network architectures (LTD and HRI) demonstrate the high-fidelity, effectiveness, and stealthiness of BadHMP. Robustness of our attack against fine-tuning defense is also verified.
Authors: Xinyue Zhang, Jiaqi Yang, Xiangting Meng, Abdelrahman Mohamed, Laurent Kneip
Abstract: In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subject of intense research within the community. In practical applications, without a strong scene geometry prior like the Manhattan World assumption or special artificial calibration patterns, monocular focal length estimation becomes a challenging task. In this paper, we propose a method for monocular focal length estimation using category-level object priors. Based on two well-studied existing tasks: monocular depth estimation and category-level object canonical representation learning, our focal solver takes depth priors and object shape priors from images containing objects and estimates the focal length from triplets of correspondences in closed form. Our experiments on simulated and real world data demonstrate that the proposed method outperforms the current state-of-the-art, offering a promising solution to the long-standing monocular focal length estimation problem.
Authors: Jiaqi Zhao, Zeyu Ding, Yong Zhou, Hancheng Zhu, Wen-Liang Du, Rui Yao, Abdulmotaleb El Saddik
Abstract: Oriented object detection in remote sensing images is a challenging task due to objects being distributed in multi-orientation. Recently, end-to-end transformer-based methods have achieved success by eliminating the need for post-processing operators compared to traditional CNN-based methods. However, directly extending transformers to oriented object detection presents three main issues: 1) objects rotate arbitrarily, necessitating the encoding of angles along with position and size; 2) the geometric relations of oriented objects are lacking in self-attention, due to the absence of interaction between content and positional queries; and 3) oriented objects cause misalignment, mainly between values and positional queries in cross-attention, making accurate classification and localization difficult. In this paper, we propose an end-to-end transformer-based oriented object detector, consisting of three dedicated modules to address these issues. First, Gaussian positional encoding is proposed to encode the angle, position, and size of oriented boxes using Gaussian distributions. Second, Wasserstein self-attention is proposed to introduce geometric relations and facilitate interaction between content and positional queries by utilizing Gaussian Wasserstein distance scores. Third, oriented cross-attention is proposed to align values and positional queries by rotating sampling points around the positional query according to their angles. Experiments on six datasets DIOR-R, a series of DOTA, HRSC2016 and ICDAR2015 show the effectiveness of our approach. Compared with previous end-to-end detectors, the OrientedFormer gains 1.16 and 1.21 AP$_{50}$ on DIOR-R and DOTA-v1.0 respectively, while reducing training epochs from 3$\times$ to 1$\times$. The codes are available at https://github.com/wokaikaixinxin/OrientedFormer.
Authors: Cuiyu Liu, Wei Zhai, Yuhang Yang, Hongchen Luo, Sen Liang, Yang Cao, Zheng-Jun Zha
Abstract: Grounding 3D scene affordance aims to locate interactive regions in 3D environments, which is crucial for embodied agents to interact intelligently with their surroundings. Most existing approaches achieve this by mapping semantics to 3D instances based on static geometric structure and visual appearance. This passive strategy limits the agent's ability to actively perceive and engage with the environment, making it reliant on predefined semantic instructions. In contrast, humans develop complex interaction skills by observing and imitating how others interact with their surroundings. To empower the model with such abilities, we introduce a novel task: grounding 3D scene affordance from egocentric interactions, where the goal is to identify the corresponding affordance regions in a 3D scene based on an egocentric video of an interaction. This task faces the challenges of spatial complexity and alignment complexity across multiple sources. To address these challenges, we propose the Egocentric Interaction-driven 3D Scene Affordance Grounding (Ego-SAG) framework, which utilizes interaction intent to guide the model in focusing on interaction-relevant sub-regions and aligns affordance features from different sources through a bidirectional query decoder mechanism. Furthermore, we introduce the Egocentric Video-3D Scene Affordance Dataset (VSAD), covering a wide range of common interaction types and diverse 3D environments to support this task. Extensive experiments on VSAD validate both the feasibility of the proposed task and the effectiveness of our approach.
Authors: Hongchao Zhou, Shunbo Hu
Abstract: Deformable medical image registration is a crucial aspect of medical image analysis. In recent years, researchers have begun leveraging auxiliary tasks (such as supervised segmentation) to provide anatomical structure information for the primary registration task, addressing complex deformation challenges in medical image registration. In this work, we propose a multi-task learning framework based on multi-scale dual attention frequency fusion (DAFF-Net), which simultaneously achieves the segmentation masks and dense deformation fields in a single-step estimation. DAFF-Net consists of a global encoder, a segmentation decoder, and a coarse-to-fine pyramid registration decoder. During the registration decoding process, we design the dual attention frequency feature fusion (DAFF) module to fuse registration and segmentation features at different scales, fully leveraging the correlation between the two tasks. The DAFF module optimizes the features through global and local weighting mechanisms. During local weighting, it incorporates both high-frequency and low-frequency information to further capture the features that are critical for the registration task. With the aid of segmentation, the registration learns more precise anatomical structure information, thereby enhancing the anatomical consistency of the warped images after registration. Additionally, due to the DAFF module's outstanding ability to extract effective feature information, we extend its application to unsupervised registration. Extensive experiments on three public 3D brain magnetic resonance imaging (MRI) datasets demonstrate that the proposed DAFF-Net and its unsupervised variant outperform state-of-the-art registration methods across several evaluation metrics, demonstrating the effectiveness of our approach in deformable medical image registration.
Authors: Haonan Lin, Wenbin An, Jiahao Wang, Yan Chen, Feng Tian, Mengmeng Wang, Guang Dai, Qianying Wang, Jingdong Wang
Abstract: Recent advancements have shown promise in applying traditional Semi-Supervised Learning strategies to the task of Generalized Category Discovery (GCD). Typically, this involves a teacher-student framework in which the teacher imparts knowledge to the student to classify categories, even in the absence of explicit labels. Nevertheless, GCD presents unique challenges, particularly the absence of priors for new classes, which can lead to the teacher's misguidance and unsynchronized learning with the student, culminating in suboptimal outcomes. In our work, we delve into why traditional teacher-student designs falter in open-world generalized category discovery as compared to their success in closed-world semi-supervised learning. We identify inconsistent pattern learning across attention layers as the crux of this issue and introduce FlipClass, a method that dynamically updates the teacher to align with the student's attention, instead of maintaining a static teacher reference. Our teacher-student attention alignment strategy refines the teacher's focus based on student feedback from an energy perspective, promoting consistent pattern recognition and synchronized learning across old and new classes. Extensive experiments on a spectrum of benchmarks affirm that FlipClass significantly surpasses contemporary GCD methods, establishing new standards for the field.
Authors: Xu Zhang, Peiyao Guo, Ming Lu, Zhan Ma
Abstract: Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and bitrate usage, or face challenges in multi-objective optimization under a unified representation, failing to achieve both performance and efficiency. To this end, we propose Multi-Path Aggregation (MPA) integrated into existing coding models for joint human-machine vision, unifying the feature representation with an all-in-one architecture. MPA employs a predictor to allocate latent features among task-specific paths based on feature importance varied across tasks, maximizing the utility of shared features while preserving task-specific features for subsequent refinement. Leveraging feature correlations, we develop a two-stage optimization strategy to alleviate multi-task performance degradation. Upon the reuse of shared features, as low as 1.89% parameters are further augmented and fine-tuned for a specific task, which completely avoids extensive optimization of the entire model. Experimental results show that MPA achieves performance comparable to state-of-the-art methods in both task-specific and multi-objective optimization across human viewing and machine analysis tasks. Moreover, our all-in-one design supports seamless transitions between human- and machine-oriented reconstruction, enabling task-controllable interpretation without altering the unified model. Code is available at https://github.com/NJUVISION/MPA.
Authors: Chengxin Zheng, Junzhong Ji, Yanzhao Shi, Xiaodan Zhang, Liangqiong Qu
Abstract: Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at https://github.com/Chauncey-Jheng/PCRL-MRG.
Authors: Fang Long, Wenkang Su, Zixuan Li, Lei Cai, Mingjie Li, Yuan-Gen Wang, Xiaochun Cao
Abstract: Adverse weather removal aims to restore clear vision under adverse weather conditions. Existing methods are mostly tailored for specific weather types and rely heavily on extensive labeled data. In dealing with these two limitations, this paper presents a pioneering semi-supervised all-in-one adverse weather removal framework built on the teacher-student network with a Denoising Diffusion Model (DDM) as the backbone, termed SemiDDM-Weather. As for the design of DDM backbone in our SemiDDM-Weather, we adopt the SOTA Wavelet Diffusion Model-Wavediff with customized inputs and loss functions, devoted to facilitating the learning of many-to-one mapping distributions for efficient all-in-one adverse weather removal with limited label data. To mitigate the risk of misleading model training due to potentially inaccurate pseudo-labels generated by the teacher network in semi-supervised learning, we introduce quality assessment and content consistency constraints to screen the "optimal" outputs from the teacher network as the pseudo-labels, thus more effectively guiding the student network training with unlabeled data. Experimental results show that on both synthetic and real-world datasets, our SemiDDM-Weather consistently delivers high visual quality and superior adverse weather removal, even when compared to fully supervised competitors. Our code and pre-trained model are available at this repository.
Authors: Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen, Siwei Lyu
Abstract: Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based accelerated sampling methods have been developed recently. However, they generally require time-consuming fine tuning with elaborate designs to achieve satisfactory performance in a specific number of function evaluation (NFE), making them difficult to employ in practice. To address this issue, we propose Simple and Fast Distillation (SFD) of diffusion models, which simplifies the paradigm used in existing methods and largely shortens their fine-tuning time up to 1000$\times$. We begin with a vanilla distillation-based sampling method and boost its performance to state of the art by identifying and addressing several small yet vital factors affecting the synthesis efficiency and quality. Our method can also achieve sampling with variable NFEs using a single distilled model. Extensive experiments demonstrate that SFD strikes a good balance between the sample quality and fine-tuning costs in few-step image generation task. For example, SFD achieves 4.53 FID (NFE=2) on CIFAR-10 with only 0.64 hours of fine-tuning on a single NVIDIA A100 GPU. Our code is available at https://github.com/zju-pi/diff-sampler.
Authors: Lijian Xu, Hao Sun, Ziyu Ni, Hongsheng Li, Shaoting Zhang
Abstract: Medicine is inherently multimodal and multitask, with diverse data modalities spanning text, imaging. However, most models in medical field are unimodal single tasks and lack good generalizability and explainability. In this study, we introduce MedViLaM, a unified vision-language model towards a generalist model for medical data that can flexibly encode and interpret various forms of medical data, including clinical language and imaging, all using the same set of model weights. To facilitate the creation of such multi-task model, we have curated MultiMedBench, a comprehensive pretaining dataset and benchmark consisting of several distinct tasks, i.e., continuous question-answering, multi-label disease classification, disease localization, generation and summarization of radiology reports. MedViLaM demonstrates strong performance across all MultiMedBench tasks, frequently outpacing other generalist models by a significant margin. Additionally, we present instances of zero-shot generalization to new medical concepts and tasks, effective transfer learning across different tasks, and the emergence of zero-shot medical reasoning.
Authors: Xiaofeng Cong, Jing Zhang, Yeying Jin, Junming Hou, Yu Zhao, Jie Gui, James Tin-Yau Kwok, Yuan Yan Tang
Abstract: Underwater images often suffer from quality degradation due to absorption and scattering effects. Most existing underwater image enhancement algorithms produce a single, fixed-color image, limiting user flexibility and application. To address this limitation, we propose a method called \textit{ColorCode}, which enhances underwater images while offering a range of controllable color outputs. Our approach involves recovering an underwater image to a reference enhanced image through supervised training and decomposing it into color and content codes via self-reconstruction and cross-reconstruction. The color code is explicitly constrained to follow a Gaussian distribution, allowing for efficient sampling and interpolation during inference. ColorCode offers three key features: 1) color enhancement, producing an enhanced image with a fixed color; 2) color adaptation, enabling controllable adjustments of long-wavelength color components using guidance images; and 3) color interpolation, allowing for the smooth generation of multiple colors through continuous sampling of the color code. Quantitative and visual evaluations on popular and challenging benchmark datasets demonstrate the superiority of ColorCode over existing methods in providing diverse, controllable, and color-realistic enhancement results. The source code is available at https://github.com/Xiaofeng-life/ColorCode.
Authors: Xingyu Chen
Abstract: Text-driven human motion generation is a multimodal task that synthesizes human motion sequences conditioned on natural language. It requires the model to satisfy textual descriptions under varying conditional inputs, while generating plausible and realistic human actions with high diversity. Existing diffusion model-based approaches have outstanding performance in the diversity and multimodality of generation. However, compared to autoregressive methods that train motion encoders before inference, diffusion methods lack in fitting the distribution of human motion features which leads to an unsatisfactory FID score. One insight is that the diffusion model lack the ability to learn the motion relations among spatio-temporal semantics through contextual reasoning. To solve this issue, in this paper, we proposed Motion Masked Diffusion Model \textbf{(MMDM)}, a novel human motion masked mechanism for diffusion model to explicitly enhance its ability to learn the spatio-temporal relationships from contextual joints among motion sequences. Besides, considering the complexity of human motion data with dynamic temporal characteristics and spatial structure, we designed two mask modeling strategies: \textbf{time frames mask} and \textbf{body parts mask}. During training, MMDM masks certain tokens in the motion embedding space. Then, the diffusion decoder is designed to learn the whole motion sequence from masked embedding in each sampling step, this allows the model to recover a complete sequence from incomplete representations. Experiments on HumanML3D and KIT-ML dataset demonstrate that our mask strategy is effective by balancing motion quality and text-motion consistency.
Authors: Yiming Zhao, Dewen Guo, Zhouhui Lian, Yue Gao, Jianhong Han, Jie Feng, Guoping Wang, Bingfeng Zhou, Sheng Li
Abstract: To bridge the gap between artists and non-specialists, we present a unified framework, Neural-Polyptych, to facilitate the creation of expansive, high-resolution paintings by seamlessly incorporating interactive hand-drawn sketches with fragments from original paintings. We have designed a multi-scale GAN-based architecture to decompose the generation process into two parts, each responsible for identifying global and local features. To enhance the fidelity of semantic details generated from users' sketched outlines, we introduce a Correspondence Attention module utilizing our Reference Bank strategy. This ensures the creation of high-quality, intricately detailed elements within the artwork. The final result is achieved by carefully blending these local elements while preserving coherent global consistency. Consequently, this methodology enables the production of digital paintings at megapixel scale, accommodating diverse artistic expressions and enabling users to recreate content in a controlled manner. We validate our approach to diverse genres of both Eastern and Western paintings. Applications such as large painting extension, texture shuffling, genre switching, mural art restoration, and recomposition can be successfully based on our framework.
Authors: Jiahui Fan, Fujun Luan, Jian Yang, Milo\v{s} Ha\v{s}an, Beibei Wang
Abstract: 3D Gaussian Splatting (3DGS) has shown its impressive power in novel view synthesis. However, creating relightable 3D assets, especially for objects with ill-defined shapes (e.g., fur), is still a challenging task. For these scenes, the decomposition between the light, geometry, and material is more ambiguous, as neither the surface constraints nor the analytical shading model hold. To address this issue, we propose RNG, a novel representation of relightable neural Gaussians, enabling the relighting of objects with both hard surfaces or fluffy boundaries. We avoid any assumptions in the shading model but maintain feature vectors, which can be further decoded by an MLP into colors, in each Gaussian point. Following prior work, we utilize a point light to reduce the ambiguity and introduce a shadow-aware condition to the network. We additionally propose a depth refinement network to help the shadow computation under the 3DGS framework, leading to better shadow effects under point lights. Furthermore, to avoid the blurriness brought by the alpha-blending in 3DGS, we design a hybrid forward-deferred optimization strategy. As a result, we achieve about $20\times$ faster in training and about $600\times$ faster in rendering than prior work based on neural radiance fields, with $60$ frames per second on an RTX4090.
Authors: Shuang Wang
Abstract: I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into the teacher model, which significantly improves the accuracy of pseudo-label generation. By addressing key issues such as class imbalance and the precision of bounding boxes, the Lower Biased Teacher model demonstrates superior performance in object detection tasks. Extensive experiments on multiple semi-supervised object detection datasets show that the Lower Biased Teacher model not only reduces the pseudo-labeling bias caused by class imbalances but also mitigates errors arising from incorrect bounding boxes. As a result, the model achieves higher mAP scores and more reliable detection outcomes compared to existing methods. This research underscores the importance of accurate pseudo-label generation and provides a robust framework for future advancements in semi-supervised learning for object detection.
Authors: Kexue Fu, Xiaoyuan Luo, Linhao Qu, Shuo Wang, Ying Xiong, Ilias Maglogiannis, Longxiang Gao, Manning Wang
Abstract: The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide Images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22$\%$ annotation costs. All codes and models will be publicly available on https://github.com/fukexue/FAST.
Authors: Yibo Zhong, Yao Zhou
Abstract: Adapters have been widely explored to alleviate computational and storage costs when fine-tuning pretrained foundation models. However, the adapter itself can exhibit redundancy, leading to unnecessary storage overhead and inferior performance. In this paper, we propose Prune and Share (Pear), a novel adapter-pruning framework for efficient fine-tuning of pretrained visual foundation models. Specifically, we prune certain adapters and share the more important unpruned ones with positions where adapters are pruned, allowing continual adaptation at these positions after pruning. Additionally, a knowledge checkpoint strategy is introduced, which preserves the information of the pruned adapters and further boosts performance. Experimental results on visual adaptation benchmark validate the effectiveness and efficiency of the proposed Pear comparing to other competitive methods. Code is in https://github.com/yibozhong/pear.
Authors: Chen Yeh, You-Ming Chang, Wei-Chen Chiu, Ning Yu
Abstract: To address the risks of encountering inappropriate or harmful content, researchers managed to incorporate several harmful contents datasets with machine learning methods to detect harmful concepts. However, existing harmful datasets are curated by the presence of a narrow range of harmful objects, and only cover real harmful content sources. This hinders the generalizability of methods based on such datasets, potentially leading to misjudgments. Therefore, we propose a comprehensive harmful dataset, Visual Harmful Dataset 11K (VHD11K), consisting of 10,000 images and 1,000 videos, crawled from the Internet and generated by 4 generative models, across a total of 10 harmful categories covering a full spectrum of harmful concepts with nontrivial definition. We also propose a novel annotation framework by formulating the annotation process as a multi-agent Visual Question Answering (VQA) task, having 3 different VLMs "debate" about whether the given image/video is harmful, and incorporating the in-context learning strategy in the debating process. Therefore, we can ensure that the VLMs consider the context of the given image/video and both sides of the arguments thoroughly before making decisions, further reducing the likelihood of misjudgments in edge cases. Evaluation and experimental results demonstrate that (1) the great alignment between the annotation from our novel annotation framework and those from human, ensuring the reliability of VHD11K; (2) our full-spectrum harmful dataset successfully identifies the inability of existing harmful content detection methods to detect extensive harmful contents and improves the performance of existing harmfulness recognition methods; (3) VHD11K outperforms the baseline dataset, SMID, as evidenced by the superior improvement in harmfulness recognition methods. The complete dataset and code can be found at https://github.com/nctu-eva-lab/VHD11K.
Authors: Hansong Zhang, Jiangjian Guo, Kun Li, Yang Zhang, Yimei Zhao
Abstract: Offline handwritten signature verification systems are used to verify the identity of individuals, through recognizing their handwritten signature image as genuine signatures or forgeries. The main tasks of signature verification systems include extracting features from signature images and training a classifier for classification. The challenges of these tasks are twofold. First, genuine signatures and skilled forgeries are highly similar in their appearances, resulting in a small inter-class distance. Second, the instances of skilled forgeries are often unavailable, when signature verification models are being trained. To tackle these problems, this paper proposes a new signature verification method. It is the first model that employs a variational autoencoder (VAE) to extract features directly from signature images. To make the features more discriminative, it improves the traditional VAEs by introducing a new loss function for feature disentangling. In addition, it relies on SVM (Support Vector Machine) for classification according to the extracted features. Extensive experiments are conducted on two public datasets: MCYT-75 and GPDS-synthetic where the proposed method significantly outperformed $13$ representative offline signature verification methods. The achieved improvement in distinctive datasets indicates the robustness and great potential of the developed system in real application.
Authors: Chen Song, Zhenxiao Liang, Bo Sun, Qixing Huang
Abstract: We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are ideal for processing data captured by event cameras, which are built to simulate neural activities in the human retina. We discuss how to represent the membrane potential of an artificial neuron by a parametric piecewise linear function with learnable coefficients. This design echoes the idea of building deep models from learnable parametric functions recently popularized by Kolmogorov-Arnold Networks (KANs). Experiments demonstrate the state-of-the-art performance of PPLNs in event-based and image-based vision applications, including steering prediction, human pose estimation, and motion deblurring. The source code of our implementation is available at https://github.com/chensong1995/PPLN.
Authors: Nikos Efthymiadis, Giorgos Tolias, Ond\v{r}ej Chum
Abstract: Single-source domain generalization attempts to learn a model on a source domain and deploy it to unseen target domains. Limiting access only to source domain data imposes two key challenges - how to train a model that can generalize and how to verify that it does. The standard practice of validation on the training distribution does not accurately reflect the model's generalization ability, while validation on the test distribution is a malpractice to avoid. In this work, we construct an independent validation set by transforming source domain images with a comprehensive list of augmentations, covering a broad spectrum of potential distribution shifts in target domains. We demonstrate a high correlation between validation and test performance for multiple methods and across various datasets. The proposed validation achieves a relative accuracy improvement over the standard validation equal to 15.4% or 1.6% when used for method selection or learning rate tuning, respectively. Furthermore, we introduce a novel family of methods that increase the shape bias through enhanced edge maps. To benefit from the augmentations during training and preserve the independence of the validation set, a k-fold validation process is designed to separate the augmentation types used in training and validation. The method that achieves the best performance on the augmented validation is selected from the proposed family. It achieves state-of-the-art performance on various standard benchmarks. Code at: https://github.com/NikosEfth/crafting-shifts
Authors: Shaohui Liu, Yidan Gao, Tianyi Zhang, R\'emi Pautrat, Johannes L. Sch\"onberger, Viktor Larsson, Marc Pollefeys
Abstract: Structure-from-Motion (SfM) has become a ubiquitous tool for camera calibration and scene reconstruction with many downstream applications in computer vision and beyond. While the state-of-the-art SfM pipelines have reached a high level of maturity in well-textured and well-configured scenes over the last decades, they still fall short of robustly solving the SfM problem in challenging scenarios. In particular, weakly textured scenes and poorly constrained configurations oftentimes cause catastrophic failures or large errors for the primarily keypoint-based pipelines. In these scenarios, line segments are often abundant and can offer complementary geometric constraints. Their large spatial extent and typically structured configurations lead to stronger geometric constraints as compared to traditional keypoint-based methods. In this work, we introduce an incremental SfM system that, in addition to points, leverages lines and their structured geometric relations. Our technical contributions span the entire pipeline (mapping, triangulation, registration) and we integrate these into a comprehensive end-to-end SfM system that we share as an open-source software with the community. We also present the first analytical method to propagate uncertainties for 3D optimized lines via sensitivity analysis. Experiments show that our system is consistently more robust and accurate compared to the widely used point-based state of the art in SfM -- achieving richer maps and more precise camera registrations, especially under challenging conditions. In addition, our uncertainty-aware localization module alone is able to consistently improve over the state of the art under both point-alone and hybrid setups.
Authors: Bohan Zhan, Wang Zhao, Yi Fang, Bo Du, Francisco Vasconcelos, Danail Stoyanov, Daniel S. Elson, Baoru Huang
Abstract: Accurate tracking of tissues and instruments in videos is crucial for Robotic-Assisted Minimally Invasive Surgery (RAMIS), as it enables the robot to comprehend the surgical scene with precise locations and interactions of tissues and tools. Traditional keypoint-based sparse tracking is limited by featured points, while flow-based dense two-view matching suffers from long-term drifts. Recently, the Tracking Any Point (TAP) algorithm was proposed to overcome these limitations and achieve dense accurate long-term tracking. However, its efficacy in surgical scenarios remains untested, largely due to the lack of a comprehensive surgical tracking dataset for evaluation. To address this gap, we introduce a new annotated surgical tracking dataset for benchmarking tracking methods for surgical scenarios, comprising real-world surgical videos with complex tissue and instrument motions. We extensively evaluate state-of-the-art (SOTA) TAP-based algorithms on this dataset and reveal their limitations in challenging surgical scenarios, including fast instrument motion, severe occlusions, and motion blur, etc. Furthermore, we propose a new tracking method, namely SurgMotion, to solve the challenges and further improve the tracking performance. Our proposed method outperforms most TAP-based algorithms in surgical instruments tracking, and especially demonstrates significant improvements over baselines in challenging medical videos.
Authors: Jonathan Zhou
Abstract: The rise of multi-billion parameter models has sparked an intense hunger for data across deep learning. This study explores the possibility of replacing paid annotators with video game players who are rewarded with in-game currency for good performance. We collaborate with the developers of a mobile historical strategy game, Armchair Commander, to test this idea. More specifically, the current study tests this idea using pairwise image preference data, typically used to fine-tune diffusion models. Using this method, we create GameLabel-10K, a dataset with slightly under 10 thousand labels and 7000 unique prompts. In addition to these results, we analyze some limitations of this dataset and publicly release it under an open-source license.
Authors: Changfeng Feng, Zhenyuan Chen, Renke Kou, Guangwei Gao, Chunping Wang, Xiang Li, Xiangbo Shu, Yimian Dai, Qiang Fu, Jian Yang
Abstract: Drone-based object detection in adverse weather conditions is crucial for enhancing drones' environmental perception, yet it remains largely unexplored due to the lack of relevant benchmarks. To bridge this gap, we introduce HazyDet, a large-scale dataset tailored for drone-based object detection in hazy scenes. It encompasses 383,000 real-world instances, collected from both naturally hazy environments and normal scenes with synthetically imposed haze effects to simulate adverse weather conditions. By observing the significant variations in object scale and clarity under different depth and haze conditions, we designed a Depth Conditioned Detector (DeCoDet) to incorporate this prior knowledge. DeCoDet features a Multi-scale Depth-aware Detection Head that seamlessly integrates depth perception, with the resulting depth cues harnessed by a dynamic Depth Condition Kernel module. Furthermore, we propose a Scale Invariant Refurbishment Loss to facilitate the learning of robust depth cues from pseudo-labels. Extensive evaluations on the HazyDet dataset demonstrate the flexibility and effectiveness of our method, yielding significant performance improvements. Our dataset and toolkit are available at https://github.com/GrokCV/HazyDet.
Authors: Qun Dai, Chunyang Yuan, Yimian Dai, Yuxuan Li, Xiang Li, Kang Ni, Jianhui Xu, Xiangbo Shu, Jian Yang
Abstract: Land Surface Temperature (LST) is a critical parameter for environmental studies, but obtaining high-resolution LST data remains challenging due to the spatio-temporal trade-off in satellite remote sensing. Guided LST downscaling has emerged as a solution, but current methods often neglect spatial non-stationarity and lack a open-source ecosystem for deep learning methods. To address these limitations, we propose the Modality-Conditional Large Selective Kernel (MoCoLSK) Networks, a novel architecture that dynamically fuses multi-modal data through modality-conditioned projections. MoCoLSK re-engineers our previous LSKNet to achieve a confluence of dynamic receptive field adjustment and multi-modal feature integration, leading to enhanced LST prediction accuracy. Furthermore, we establish the GrokLST project, a comprehensive open-source ecosystem featuring the GrokLST dataset, a high-resolution benchmark, and the GrokLST toolkit, an open-source PyTorch-based toolkit encapsulating MoCoLSK alongside 40+ state-of-the-art approaches. Extensive experimental results validate MoCoLSK's effectiveness in capturing complex dependencies and subtle variations within multispectral data, outperforming existing methods in LST downscaling. Our code, dataset, and toolkit are available at https://github.com/GrokCV/GrokLST.
Authors: Saehyung Lee, Jisoo Mok, Sangha Park, Yongho Shin, Dahuin Jung, Sungroh Yoon
Abstract: In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://github.com/Saehyung-Lee/HFTT
Authors: Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
Abstract: Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level recognition tasks like semantic segmentation, which additionally require understanding where the objects are located. In this work, we propose a novel method, PixelCLIP, to adapt the CLIP image encoder for pixel-level understanding by guiding the model on where, which is achieved using unlabeled images and masks generated from vision foundation models such as SAM and DINO. To address the challenges of leveraging masks without semantic labels, we devise an online clustering algorithm using learnable class names to acquire general semantic concepts. PixelCLIP shows significant performance improvements over CLIP and competitive results compared to caption-supervised methods in open-vocabulary semantic segmentation. Project page is available at https://cvlab-kaist.github.io/PixelCLIP
Authors: Nick Nikzad, Yi Liao, Yongsheng Gao, Jun Zhou
Abstract: Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing on different training strategies, input patch augmentation, or network structural enhancements. These approaches often involve extensive training and fine-tuning, which are time-consuming and resource-intensive. To tackle these obstacles, we introduce a novel approach named Spatial Autocorrelation Token Analysis (SATA). By harnessing spatial relationships between token features, SATA enhances both the representational capacity and robustness of ViT models. This is achieved through the analysis and grouping of tokens according to their spatial autocorrelation scores prior to their input into the Feed-Forward Network (FFN) block of the self-attention mechanism. Importantly, SATA seamlessly integrates into existing pre-trained ViT baselines without requiring retraining or additional fine-tuning, while concurrently improving efficiency by reducing the computational load of the FFN units. Experimental results show that the baseline ViTs enhanced with SATA not only achieve a new state-of-the-art top-1 accuracy on ImageNet-1K image classification (94.9%) but also establish new state-of-the-art performance across multiple robustness benchmarks, including ImageNet-A (top-1=63.6%), ImageNet-R (top-1=79.2%), and ImageNet-C (mCE=13.6%), all without requiring additional training or fine-tuning of baseline models.
Authors: Bingqing Zhang, Zhuo Cao, Heming Du, Xin Yu, Xue Li, Jiajun Liu, Sen Wang
Abstract: Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(candidate) alignment paradigm, which struggles to discern nuanced differences among candidates, leading to frequent mismatches. Inspired by Comparative Judgement in human cognitive science, where decisions are made by directly comparing items rather than evaluating them independently, we propose TokenBinder. This innovative two-stage TVR framework introduces a novel one-to-many coarse-to-fine alignment paradigm, imitating the human cognitive process of identifying specific items within a large collection. Our method employs a Focused-view Fusion Network with a sophisticated cross-attention mechanism, dynamically aligning and comparing features across multiple videos to capture finer nuances and contextual variations. Extensive experiments on six benchmark datasets confirm that TokenBinder substantially outperforms existing state-of-the-art methods. These results demonstrate its robustness and the effectiveness of its fine-grained alignment in bridging intra- and inter-modality information gaps in TVR tasks.
Authors: Kaihang Pan, Zhaoyu Fan, Juncheng Li, Qifan Yu, Hao Fei, Siliang Tang, Richang Hong, Hanwang Zhang, Qianru Sun
Abstract: The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of reliability, generality, and locality when applied to MLLMs. In this paper, we propose UniKE, a novel multimodal editing method that establishes a unified perspective and paradigm for intrinsic knowledge editing and external knowledge resorting. Both types of knowledge are conceptualized as vectorized key-value memories, with the corresponding editing processes resembling the assimilation and accommodation phases of human cognition, conducted at the same semantic levels. Within such a unified framework, we further promote knowledge collaboration by disentangling the knowledge representations into the semantic and truthfulness spaces. Extensive experiments validate the effectiveness of our method, which ensures that the post-edit MLLM simultaneously maintains excellent reliability, generality, and locality. The code for UniKE will be available at \url{https://github.com/beepkh/UniKE}.
Authors: Kaini Wang, Kaini Wang, Siping Zhou, Guangquan Zhou, Wentao Zhang, Bin Cui, Shuo Li
Abstract: Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically designed with task-specific branches and heads, which restricts the shared feature space and the flexibility of model. To address these challenges, we have developed a decomposed-composed universal medical imaging paradigm (UniMed) that supports tasks at all levels. To this end, we first propose a decomposed decoder that can predict two types of outputs -- pixel and semantic, based on a defined input queue. Additionally, we introduce a composed decoder that unifies the input and output spaces and standardizes task annotations across different levels into a discrete token format. The coupled design of these two components enables the model to flexibly combine tasks and mutual benefits. Moreover, our joint representation learning strategy skilfully leverages large amounts of unlabeled data and unsupervised loss, achieving efficient one-stage pretraining for more robust performance. Experimental results show that UniMed achieves state-of-the-art performance on eight datasets across all three tasks and exhibits strong zero-shot and 100-shot transferability. We will release the code and trained models upon the paper's acceptance.
Authors: Changsheng Lu, Zheyuan Liu, Piotr Koniusz
Abstract: Exploiting the foundation models (e.g., CLIP) to build a versatile keypoint detector has gained increasing attention. Most existing models accept either the text prompt (e.g., ``the nose of a cat''), or the visual prompt (e.g., support image with keypoint annotations), to detect the corresponding keypoints in query image, thereby, exhibiting either zero-shot or few-shot detection ability. However, the research on taking multimodal prompt is still underexplored, and the prompt diversity in semantics and language is far from opened. For example, how to handle unseen text prompts for novel keypoint detection and the diverse text prompts like ``Can you detect the nose and ears of a cat?'' In this work, we open the prompt diversity from three aspects: modality, semantics (seen v.s. unseen), and language, to enable a more generalized zero- and few-shot keypoint detection (Z-FSKD). We propose a novel OpenKD model which leverages multimodal prototype set to support both visual and textual prompting. Further, to infer the keypoint location of unseen texts, we add the auxiliary keypoints and texts interpolated from visual and textual domains into training, which improves the spatial reasoning of our model and significantly enhances zero-shot novel keypoint detection. We also found large language model (LLM) is a good parser, which achieves over 96% accuracy to parse keypoints from texts. With LLM, OpenKD can handle diverse text prompts. Experimental results show that our method achieves state-of-the-art performance on Z-FSKD and initiates new ways to deal with unseen text and diverse texts. The source code and data are available at https://github.com/AlanLuSun/OpenKD.
Authors: Xiang Wang, Changxin Gao, Yuehuan Wang, Nong Sang
Abstract: Recent advancements in controllable human-centric video generation, particularly with the rise of diffusion models, have demonstrated considerable progress. However, achieving precise and localized control over human motion, e.g., replacing or inserting individuals into videos while exhibiting desired motion patterns, still remains challenging. In this work, we propose the ReplaceAnyone framework, which focuses on localizing and manipulating human motion in videos with diverse and intricate backgrounds. Specifically, we formulate this task as an image-conditioned pose-driven video inpainting paradigm, employing a unified video diffusion architecture that facilitates image-conditioned pose-driven video generation and inpainting within masked video regions. Moreover, we introduce diverse mask forms involving regular and irregular shapes to avoid shape leakage and allow granular local control. Additionally, we implement a two-stage training methodology, initially training an image-conditioned pose driven video generation model, followed by joint training of the video inpainting within masked areas. In this way, our approach enables seamless replacement or insertion of characters while maintaining the desired pose motion and reference appearance within a single framework. Experimental results demonstrate the effectiveness of our method in generating realistic and coherent video content.
Authors: Ivan Reyes-Amezcua, Ricardo Espinosa, Christian Daul, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez
Abstract: Accurate depth estimation in endoscopy is vital for successfully implementing computer vision pipelines for various medical procedures and CAD tools. In this paper, we present the EndoDepth benchmark, an evaluation framework designed to assess the robustness of monocular depth prediction models in endoscopic scenarios. Unlike traditional datasets, the EndoDepth benchmark incorporates common challenges encountered during endoscopic procedures. We present an evaluation approach that is consistent and specifically designed to evaluate the robustness performance of the model in endoscopic scenarios. Among these is a novel composite metric called the mean Depth Estimation Robustness Score (mDERS), which offers an in-depth evaluation of a model's accuracy against errors brought on by endoscopic image corruptions. Moreover, we present SCARED-C, a new dataset designed specifically to assess endoscopy robustness. Through extensive experimentation, we evaluate state-of-the-art depth prediction architectures on the EndoDepth benchmark, revealing their strengths and weaknesses in handling endoscopic challenging imaging artifacts. Our results demonstrate the importance of specialized techniques for accurate depth estimation in endoscopy and provide valuable insights for future research directions.
Authors: Xi Zhang, Yaru Xue, Shaocheng Jia, Xin Pei
Abstract: Self-supervised depth estimation, which solely requires monocular image sequence as input, has become increasingly popular and promising in recent years. Current research primarily focuses on enhancing the prediction accuracy of the models. However, the excessive number of parameters impedes the universal deployment of the model on edge devices. Moreover, the emerging neural networks, being black-box models, are difficult to analyze, leading to challenges in understanding the rationales for performance improvements. To mitigate these issues, this study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE (Coding RAte reduction TransformEr) network. This novel network uses CNNs and the CRATE modules to extract local and global information in images, respectively, thereby boosting learning efficiency and reducing model size. Furthermore, incorporating the CRATE modules into the network enables a mathematically interpretable process in capturing global features. Extensive experiments on the KITTI dataset indicate that the proposed CCDepth network can achieve performance comparable with those state-of-the-art methods, while the model size has been significantly reduced. In addition, a series of quantitative and qualitative analyses on the inner features in the CCDepth network further confirm the effectiveness of the proposed method.
Authors: Ivan Reyes-Amezcua, Michael Rojas-Ruiz, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez, Christian Daul
Abstract: Deep learning developments have improved medical imaging diagnoses dramatically, increasing accuracy in several domains. Nonetheless, obstacles continue to exist because of the requirement for huge datasets and legal limitations on data exchange. A solution is provided by Federated Learning (FL), which permits decentralized model training while maintaining data privacy. However, FL models are susceptible to data corruption, which may result in performance degradation. Using pre-trained models, this research suggests a strong FL framework to improve kidney stone diagnosis. Two different kidney stone datasets, each with six different categories of images, are used in our experimental setting. Our method involves two stages: Learning Parameter Optimization (LPO) and Federated Robustness Validation (FRV). We achieved a peak accuracy of 84.1% with seven epochs and 10 rounds during LPO stage, and 77.2% during FRV stage, showing enhanced diagnostic accuracy and robustness against image corruption. This highlights the potential of merging pre-trained models with FL to address privacy and performance concerns in medical diagnostics, and guarantees improved patient care and enhanced trust in FL-based medical systems.
Authors: Wenchao Chen, Liqiang Niu, Ziyao Lu, Fandong Meng, Jie Zhou
Abstract: Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines Mamba and Transformer architectures, utilizing Masked Image Modeling for non-autoregressive image synthesis. We meticulously redesign the bidirectional Mamba architecture by implementing two key modifications: (1) replacing causal convolutions with standard convolutions to better capture global context, and (2) utilizing concatenation instead of multiplication, which significantly boosts performance while accelerating inference speed. Additionally, we explore various hybrid schemes of MaskMamba, including both serial and grouped parallel arrangements. Furthermore, we incorporate an in-context condition that allows our model to perform both class-to-image and text-to-image generation tasks. Our MaskMamba outperforms Mamba-based and Transformer-based models in generation quality. Notably, it achieves a remarkable $54.44\%$ improvement in inference speed at a resolution of $2048\times 2048$ over Transformer.
Authors: Nishq Poorav Desai, Ali Etemad, Michael Greenspan
Abstract: Self-driving research often underrepresents cyclist collisions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations, from collisions to safe interactions. This dataset enables 9 different cyclist collision prediction and classification tasks focusing on potentially hazardous conditions for cyclists and is annotated with collision-related, cyclist-related, and scene-related labels. Next, we propose VidNeXt, a novel method that leverages a ConvNeXt spatial encoder and a non-stationary transformer to capture the temporal dynamics of videos for the tasks defined in our dataset. To demonstrate the effectiveness of our method and create additional baselines on CycleCrash, we apply and compare 7 models along with a detailed ablation. We release the dataset and code at https://github.com/DeSinister/CycleCrash/ .
Authors: Sang Hyun Park, Jun Young Koh, Junha Lee, Joy Song, Dongha Kim, Hoyeon Moon, Hyunju Lee, Min Song
Abstract: In this work, we share the insights for achieving state-of-the-art quality in our text-to-image anime image generative model, called Illustrious. To achieve high resolution, dynamic color range images, and high restoration ability, we focus on three critical approaches for model improvement. First, we delve into the significance of the batch size and dropout control, which enables faster learning of controllable token based concept activations. Second, we increase the training resolution of images, affecting the accurate depiction of character anatomy in much higher resolution, extending its generation capability over 20MP with proper methods. Finally, we propose the refined multi-level captions, covering all tags and various natural language captions as a critical factor for model development. Through extensive analysis and experiments, Illustrious demonstrates state-of-the-art performance in terms of animation style, outperforming widely-used models in illustration domains, propelling easier customization and personalization with nature of open source. We plan to publicly release updated Illustrious model series sequentially as well as sustainable plans for improvements.
Authors: Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang
Abstract: Images produced by diffusion models are increasingly popular in digital artwork and visual marketing. However, such generated images might replicate content from existing ones and pose the challenge of content originality. Existing Image Copy Detection (ICD) models, though accurate in detecting hand-crafted replicas, overlook the challenge from diffusion models. This motivates us to introduce ICDiff, the first ICD specialized for diffusion models. To this end, we construct a Diffusion-Replication (D-Rep) dataset and correspondingly propose a novel deep embedding method. D-Rep uses a state-of-the-art diffusion model (Stable Diffusion V1.5) to generate 40, 000 image-replica pairs, which are manually annotated into 6 replication levels ranging from 0 (no replication) to 5 (total replication). Our method, PDF-Embedding, transforms the replication level of each image-replica pair into a probability density function (PDF) as the supervision signal. The intuition is that the probability of neighboring replication levels should be continuous and smooth. Experimental results show that PDF-Embedding surpasses protocol-driven methods and non-PDF choices on the D-Rep test set. Moreover, by utilizing PDF-Embedding, we find that the replication ratios of well-known diffusion models against an open-source gallery range from 10% to 20%.
Authors: Shiben Liu, Huijie Fan, Qiang Wang, Weihong Ren, Yandong Tang
Abstract: Lifelong person re-identification (LReID) aims to continuously learn from non-stationary data to match individuals in different environments. Each task is affected by variations in illumination and person-related information (such as pose and clothing), leading to task-wise domain gaps. Current LReID methods focus on task-specific knowledge and ignore intrinsic task-shared representations within domain gaps, limiting model performance. Bridging task-wise domain gaps is crucial for improving anti-forgetting and generalization capabilities, especially when accessing limited old classes during training. To address these issues, we propose a novel attribute-text guided forgetting compensation (ATFC) model, which explores text-driven global representations of identity-related information and attribute-related local representations of identity-free information for LReID. Due to the lack of paired text-image data, we design an attribute-text generator (ATG) to dynamically generate a text descriptor for each instance. We then introduce a text-guided aggregation network (TGA) to explore robust text-driven global representations for each identity and knowledge transfer. Furthermore, we propose an attribute compensation network (ACN) to investigate attribute-related local representations, which distinguish similar identities and bridge domain gaps. Finally, we develop an attribute anti-forgetting (AF) loss and knowledge transfer (KT) loss to minimize domain gaps and achieve knowledge transfer, improving model performance. Extensive experiments demonstrate that our ATFC method achieves superior performance, outperforming existing LReID methods by over 9.0$\%$/7.4$\%$ in average mAP/R-1 on the seen dataset.
Authors: Joshua Feinglass, Yezhou Yang
Abstract: Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in image captioning (IC) for popular datasets such as MSCOCO and Flickr8k, these approaches fall short with fine-grained datasets like CUB, FLO, UCM-Captions, and Sydney-Captions. These datasets require captions to discern between visually and semantically similar classes, focusing on detailed object parts and their attributes. To overcome this challenge, we introduce TRaining-Free Object-Part Enhancement (TROPE). TROPE enriches a base caption with additional object-part details using object detector proposals and Natural Language Processing techniques. It complements rather than alters the base caption, allowing seamless integration with other captioning methods and offering users enhanced flexibility. Our evaluations show that TROPE consistently boosts performance across all tested zero-shot IC approaches and achieves state-of-the-art results on fine-grained IC datasets.
Authors: Yabing Wang, Le Wang, Qiang Zhou, Zhibin Wang, Hao Li, Gang Hua, Wei Tang
Abstract: Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine translation (MT) to create pseudo-parallel data pairs, establishing correspondence between visual and non-English textual data. However, aligning their representations poses challenges due to the significant semantic gap between vision and text, as well as the lower quality of non-English representations caused by pre-trained encoders and data noise. To overcome these challenges, we propose LECCR, a novel solution that incorporates the multi-modal large language model (MLLM) to improve the alignment between visual and non-English representations. Specifically, we first employ MLLM to generate detailed visual content descriptions and aggregate them into multi-view semantic slots that encapsulate different semantics. Then, we take these semantic slots as internal features and leverage them to interact with the visual features. By doing so, we enhance the semantic information within the visual features, narrowing the semantic gap between modalities and generating local visual semantics for subsequent multi-level matching. Additionally, to further enhance the alignment between visual and non-English features, we introduce softened matching under English guidance. This approach provides more comprehensive and reliable inter-modal correspondences between visual and non-English features. Extensive experiments on four CCR benchmarks, \ie Multi30K, MSCOCO, VATEX, and MSR-VTT-CN, demonstrate the effectiveness of our proposed method. Code: \url{https://github.com/LiJiaBei-7/leccr}.
Authors: Chenyi Zhuang, Ying Hu, Pan Gao
Abstract: Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts involving multiple attributes and objects. While previous studies suggest that blended text embeddings lead to improper attribute binding, few have explored this in depth. In this work, we critically examine the limitations of the CLIP text encoder in understanding attributes and investigate how this affects diffusion models. We discern a phenomenon of attribute bias in the text space and highlight a contextual issue in padding embeddings that entangle different concepts. We propose \textbf{Magnet}, a novel training-free approach to tackle the attribute binding problem. We introduce positive and negative binding vectors to enhance disentanglement, further with a neighbor strategy to increase accuracy. Extensive experiments show that Magnet significantly improves synthesis quality and binding accuracy with negligible computational cost, enabling the generation of unconventional and unnatural concepts.
Authors: Zhen Yang, Yanpeng Dong, Heng Wang
Abstract: Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics. However, existing approaches depend on large image resolutions and complex networks to achieve top performance, hindering their application in practical scenarios. Additionally, most multi-sensor fusion approaches focus on improving fusion features while overlooking the exploration of supervision strategies for these features. To this end, we propose DAOcc, a novel multi-sensor fusion occupancy network that leverages 3D object detection supervision to assist in achieving superior performance, while using a deployment-friendly image feature extraction network and practical input image resolution. Furthermore, we introduce a BEV View Range Extension strategy to mitigate the adverse effects of reduced image resolution. As a result, our approach achieves new state-of-the-art results on the Occ3D-nuScenes and SurroundOcc datasets, using ResNet50 and a 256x704 input image resolution. Code will be made available at https://github.com/AlphaPlusTT/DAOcc.
Authors: Kaini Wang, Haolin Wang, Guang-Quan Zhou, Yangang Wang, Ling Yang, Yang Chen, Shuo Li
Abstract: CNN-based object detection models that strike a balance between performance and speed have been gradually used in polyp detection tasks. Nevertheless, accurately locating polyps within complex colonoscopy video scenes remains challenging since existing methods ignore two key issues: intra-sequence distribution heterogeneity and precision-confidence discrepancy. To address these challenges, we propose a novel Temporal-Spatial self-correction detector (TSdetector), which first integrates temporal-level consistency learning and spatial-level reliability learning to detect objects continuously. Technically, we first propose a global temporal-aware convolution, assembling the preceding information to dynamically guide the current convolution kernel to focus on global features between sequences. In addition, we designed a hierarchical queue integration mechanism to combine multi-temporal features through a progressive accumulation manner, fully leveraging contextual consistency information together with retaining long-sequence-dependency features. Meanwhile, at the spatial level, we advance a position-aware clustering to explore the spatial relationships among candidate boxes for recalibrating prediction confidence adaptively, thus eliminating redundant bounding boxes efficiently. The experimental results on three publicly available polyp video dataset show that TSdetector achieves the highest polyp detection rate and outperforms other state-of-the-art methods. The code can be available at https://github.com/soleilssss/TSdetector.
Authors: Yu Deng, Teng Cao, Jiahong Xue
Abstract: We developed a robust solution for real-time 6D object detection in industrial applications by integrating FoundationPose, SAM2, and LightGlue, eliminating the need for retraining. Our approach addresses two key challenges: the requirement for an initial object mask in the first frame in FoundationPose and issues with tracking loss and automatic rotation for symmetric objects. The algorithm requires only a CAD model of the target object, with the user clicking on its location in the live feed during the initial setup. Once set, the algorithm automatically saves a reference image of the object and, in subsequent runs, employs LightGlue for feature matching between the object and the real-time scene, providing an initial prompt for detection. Tested on the YCB dataset and industrial components such as bleach cleanser and gears, the algorithm demonstrated reliable 6D detection and tracking. By integrating SAM2 and FoundationPose, we effectively mitigated common limitations such as the problem of tracking loss, ensuring continuous and accurate tracking under challenging conditions like occlusion or rapid movement.
Authors: Junming Wang, Wei Yin, Xiaoxiao Long, Xingyu Zhang, Zebin Xing, Xiaoyang Guo, Qian Zhang
Abstract: 3D semantic occupancy prediction networks have demonstrated remarkable capabilities in reconstructing the geometric and semantic structure of 3D scenes, providing crucial information for robot navigation and autonomous driving systems. However, due to their large overhead from dense network structure designs, existing networks face challenges balancing accuracy and latency.In this paper, we introduce OccRWKV, an efficient semantic occupancy network inspired by Receptance Weighted Key Value (RWKV). OccRWKV separates semantics, occupancy prediction, and feature fusion into distinct branches, each incorporating Sem-RWKV and Geo-RWKV blocks. These blocks are designed to capture long-range dependencies, enabling the network to learn domain-specific representation (i.e., semantics and geometry), which enhances prediction accuracy. Leveraging the sparse nature of real-world 3D occupancy, we reduce computational overhead by projecting features into the bird's-eye view (BEV) space and propose a BEV-RWKV block for efficient feature enhancement and fusion. This enables real-time inference at 22.2 FPS without compromising performance. Experiments demonstrate that OccRWKV outperforms the state-of-the-art methods on the SemanticKITTI dataset, achieving a mIoU of 25.1 while being 20 times faster than the best baseline, Co-Occ, making it suitable for real-time deployment on robots to enhance autonomous navigation efficiency. Code and video are available on our project page: \url{https://jmwang0117.github.io/OccRWKV/}.
Authors: Jangyeong Kim, Donggoo Kang, Junyoung Choi, Jeonga Wi, Junho Gwon, Jiun Bae, Dumim Yoon, Junghyun Han
Abstract: Text-to-texture generation has recently attracted increasing attention, but existing methods often suffer from the problems of view inconsistencies, apparent seams, and misalignment between textures and the underlying mesh. In this paper, we propose a robust text-to-texture method for generating consistent and seamless textures that are well aligned with the mesh. Our method leverages state-of-the-art 2D diffusion models, including SDXL and multiple ControlNets, to capture structural features and intricate details in the generated textures. The method also employs a symmetrical view synthesis strategy combined with regional prompts for enhancing view consistency. Additionally, it introduces novel texture blending and soft-inpainting techniques, which significantly reduce the seam regions. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods.
Authors: Javier Galbally, Aleksandrs Cepilovs, Ramon Blanco-Gonzalo, Gillian Ormiston, Oscar Miguel-Hurtado, Istvan Sz. Racz
Abstract: Even though a few initial works have shown on small sets of data some level of bias in the performance of fingerprint recognition technology with respect to certain demographic groups, there is still not sufficient evidence to understand the impact that certain factors such as gender, age or finger-type may have on fingerprint quality and, in turn, also on fingerprint matching accuracy. The present work addresses this still under researched topic, on a large-scale database of operational data containing 10-print impressions of almost 16,000 subjects. The results reached provide further insight into the dependency of fingerprint quality and demographics, and show that there in fact exists a certain degree of performance variability in fingerprint-based recognition systems for different segments of the population. Based on the experimental evaluation, the work points out new observations based on data-driven evidence, provides plausible hypotheses to explain such observations, and concludes with potential follow-up actions that can help to reduce the observed fingerprint quality differences. This way, the current paper can be considered as a contribution to further increase the algorithmic fairness and equality of biometric technology.
Authors: Koichi Ito, Taito Tonosaki, Takafumi Aoki, Tetsushi Ohki, Masakatsu Nishigaki
Abstract: Multibiometrics, which uses multiple biometric traits to improve recognition performance instead of using only one biometric trait to authenticate individuals, has been investigated. Previous studies have combined individually acquired biometric traits or have not fully considered the convenience of the system.Focusing on a single face image, we propose a novel multibiometric method that combines five biometric traits, i.e., face, iris, periocular, nose, eyebrow, that can be extracted from a single face image. The proposed method does not sacrifice the convenience of biometrics since only a single face image is used as input.Through a variety of experiments using the CASIA Iris Distance database, we demonstrate the effectiveness of the proposed multibiometrics method.
Authors: Jihwan Kim, Youngdo Kim, Hyo Seung Lee, Eunseok Seo, Sang Joon Lee
Abstract: Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing deep learning-based phase retrieval methods have technical limitations in generalization performance and three-dimensional (3D) morphology reconstruction from a single-shot hologram of biological cells. In this study, we propose a novel deep learning model, named MorpHoloNet, for single-shot reconstruction of 3D morphology by integrating physics-driven and coordinate-based neural networks. By simulating the optical diffraction of coherent light through a 3D phase shift distribution, the proposed MorpHoloNet is optimized by minimizing the loss between the simulated and input holograms on the sensor plane. Compared to existing DIHM methods that face challenges with twin image and phase retrieval problems, MorpHoloNet enables direct reconstruction of 3D complex light field and 3D morphology of a test sample from its single-shot hologram without requiring multiple phase-shifted holograms or angle scanning. The performance of the proposed MorpHoloNet is validated by reconstructing 3D morphologies and refractive index distributions from synthetic holograms of ellipsoids and experimental holograms of biological cells. The proposed deep learning model is utilized to reconstruct spatiotemporal variations in 3D translational and rotational behaviors and morphological deformations of biological cells from consecutive single-shot holograms captured using DIHM. MorpHoloNet would pave the way for advancing label-free, real-time 3D imaging and dynamic analysis of biological cells under various cellular microenvironments in biomedical and engineering fields.
Authors: Hongchen Wei, Zhenzhong Chen
Abstract: Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding capabilities in modeling long texts. Existing work attempts to address this issue by introducing long video-text pairs during training. However, these approaches require substantial computational and data resources. In this paper, we tackle the challenge of long video understanding from the perspective of context windows, aiming to apply LMMs to long video tasks without retraining on long video datasets. We first conduct an in-depth analysis of why pretrained LMMs struggle to understand lengthy video content, identifying that discrepancies between visual and language modalities lead to different context windows for visual and language tokens, making it difficult to directly extend the visual tokens to match the language context window. Based on this, we propose to adapt LMMs for long video understanding tasks by extending the visual context window, eliminating the need for retraining on large scalelong video datasets. To further mitigate the significant memory consumption caused by long sequences, we introduce a progressive pooling inference strategy that selectively adjusts the spatial resolution of frame embeddings, reducing the number of visual tokens while retaining important spatial information. Across multiple long video understanding benchmarks, our method consistently improves the performance as the number of video frames increases. On the MLVU benchmark, our method outperforms GPT-4o, even though our model size is only 7B. Additionally, in the 256-frame setting, our method reduces memory usage by approximately 45% compared to the baseline, without introducing any performance loss.
Authors: Shunkun Liang, Banglei Guan, Zhenbao Yu, Pengju Sun, Yang Shang
Abstract: Camera calibration is a crucial step in photogrammetry and 3D vision applications. In practical scenarios with a long working distance to cover a wide area, target-based calibration methods become complicated and inflexible due to site limitations. This paper introduces a novel camera calibration method using a collimator system, which can provide a reliable and controllable calibration environment for cameras with varying working distances. Based on the optical geometry of the collimator system, we prove that the relative motion between the target and camera conforms to the spherical motion model, reducing the original 6DOF relative motion to 3DOF pure rotation motion. Furthermore, a closed-form solver for multiple views and a minimal solver for two views are proposed for camera calibration. The performance of our method is evaluated in both synthetic and real-world experiments, which verify the feasibility of calibration using the collimator system and demonstrate that our method is superior to the state-of-the-art methods. Demo code is available at https://github.com/LiangSK98/CollimatorCalibration.
Authors: Yu Zheng, Yueqi Duan, Kangfu Zheng, Hongru Yan, Jiwen Lu, Jie Zhou
Abstract: In this paper, we propose a One-Point-One NeRF (OPONeRF) framework for robust scene rendering. Existing NeRFs are designed based on a key assumption that the target scene remains unchanged between the training and test time. However, small but unpredictable perturbations such as object movements, light changes and data contaminations broadly exist in real-life 3D scenes, which lead to significantly defective or failed rendering results even for the recent state-of-the-art generalizable methods. To address this, we propose a divide-and-conquer framework in OPONeRF that adaptively responds to local scene variations via personalizing appropriate point-wise parameters, instead of fitting a single set of NeRF parameters that are inactive to test-time unseen changes. Moreover, to explicitly capture the local uncertainty, we decompose the point representation into deterministic mapping and probabilistic inference. In this way, OPONeRF learns the sharable invariance and unsupervisedly models the unexpected scene variations between the training and testing scenes. To validate the effectiveness of the proposed method, we construct benchmarks from both realistic and synthetic data with diverse test-time perturbations including foreground motions, illumination variations and multi-modality noises, which are more challenging than conventional generalization and temporal reconstruction benchmarks. Experimental results show that our OPONeRF outperforms state-of-the-art NeRFs on various evaluation metrics through benchmark experiments and cross-scene evaluations. We further show the efficacy of the proposed method via experimenting on other existing generalization-based benchmarks and incorporating the idea of One-Point-One NeRF into other advanced baseline methods.
Authors: Felix Tempel, Espen Alexander F. Ihlen, Inga Str\"umke
Abstract: The neurological condition known as cerebral palsy (CP) first manifests in infancy or early childhood and has a lifelong impact on motor coordination and body movement. CP is one of the leading causes of childhood disabilities, and early detection is crucial for providing appropriate treatment. However, such detection relies on assessments by human experts trained in methods like general movement assessment (GMA). These are not widely accessible, especially in developing countries. Conventional machine learning approaches offer limited predictive performance on CP detection tasks, and the approaches developed by the few available domain experts are generally dataset-specific, restricting their applicability beyond the context for which these were created. To address these challenges, we propose a neural architecture search (NAS) algorithm applying a reinforcement learning update scheme capable of efficiently optimizing for the best architectural and hyperparameter combination to discover the most suitable neural network configuration for detecting CP. Our method performs better on a real-world CP dataset than other approaches in the field, which rely on large ensembles. As our approach is less resource-demanding and performs better, it is particularly suitable for implementation in resource-constrained settings, including rural or developing areas with limited access to medical experts and the required diagnostic tools. The resulting model's lightweight architecture and efficient computation time allow for deployment on devices with limited processing power, reducing the need for expensive infrastructure, and can, therefore, be integrated into clinical workflows to provide timely and accurate support for early CP diagnosis.
Authors: Zicheng Zhang, Ziheng Jia, Haoning Wu, Chunyi Li, Zijian Chen, Yingjie Zhou, Wei Sun, Xiaohong Liu, Xiongkuo Min, Weisi Lin, Guangtao Zhai
Abstract: With the rising interest in research on Large Multi-modal Models (LMMs) for video understanding, many studies have emphasized general video comprehension capabilities, neglecting the systematic exploration into video quality understanding. To address this oversight, we introduce Q-Bench-Video in this paper, a new benchmark specifically designed to evaluate LMMs' proficiency in discerning video quality. a) To ensure video source diversity, Q-Bench-Video encompasses videos from natural scenes, AI-generated Content (AIGC), and Computer Graphics (CG). b) Building on the traditional multiple-choice questions format with the Yes-or-No and What-How categories, we include Open-ended questions to better evaluate complex scenarios. Additionally, we incorporate the video pair quality comparison question to enhance comprehensiveness. c) Beyond the traditional Technical, Aesthetic, and Temporal distortions, we have expanded our evaluation aspects to include the dimension of AIGC distortions, which addresses the increasing demand for video generation. Finally, we collect a total of 2,378 question-answer pairs and test them on 12 open-source & 5 proprietary LMMs. Our findings indicate that while LMMs have a foundational understanding of video quality, their performance remains incomplete and imprecise, with a notable discrepancy compared to human performance. Through Q-Bench-Video, we seek to catalyze community interest, stimulate further research, and unlock the untapped potential of LMMs to close the gap in video quality understanding.
Authors: Can Cui, Siteng Huang, Wenxuan Song, Pengxiang Ding, Min Zhang, Donglin Wang
Abstract: To address the occlusion issues in person Re-Identification (ReID) tasks, many methods have been proposed to extract part features by introducing external spatial information. However, due to missing part appearance information caused by occlusion and noisy spatial information from external model, these purely vision-based approaches fail to correctly learn the features of human body parts from limited training data and struggle in accurately locating body parts, ultimately leading to misaligned part features. To tackle these challenges, we propose a Prompt-guided Feature Disentangling method (ProFD), which leverages the rich pre-trained knowledge in the textual modality facilitate model to generate well-aligned part features. ProFD first designs part-specific prompts and utilizes noisy segmentation mask to preliminarily align visual and textual embedding, enabling the textual prompts to have spatial awareness. Furthermore, to alleviate the noise from external masks, ProFD adopts a hybrid-attention decoder, ensuring spatial and semantic consistency during the decoding process to minimize noise impact. Additionally, to avoid catastrophic forgetting, we employ a self-distillation strategy, retaining pre-trained knowledge of CLIP to mitigate over-fitting. Evaluation results on the Market1501, DukeMTMC-ReID, Occluded-Duke, Occluded-ReID, and P-DukeMTMC datasets demonstrate that ProFD achieves state-of-the-art results. Our project is available at: https://github.com/Cuixxx/ProFD.
Authors: Shu Yang, Zhiyuan Cai, Luyang Luo, Ning Ma, Shuchang Xu, Hao Chen
Abstract: Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed by video fine-tuning" for high-dimensional video data inevitably poses significant performance bottlenecks. Furthermore, in the medical domain, many surgical video tasks encounter additional challenges posed by the limited availability of video data and the necessity for comprehensive spatial-temporal modeling. Recently, Parameter-Efficient Image-to-Video Transfer Learning has emerged as an efficient and effective paradigm for video action recognition tasks, which employs image-level pre-trained models with promising feature transferability and involves cross-modality temporal modeling with minimal fine-tuning. Nevertheless, the effectiveness and generalizability of this paradigm within intricate surgical domain remain unexplored. In this paper, we delve into a novel problem of efficiently adapting image-level pre-trained models to specialize in fine-grained surgical phase recognition, termed as Parameter-Efficient Image-to-Surgical-Video Transfer Learning. Firstly, we develop a parameter-efficient transfer learning benchmark SurgPETL for surgical phase recognition, and conduct extensive experiments with three advanced methods based on ViTs of two distinct scales pre-trained on five large-scale natural and medical datasets. Then, we introduce the Spatial-Temporal Adaptation module, integrating a standard spatial adapter with a novel temporal adapter to capture detailed spatial features and establish connections across temporal sequences for robust spatial-temporal modeling. Extensive experiments on three challenging datasets spanning various surgical procedures demonstrate the effectiveness of SurgPETL with STA.
Authors: Tingzhang Luo, Yichao Liu, Yuanyuan Liu, Andi Zhang, Xin Wang, Chang Tang, Zhe Chen
Abstract: We introduce Facial Expression Category Discovery (FECD), a novel task in the domain of open-world facial expression recognition (O-FER). While Generalized Category Discovery (GCD) has been explored in natural image datasets, applying it to facial expressions presents unique challenges. Specifically, we identify two key biases to better understand these challenges: Theoretical Bias-arising from the introduction of new categories in unlabeled training data, and Practical Bias-stemming from the imbalanced and fine-grained nature of facial expression data. To address these challenges, we propose FER-GCD, an adversarial approach that integrates both implicit and explicit debiasing components. In the implicit debiasing process, we devise F-discrepancy, a novel metric used to estimate the upper bound of Theoretical Bias, helping the model minimize this upper bound through adversarial training. The explicit debiasing process further optimizes the feature generator and classifier to reduce Practical Bias. Extensive experiments on GCD-based FER datasets demonstrate that our FER-GCD framework significantly improves accuracy on both old and new categories, achieving an average improvement of 9.8% over the baseline and outperforming state-of-the-art methods.
Authors: Jiayi Zhao, Alison Wun-lam Yeung, Ali Muhammad, Songjiang Lai, Vincent To-Yee NG
Abstract: Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been developed in recent years, efficiently identifying small-scale rail defects has not yet been studied, especially for categories such as Dirt or Squat on rail surface. To address this challenge, this study utilizes Swin Transformer (SwinT) as baseline and incorporates the Convolutional Block Attention Module (CBAM) for enhancement. Our proposed method integrates CBAM successively within the swin transformer blocks, resulting in significant performance improvement in rail defect detection, particularly for categories with small instance sizes. The proposed framework is named CBAM-Enhanced Swin Transformer in Block Level (CBAM-SwinT-BL). Experiment and ablation study have proven the effectiveness of the framework. The proposed framework has a notable improvement in the accuracy of small size defects, such as dirt and dent categories in RIII dataset, with mAP-50 increasing by +23.0% and +38.3% respectively, and the squat category in MUET dataset also reaches +13.2% higher than the original model. Compares to the original SwinT, CBAM-SwinT-BL increase overall precision around +5% in the MUET dataset and +7% in the RIII dataset, reaching 69.1% and 88.1% respectively. Meanwhile, the additional module CBAM merely extend the model training speed by an average of +0.04s/iteration, which is acceptable compared to the significant improvement in system performance.
Authors: Wiktor Mucha, Kentaro Tanaka, Martin Kampel
Abstract: Stroke represents the third cause of death and disability worldwide, and is recognised as a significant global health problem. A major challenge for stroke survivors is persistent hand dysfunction, which severely affects the ability to perform daily activities and the overall quality of life. In order to regain their functional hand ability, stroke survivors need rehabilitation therapy. However, traditional rehabilitation requires continuous medical support, creating dependency on an overburdened healthcare system. In this paper, we explore the use of egocentric recordings from commercially available smart glasses, specifically RayBan Stories, for remote hand rehabilitation. Our approach includes offline experiments to evaluate the potential of smart glasses for automatic exercise recognition, exercise form evaluation and repetition counting. We present REST-HANDS, the first dataset of egocentric hand exercise videos. Using state-of-the-art methods, we establish benchmarks with high accuracy rates for exercise recognition (98.55%), form evaluation (86.98%), and repetition counting (mean absolute error of 1.33). Our study demonstrates the feasibility of using egocentric video from smart glasses for remote rehabilitation, paving the way for further research.
Authors: Doyi Kim, Minseok Seo, Hakjin Lee, Junghoon Seo
Abstract: The growing impact of global climate change amplifies the need for accurate and reliable weather forecasting. Traditional autoregressive approaches, while effective for temporal modeling, suffer from error accumulation in long-term prediction tasks. The lead time embedding method has been suggested to address this issue, but it struggles to maintain crucial correlations in atmospheric events. To overcome these challenges, we propose the Masked Autoregressive Model for Weather Forecasting (MAM4WF). This model leverages masked modeling, where portions of the input data are masked during training, allowing the model to learn robust spatiotemporal relationships by reconstructing the missing information. MAM4WF combines the advantages of both autoregressive and lead time embedding methods, offering flexibility in lead time modeling while iteratively integrating predictions. We evaluate MAM4WF across weather, climate forecasting, and video frame prediction datasets, demonstrating superior performance on five test datasets.
Authors: Thomas H. Schmitt, Maximilian Bundscherer, Tobias Bocklet
Abstract: In the food industry, reprocessing returned product is a vital step to increase resource efficiency. [SBB23] presented an AI application that automates the tracking of returned bread buns. We extend their work by creating an expanded dataset comprising 2432 images and a wider range of baked goods. To increase model robustness, we use generative models pix2pix and CycleGAN to create synthetic images. We train state-of-the-art object detection model YOLOv9 and YOLOv8 on our detection task. Our overall best-performing model achieved an average precision AP@0.5 of 90.3% on our test set.
Authors: Peer Stelldinger, Nils Sch\"onherr, Justus Biermann
Abstract: Accurate camera calibration is a well-known and widely used task in computer vision that has been researched for decades. However, the standard approach based on checkerboard calibration patterns has some drawbacks that limit its applicability. For example, the calibration pattern must be completely visible without any occlusions. Alternative solutions such as ChArUco boards allow partial occlusions, but require a higher camera resolution due to the fine details of the position encoding. We present a new calibration pattern that combines the advantages of checkerboard calibration patterns with a lightweight position coding that can be decoded at very low resolutions. The decoding algorithm includes error correction and is computationally efficient. The whole approach is backward compatible to both checkerboard calibration patterns and several checkerboard calibration algorithms. Furthermore, the method can be used not only for camera calibration but also for camera pose estimation and marker-based object localization tasks.
Authors: Maximilian Bundscherer, Thomas H. Schmitt, Tobias Bocklet
Abstract: In industrial manufacturing of glass bottles, quality control of bottle prints is necessary as numerous factors can negatively affect the printing process. Even minor defects in the bottle prints must be detected despite reflections in the glass or manufacturing-related deviations. In cooperation with our medium-sized industrial partner, two ML-based approaches for quality control of these bottle prints were developed and evaluated, which can also be used in this challenging scenario. Our first approach utilized different filters to supress reflections (e.g. Sobel or Canny) and image quality metrics for image comparison (e.g. MSE or SSIM) as features for different supervised classification models (e.g. SVM or k-Neighbors), which resulted in an accuracy of 84%. The images were aligned based on the ORB algorithm, which allowed us to estimate the rotations of the prints, which may serve as an indicator for anomalies in the manufacturing process. In our second approach, we fine-tuned different pre-trained CNN models (e.g. ResNet or VGG) for binary classification, which resulted in an accuracy of 87%. Utilizing Grad-Cam on our fine-tuned ResNet-34, we were able to localize and visualize frequently defective bottle print regions. This method allowed us to provide insights that could be used to optimize the actual manufacturing process. This paper also describes our general approach and the challenges we encountered in practice with data collection during ongoing production, unsupervised preselection, and labeling.
Authors: Roland Kammerbauer, Thomas H. Schmitt, Tobias Bocklet
Abstract: In the woodworking industry, a huge amount of effort has to be invested into the initial quality assessment of the raw material. In this study we present an AI model to detect, quantify and localize defects on wooden logs. This model aims to both automate the quality control process and provide a more consistent and reliable quality assessment. For this purpose a dataset of 1424 sample images of wood logs is created. A total of 5 annotators possessing different levels of expertise is involved in dataset creation. An inter-annotator agreement analysis is conducted to analyze the impact of expertise on the annotation task and to highlight subjective differences in annotator judgement. We explore, train and fine-tune the state-of-the-art InternImage and ONE-PEACE architectures for semantic segmentation. The best model created achieves an average IoU of 0.71, and shows detection and quantification capabilities close to the human annotators.
Authors: Deheng Zhang, Jingyu Wang, Shaofei Wang, Marko Mihajlovic, Sergey Prokudin, Hendrik P. A. Lensch, Siyu Tang
Abstract: In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornerstone of our method is a two-stage approach for learning a better factorization of scene parameters. In the first stage, we develop a reflection-aware radiance field using a neural signed distance field (SDF) as the geometry representation and deploy an MLP (multilayer perceptron) to estimate indirect illumination. In the second stage, we introduce a novel information-sharing network structure to jointly learn the radiance field and the physically based factorization of the scene. For the physically based factorization, to reduce the noise caused by Monte Carlo sampling, we apply a split-sum approximation with a simplified Disney BRDF and cube mipmap as the environment light representation. In the relighting phase, to enhance the quality of indirect illumination, we propose a second split-sum algorithm to trace secondary rays under the split-sum rendering framework.Furthermore, there is no dataset or protocol available to quantitatively evaluate the inverse rendering performance for glossy objects. To assess the quality of material reconstruction and relighting, we have created a new dataset with ground truth BRDF parameters and relighting results. Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.
Authors: Huilin Deng, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang
Abstract: Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, demonstrating excellent research value in flexible industrial manufacturing. However, existing ZSAD methods are limited by closed-world settings, struggling to unseen defects with predefined prompts. Recently, adapting Multimodal Large Language Models (MLLMs) for Industrial Anomaly Detection (IAD) presents a viable solution. Unlike fixed-prompt methods, MLLMs exhibit a generative paradigm with open-ended text interpretation, enabling more adaptive anomaly analysis. However, this adaption faces inherent challenges as anomalies often manifest in fine-grained regions and exhibit minimal visual discrepancies from normal samples. To address these challenges, we propose a novel framework VMAD (Visual-enhanced MLLM Anomaly Detection) that enhances MLLM with visual-based IAD knowledge and fine-grained perception, simultaneously providing precise detection and comprehensive analysis of anomalies. Specifically, we design a Defect-Sensitive Structure Learning scheme that transfers patch-similarities cues from visual branch to our MLLM for improved anomaly discrimination. Besides, we introduce a novel visual projector, Locality-enhanced Token Compression, which mines multi-level features in local contexts to enhance fine-grained detection. Furthermore, we introduce the Real Industrial Anomaly Detection (RIAD), a comprehensive IAD dataset with detailed anomaly descriptions and analyses, offering a valuable resource for MLLM-based IAD development. Extensive experiments on zero-shot benchmarks, including MVTec-AD, Visa, WFDD, and RIAD datasets, demonstrate our superior performance over state-of-the-art methods. The code and dataset will be available soon.
Authors: Fulong Ma, Weiqing Qi, Guoyang Zhao, Ming Liu, Jun Ma
Abstract: Data augmentation is one of the most common tools in deep learning, underpinning many recent advances including tasks such as classification, detection, and semantic segmentation. The standard approach to data augmentation involves simple transformations like rotation and flipping to generate new images. However, these new images often lack diversity along the main semantic dimensions within the data. Traditional data augmentation methods cannot alter high-level semantic attributes such as the presence of vehicles, trees, and buildings in a scene to enhance data diversity. In recent years, the rapid development of generative models has injected new vitality into the field of data augmentation. In this paper, we address the lack of diversity in data augmentation for road detection task by using a pre-trained text-to-image diffusion model to parameterize image-to-image transformations. Our method involves editing images using these diffusion models to change their semantics. In essence, we achieve this goal by erasing instances of real objects from the original dataset and generating new instances with similar semantics in the erased regions using the diffusion model, thereby expanding the original dataset. We evaluate our approach on the KITTI road dataset and achieve the best results compared to other data augmentation methods, which demonstrates the effectiveness of our proposed development.
Authors: Fulong Ma, Guoyang Zhao, Weiqing Qi, Ming Liu, Jun Ma
Abstract: Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid foundation for models, improving generalization abilities and accelerating convergence rates. This approach has seen significant success in the fields of natural language processing and computer vision. However, traditional pre-training methods necessitate large datasets and substantial computational resources, and they can only learn shared features through prolonged training and struggle to capture deeper, task-specific features. In this paper, we propose a task-oriented pre-training method that begins with generating redundant segmentation proposals using the Segment Anything (SAM) model. We then introduce a Specific Category Enhancement Fine-tuning (SCEF) strategy for fine-tuning the Contrastive Language-Image Pre-training (CLIP) model to select proposals most closely related to the drivable area from those generated by SAM. This approach can generate a lot of coarse training data for pre-training models, which are further fine-tuned using manually annotated data, thereby improving model's performance. Comprehensive experiments conducted on the KITTI road dataset demonstrate that our task-oriented pre-training method achieves an all-around performance improvement compared to models without pre-training. Moreover, our pre-training method not only surpasses traditional pre-training approach but also achieves the best performance compared to state-of-the-art self-training methods.
Authors: Fulong Ma, Peng Hou, Yuxuan Liu, Ming Liu, Jun Ma
Abstract: Road curbs are considered as one of the crucial and ubiquitous traffic features, which are essential for ensuring the safety of autonomous vehicles. Current methods for detecting curbs primarily rely on camera imagery or LiDAR point clouds. Image-based methods are vulnerable to fluctuations in lighting conditions and exhibit poor robustness, while methods based on point clouds circumvent the issues associated with lighting variations. However, it is the typical case that significant processing delays are encountered due to the voluminous amount of 3D points contained in each frame of the point cloud data. Furthermore, the inherently unstructured characteristics of point clouds poses challenges for integrating the latest deep learning advancements into point cloud data applications. To address these issues, this work proposes an annotation-free curb detection method leveraging Altitude Difference Image (ADI), which effectively mitigates the aforementioned challenges. Given that methods based on deep learning generally demand extensive, manually annotated datasets, which are both expensive and labor-intensive to create, we present an Automatic Curb Annotator (ACA) module. This module utilizes a deterministic curb detection algorithm to automatically generate a vast quantity of training data. Consequently, it facilitates the training of the curb detection model without necessitating any manual annotation of data. Finally, by incorporating a post-processing module, we manage to achieve state-of-the-art results on the KITTI 3D curb dataset with considerably reduced processing delays compared to existing methods, which underscores the effectiveness of our approach in curb detection tasks.
Authors: Arunava Chakravarty, Taha Emre, Dmitrii Lachinov, Antoine Rivail, Hendrik Scholl, Lars Fritsche, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunovi\'c
Abstract: Predicting future disease progression risk from medical images is challenging due to patient heterogeneity, and subtle or unknown imaging biomarkers. Moreover, deep learning (DL) methods for survival analysis are susceptible to image domain shifts across scanners. We tackle these issues in the task of predicting late dry Age-related Macular Degeneration (dAMD) onset from retinal OCT scans. We propose a novel DL method for survival prediction to jointly predict from the current scan a risk score, inversely related to time-to-conversion, and the probability of conversion within a time interval $t$. It uses a family of parallel hyperplanes generated by parameterizing the bias term as a function of $t$. In addition, we develop unsupervised losses based on intra-subject image pairs to ensure that risk scores increase over time and that future conversion predictions are consistent with AMD stage prediction using actual scans of future visits. Such losses enable data-efficient fine-tuning of the trained model on new unlabeled datasets acquired with a different scanner. Extensive evaluation on two large datasets acquired with different scanners resulted in a mean AUROCs of 0.82 for Dataset-1 and 0.83 for Dataset-2, across prediction intervals of 6,12 and 24 months.
Authors: Cheng Zhang, Dong Gong, Jiumei He, Yu Zhu, Jinqiu Sun, Yanning Zhang
Abstract: Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restoration methods, they overlook the utilization of commonalities and specificities within multi-task restoration, thereby impeding the model's performance. Inspired by the success of deep generative models and fine-tuning techniques, we proposed a universal image restoration framework based on multiple low-rank adapters (LoRA) from multi-domain transfer learning. Our framework leverages the pre-trained generative model as the shared component for multi-degradation restoration and transfers it to specific degradation image restoration tasks using low-rank adaptation. Additionally, we introduce a LoRA composing strategy based on the degradation similarity, which adaptively combines trained LoRAs and enables our model to be applicable for mixed degradation restoration. Extensive experiments on multiple and mixed degradations demonstrate that the proposed universal image restoration method not only achieves higher fidelity and perceptual image quality but also has better generalization ability than other unified image restoration models. Our code is available at https://github.com/Justones/UIR-LoRA.
Authors: Oleh Kolner, Thomas Ortner, Stanis{\l}aw Wo\'zniak, Angeliki Pantazi
Abstract: Human capabilities in understanding visual relations are far superior to those of AI systems, especially for previously unseen objects. For example, while AI systems struggle to determine whether two such objects are visually the same or different, humans can do so with ease. Active vision theories postulate that the learning of visual relations is grounded in actions that we take to fixate objects and their parts by moving our eyes. In particular, the low-dimensional spatial information about the corresponding eye movements is hypothesized to facilitate the representation of relations between different image parts. Inspired by these theories, we develop a system equipped with a novel Glimpse-based Active Perception (GAP) that sequentially glimpses at the most salient regions of the input image and processes them at high resolution. Importantly, our system leverages the locations stemming from the glimpsing actions, along with the visual content around them, to represent relations between different parts of the image. The results suggest that the GAP is essential for extracting visual relations that go beyond the immediate visual content. Our approach reaches state-of-the-art performance on several visual reasoning tasks being more sample-efficient, and generalizing better to out-of-distribution visual inputs than prior models.
Authors: Chen Xie, Ciyun Lin, Xiaoyu Zheng, Bowen Gong, Dayong Wu, Antonio M. L\'opez
Abstract: Understanding and predicting pedestrian crossing behavioral intention is crucial for autonomous vehicles driving safety. Nonetheless, challenges emerge when using promising images or environmental context masks to extract various factors for time-series network modeling, causing pre-processing errors or a loss in efficiency. Typically, pedestrian positions captured by onboard cameras are often distorted and do not accurately reflect their actual movements. To address these issues, GTransPDM -- a Graph-embedded Transformer with a Position Decoupling Module -- was developed for pedestrian crossing intention prediction by leveraging multi-modal features. First, a positional decoupling module was proposed to decompose the pedestrian lateral movement and simulate depth variations in the image view. Then, a graph-embedded Transformer was designed to capture the spatial-temporal dynamics of human pose skeletons, integrating essential factors such as position, skeleton, and ego-vehicle motion. Experimental results indicate that the proposed method achieves 92% accuracy on the PIE dataset and 87% accuracy on the JAAD dataset, with a processing speed of 0.05ms. It outperforms the state-of-the-art in comparison.
Authors: Shalini Sarode, Muhammad Saif Ullah Khan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
Abstract: We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between student and multiple mentors. Unlike traditional methods that rely on fixed mentor-student relationships, our framework dynamically selects and adapts the teaching strategies of diverse mentors based on their effectiveness for each data sample. ClassroomKD comprises two main modules: the Knowledge Filtering (KF) Module and the Mentoring Module. The KF Module dynamically ranks mentors based on their performance for each input, activating only high-quality mentors to minimize error accumulation and prevent information loss. The Mentoring Module adjusts the distillation strategy by tuning each mentor's influence according to the performance gap between the student and mentors, effectively modulating the learning pace. Extensive experiments on image classification (CIFAR-100 and ImageNet) and 2D human pose estimation (COCO Keypoints and MPII Human Pose) demonstrate that ClassroomKD significantly outperforms existing knowledge distillation methods. Our results highlight that a dynamic and adaptive approach to mentor selection and guidance leads to more effective knowledge transfer, paving the way for enhanced model performance through distillation.
Authors: Iira H\"akkinen, Iaroslav Melekhov, Erik Englesson, Hossein Azizpour, Juho Kannala
Abstract: The field of medical image segmentation is hindered by the scarcity of large, publicly available annotated datasets. Not all datasets are made public for privacy reasons, and creating annotations for a large dataset is time-consuming and expensive, as it requires specialized expertise to accurately identify regions of interest (ROIs) within the images. To address these challenges, we evaluate the performance of the Segment Anything Model (SAM) as an annotation tool for medical data by using it to produce so-called "pseudo labels" on the Medical Segmentation Decathlon (MSD) computed tomography (CT) tasks. The pseudo labels are then used in place of ground truth labels to train a UNet model in a weakly-supervised manner. We experiment with different prompt types on SAM and find that the bounding box prompt is a simple yet effective method for generating pseudo labels. This method allows us to develop a weakly-supervised model that performs comparably to a fully supervised model.
Authors: Nikolai K\"orber, Eduard Kromer, Andreas Siebert, Sascha Hauke, Daniel Mueller-Gritschneder, Bj\"orn Schuller
Abstract: We introduce PerCo (SD), a perceptual image compression method based on Stable Diffusion v2.1, targeting the ultra-low bit range. PerCo (SD) serves as an open and competitive alternative to the state-of-the-art method PerCo, which relies on a proprietary variant of GLIDE and remains closed to the public. In this work, we review the theoretical foundations, discuss key engineering decisions in adapting PerCo to the Stable Diffusion ecosystem, and provide a comprehensive comparison, both quantitatively and qualitatively. On the MSCOCO-30k dataset, PerCo (SD) demonstrates improved perceptual characteristics at the cost of higher distortion. We partly attribute this gap to the different model capacities being used (866M vs. 1.4B). We hope our work contributes to a deeper understanding of the underlying mechanisms and paves the way for future advancements in the field. Code and trained models will be released at https://github.com/Nikolai10/PerCo.
Authors: Abid Ali, Rui Dai, Ashish Marisetty, Guillaume Astruc, Monique Thonnat, Jean-Marc Odobez, Susanne Th\"ummler, Francois Bremond
Abstract: The computer vision community has explored dyadic interactions for atomic actions such as pushing, carrying-object, etc. However, with the advancement in deep learning models, there is a need to explore more complex dyadic situations such as loose interactions. These are interactions where two people perform certain atomic activities to complete a global action irrespective of temporal synchronisation and physical engagement, like cooking-together for example. Analysing these types of dyadic-interactions has several useful applications in the medical domain for social-skills development and mental health diagnosis. To achieve this, we propose a novel dual-path architecture to capture the loose interaction between two individuals. Our model learns global abstract features from each stream via a CNNs backbone and fuses them using a new Global-Layer-Attention module based on a cross-attention strategy. We evaluate our model on real-world autism diagnoses such as our Loose-Interaction dataset, and the publicly available Autism dataset for loose interactions. Our network achieves baseline results on the Loose-Interaction and SOTA results on the Autism datasets. Moreover, we study different social interactions by experimenting on a publicly available dataset i.e. NTU-RGB+D (interactive classes from both NTU-60 and NTU-120). We have found that different interactions require different network designs. We also compare a slightly different version of our method by incorporating time information to address tight interactions achieving SOTA results.
Authors: Zijia Kuang, Zike Yan, Hao Zhao, Guyue Zhou, Hongbin Zha
Abstract: We introduce a NeRF-based active mapping system that enables efficient and robust exploration of large-scale indoor environments. The key to our approach is the extraction of a generalized Voronoi graph (GVG) from the continually updated neural map, leading to the synergistic integration of scene geometry, appearance, topology, and uncertainty. Anchoring uncertain areas induced by the neural map to the vertices of GVG allows the exploration to undergo adaptive granularity along a safe path that traverses unknown areas efficiently. Harnessing a modern hybrid NeRF representation, the proposed system achieves competitive results in terms of reconstruction accuracy, coverage completeness, and exploration efficiency even when scaling up to large indoor environments. Extensive results at different scales validate the efficacy of the proposed system.
Authors: Mingxu Feng, Dian Chao, Peng Zheng, Yang Yang
Abstract: This report provides a detailed description of the method we explored and proposed in the OSR Challenge at the OOD-CV Workshop during ECCV 2024. The challenge required identifying whether a test sample belonged to the semantic classes of a classifier's training set, a task known as open-set recognition (OSR). Using the Semantic Shift Benchmark (SSB) for evaluation, we focused on ImageNet1k as the in-distribution (ID) dataset and a subset of ImageNet21k as the out-of-distribution (OOD) dataset.To address this, we proposed a hybrid approach, experimenting with the fusion of various post-hoc OOD detection techniques and different Test-Time Augmentation (TTA) strategies. Additionally, we evaluated the impact of several base models on the final performance. Our best-performing method combined Test-Time Augmentation with the post-hoc OOD techniques, achieving a strong balance between AUROC and FPR95 scores. Our approach resulted in AUROC: 79.77 (ranked 5th) and FPR95: 61.44 (ranked 2nd), securing second place in the overall competition.
Authors: Junpeng Jing, Ye Mao, Anlan Qiu, Krystian Mikolajczyk
Abstract: Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods within this area. Recent learning-based methods often focus on optimizing performance for independent stereo pairs, leading to temporal inconsistencies in videos. Existing video methods typically employ sliding window operation over time dimension, which can result in low-frequency oscillations corresponding to the window size. To address these challenges, we propose a bidirectional alignment mechanism for adjacent frames as a fundamental operation. Building on this, we introduce a novel video processing framework, BiDAStereo, and a plugin stabilizer network, BiDAStabilizer, compatible with general image-based methods. Regarding datasets, current synthetic object-based and indoor datasets are commonly used for training and benchmarking, with a lack of outdoor nature scenarios. To bridge this gap, we present a realistic synthetic dataset and benchmark focused on natural scenes, along with a real-world dataset captured by a stereo camera in diverse urban scenes for qualitative evaluation. Extensive experiments on in-domain, out-of-domain, and robustness evaluation demonstrate the contribution of our methods and datasets, showcasing improvements in prediction quality and achieving state-of-the-art results on various commonly used benchmarks. The project page, demos, code, and datasets are available at: \url{https://tomtomtommi.github.io/BiDAVideo/}.
Authors: M\'elanie Gaillochet, Christian Desrosiers, Herv\'e Lombaert
Abstract: Foundation models such as the recently introduced Segment Anything Model (SAM) have achieved remarkable results in image segmentation tasks. However, these models typically require user interaction through handcrafted prompts such as bounding boxes, which limits their deployment to downstream tasks. Adapting these models to a specific task with fully labeled data also demands expensive prior user interaction to obtain ground-truth annotations. This work proposes to replace conditioning on input prompts with a lightweight module that directly learns a prompt embedding from the image embedding, both of which are subsequently used by the foundation model to output a segmentation mask. Our foundation models with learnable prompts can automatically segment any specific region by 1) modifying the input through a prompt embedding predicted by a simple module, and 2) using weak labels (tight bounding boxes) and few-shot supervision (10 samples). Our approach is validated on MedSAM, a version of SAM fine-tuned for medical images, with results on three medical datasets in MR and ultrasound imaging. Our code is available on https://github.com/Minimel/MedSAMWeakFewShotPromptAutomation.
URLs: https://github.com/Minimel/MedSAMWeakFewShotPromptAutomation.
Authors: Yasaman Haghighi, Celine Demonsant, Panagiotis Chalimourdas, Maryam Tavasoli Naeini, Jhon Kevin Munoz, Bladimir Bacca, Silvan Suter, Matthieu Gani, Alexandre Alahi
Abstract: In this paper, we introduce HEADS-UP, the first egocentric dataset collected from head-mounted cameras, designed specifically for trajectory prediction in blind assistance systems. With the growing population of blind and visually impaired individuals, the need for intelligent assistive tools that provide real-time warnings about potential collisions with dynamic obstacles is becoming critical. These systems rely on algorithms capable of predicting the trajectories of moving objects, such as pedestrians, to issue timely hazard alerts. However, existing datasets fail to capture the necessary information from the perspective of a blind individual. To address this gap, HEADS-UP offers a novel dataset focused on trajectory prediction in this context. Leveraging this dataset, we propose a semi-local trajectory prediction approach to assess collision risks between blind individuals and pedestrians in dynamic environments. Unlike conventional methods that separately predict the trajectories of both the blind individual (ego agent) and pedestrians, our approach operates within a semi-local coordinate system, a rotated version of the camera's coordinate system, facilitating the prediction process. We validate our method on the HEADS-UP dataset and implement the proposed solution in ROS, performing real-time tests on an NVIDIA Jetson GPU through a user study. Results from both dataset evaluations and live tests demonstrate the robustness and efficiency of our approach.
Authors: Akshatha Arodi, Margaux Luck, Jean-Luc Bedwani, Aldo Zaimi, Ge Li, Nicolas Pouliot, Julien Beaudry, Ga\'etan Marceau Caron
Abstract: Machine learning models are increasingly being deployed in real-world contexts. However, systematic studies on their transferability to specific and critical applications are underrepresented in the research literature. An important example is visual anomaly detection (VAD) for robotic power line inspection. While existing VAD methods perform well in controlled environments, real-world scenarios present diverse and unexpected anomalies that current datasets fail to capture. To address this gap, we introduce $\textit{CableInspect-AD}$, a high-quality, publicly available dataset created and annotated by domain experts from Hydro-Qu\'ebec, a Canadian public utility. This dataset includes high-resolution images with challenging real-world anomalies, covering defects with varying severity levels. To address the challenges of collecting diverse anomalous and nominal examples for setting a detection threshold, we propose an enhancement to the celebrated PatchCore algorithm. This enhancement enables its use in scenarios with limited labeled data. We also present a comprehensive evaluation protocol based on cross-validation to assess models' performances. We evaluate our $\textit{Enhanced-PatchCore}$ for few-shot and many-shot detection, and Vision-Language Models for zero-shot detection. While promising, these models struggle to detect all anomalies, highlighting the dataset's value as a challenging benchmark for the broader research community. Project page: https://mila-iqia.github.io/cableinspect-ad/.
Authors: Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai, Gengyuan Zhang, Yunpu Ma, Volker Tresp
Abstract: In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-to-end models. However, long video understanding presents unique challenges due to the complexity of reasoning over extended timespans, even for zero-shot LLM-based approaches. The challenge of information redundancy in long videos prompts the question of what specific information is essential for large language models (LLMs) and how to leverage them for complex spatial-temporal reasoning in long-form video analysis. We propose a framework VideoINSTA, i.e. INformative Spatial-TemporAl Reasoning for zero-shot long-form video understanding. VideoINSTA contributes (1) a zero-shot framework for long video understanding using LLMs; (2) an event-based temporal reasoning and content-based spatial reasoning approach for LLMs to reason over spatial-temporal information in videos; (3) a self-reflective information reasoning scheme balancing temporal factors based on information sufficiency and prediction confidence. Our model significantly improves the state-of-the-art on three long video question-answering benchmarks: EgoSchema, NextQA, and IntentQA, and the open question answering dataset ActivityNetQA. The code is released here: https://github.com/mayhugotong/VideoINSTA.
Authors: Mahamudul Hasan, Md Maruf Al Hossain Prince, Mohammad Samar Ansari, Sabrina Jahan, Abu Saleh Musa Miah, Jungpil Shin
Abstract: Fire hazards are extremely dangerous, particularly in sectors such as the transportation industry, where political unrest increases the likelihood of their occurrence. By employing IP cameras to facilitate the setup of fire detection systems on transport vehicles, losses from fire events may be prevented proactively. However, the development of lightweight fire detection models is required due to the computational constraints of the embedded systems within these cameras. We introduce FireLite, a low-parameter convolutional neural network (CNN) designed for quick fire detection in contexts with limited resources, in response to this difficulty. With an accuracy of 98.77\%, our model -- which has just 34,978 trainable parameters achieves remarkable performance numbers. It also shows a validation loss of 8.74 and peaks at 98.77 for precision, recall, and F1-score measures. Because of its precision and efficiency, FireLite is a promising solution for fire detection in resource-constrained environments.
Authors: Boyu Han, Qianqian Xu, Zhiyong Yang, Shilong Bao, Peisong Wen, Yangbangyan Jiang, Qingming Huang
Abstract: The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://github.com/boyuh/AUCSeg.
Authors: George R. Nahass, Emma Koehler, Nicholas Tomaras, Danny Lopez, Madison Cheung, Alexander Palacios, Jefferey Peterson, Sacha Hubschman, Kelsey Green, Chad A. Purnell, Pete Setabutr, Ann Q. Tran, Darvin Yi
Abstract: Periorbital segmentation and distance prediction using deep learning allows for the objective quantification of disease state, treatment monitoring, and remote medicine. However, there are currently no reports of segmentation datasets for the purposes of training deep learning models with sub mm accuracy on the regions around the eyes. All images (n=2842) had the iris, sclera, lid, caruncle, and brow segmented by five trained annotators. Here, we validate this dataset through intra and intergrader reliability tests and show the utility of the data in training periorbital segmentation networks. All the annotations are publicly available for free download. Having access to segmentation datasets designed specifically for oculoplastic surgery will permit more rapid development of clinically useful segmentation networks which can be leveraged for periorbital distance prediction and disease classification. In addition to the annotations, we also provide an open-source toolkit for periorbital distance prediction from segmentation masks. The weights of all models have also been open-sourced and are publicly available for use by the community.
Authors: Michal Balcerak, Tamaz Amiranashvili, Andreas Wagner, Jonas Weidner, Petr Karnakov, Johannes C. Paetzold, Ivan Ezhov, Petros Koumoutsakos, Benedikt Wiestler, Bjoern Menze
Abstract: Physical models in the form of partial differential equations represent an important prior for many under-constrained problems. One example is tumor treatment planning, which heavily depends on accurate estimates of the spatial distribution of tumor cells in a patient's anatomy. Medical imaging scans can identify the bulk of the tumor, but they cannot reveal its full spatial distribution. Tumor cells at low concentrations remain undetectable, for example, in the most frequent type of primary brain tumors, glioblastoma. Deep-learning-based approaches fail to estimate the complete tumor cell distribution due to a lack of reliable training data. Most existing works therefore rely on physics-based simulations to match observed tumors, providing anatomically and physiologically plausible estimations. However, these approaches struggle with complex and unknown initial conditions and are limited by overly rigid physical models. In this work, we present a novel method that balances data-driven and physics-based cost functions. In particular, we propose a unique discretization scheme that quantifies the adherence of our learned spatiotemporal tumor and brain tissue distributions to their corresponding growth and elasticity equations. This quantification, serving as a regularization term rather than a hard constraint, enables greater flexibility and proficiency in assimilating patient data than existing models. We demonstrate improved coverage of tumor recurrence areas compared to existing techniques on real-world data from a cohort of patients. The method holds the potential to enhance clinical adoption of model-driven treatment planning for glioblastoma.
Authors: Yinzheng Zhao, Zhihao Zhao, Junjie Yang, Li Li, M. Ali Nasseri, Daniel Zapp
Abstract: Purpose: To investigate the changes in retinal vascular structures associated various stages of myopia by designing automated software based on an artif intelligencemodel. Methods: The study involved 1324 pediatric participants from the National Childr Medical Center in China, and 2366 high-quality retinal images and correspon refractive parameters were obtained and analyzed. Spherical equivalent refrac(SER) degree was calculated. We proposed a data analysis model based c combination of the Convolutional Neural Networks (CNN) model and the atter module to classify images, segment vascular structures, and measure vasc parameters, such as main angle (MA), branching angle (BA), bifurcation edge al(BEA) and bifurcation edge coefficient (BEC). One-way ANOVA compared param measurements betweenthenormalfundus,lowmyopia,moderate myopia,and high myopia group. Results: There were 279 (12.38%) images in normal group and 384 (16.23%) images in the high myopia group. Compared normal fundus, the MA of fundus vessels in different myopic refractive groups significantly reduced (P = 0.006, P = 0.004, P = 0.019, respectively), and performance of the venous system was particularly obvious (P<0.001). At the sa time, the BEC decreased disproportionately (P<0.001). Further analysis of fundus vascular parameters at different degrees of myopia showed that there were also significant differences in BA and branching coefficient (BC). The arterial BA value of the fundus vessel in the high myopia group was lower than that of other groups (P : 0.032, 95% confidence interval [Ci], 0.22-4.86), while the venous BA values increased(P = 0.026). The BEC values of high myopia were higher than those of low and moderate myopia groups. When the loss function of our data classification model converged to 0.09,the model accuracy reached 94.19%
Authors: Jiacong Wang, Bohong Wu, Haiyong Jiang, Xun Zhou, Xin Xiao, Haoyuan Guo, Jun Xiao
Abstract: Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated multi-modal data construction pipeline that organizes the final generation output into a Python code format. The pipeline leverages the VLM itself to extract cross-modal information via different prompts and filter the generated outputs again via a consistency filtering strategy. Experiments have demonstrated the high quality of W2C by improving various existing visual question answering and visual grounding benchmarks across different VLMs. Further analysis also demonstrates that the new code parsing ability of VLMs presents better cross-modal equivalence than the commonly used detail caption ability. Our code is available at https://github.com/foundation-multimodal-models/World2Code.
URLs: https://github.com/foundation-multimodal-models/World2Code.
Authors: Amira Guesmi, Muhammad Shafique
Abstract: Autonomous vehicles (AVs) rely heavily on LiDAR (Light Detection and Ranging) systems for accurate perception and navigation, providing high-resolution 3D environmental data that is crucial for object detection and classification. However, LiDAR systems are vulnerable to adversarial attacks, which pose significant challenges to the safety and robustness of AVs. This survey presents a thorough review of the current research landscape on physical adversarial attacks targeting LiDAR-based perception systems, covering both single-modality and multi-modality contexts. We categorize and analyze various attack types, including spoofing and physical adversarial object attacks, detailing their methodologies, impacts, and potential real-world implications. Through detailed case studies and analyses, we identify critical challenges and highlight gaps in existing attacks for LiDAR-based systems. Additionally, we propose future research directions to enhance the security and resilience of these systems, ultimately contributing to the safer deployment of autonomous vehicles.
Authors: Muhammad Saif Ullah Khan, Muhammad Ahmed Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker
Abstract: This paper reformulates cross-dataset human pose estimation as a continual learning task, aiming to integrate new keypoints and pose variations into existing models without losing accuracy on previously learned datasets. We benchmark this formulation against established regularization-based methods for mitigating catastrophic forgetting, including EWC, LFL, and LwF. Moreover, we propose a novel regularization method called Importance-Weighted Distillation (IWD), which enhances conventional LwF by introducing a layer-wise distillation penalty and dynamic temperature adjustment based on layer importance for previously learned knowledge. This allows for a controlled adaptation to new tasks that respects the stability-plasticity balance critical in continual learning. Through extensive experiments across three datasets, we demonstrate that our approach outperforms existing regularization-based continual learning strategies. IWD shows an average improvement of 3.60\% over the state-of-the-art LwF method. The results highlight the potential of our method to serve as a robust framework for real-world applications where models must evolve with new data without forgetting past knowledge.
Authors: Ruiqiang Xiao, Xiaohu Chen
Abstract: Crack segmentation is crucial in civil engineering, particularly for assessing pavement integrity and ensuring the durability of infrastructure. While deep learning has advanced RGB-based segmentation, performance degrades under adverse conditions like low illumination or motion blur. Thermal imaging offers complementary information by capturing emitted radiation, improving crack detection in challenging environments. Combining RGB and thermal images (RGB-T) for crack segmentation shows promise in complex real-world conditions, such as adverse weather, yet research in this area remains limited. Current RGB-T segmentation methods often fail to fully exploit the complementary relationships between modalities at various levels of interaction. To address this, we propose IRFusionFormer, a novel model for crack segmentation that effectively integrates RGB and thermal data. Our Efficient RGB-T Cross Fusion Module captures multi-scale relationships and long-range dependencies between modalities without significant computational overhead. Additionally, we introduce the Interaction-Hybrid-Branch-Supervision framework, which enhances interaction between modalities by distributing fused features across branches with joint supervision. To maintain the topological structure of cracks, we introduce a novel topology-based loss function that preserves connectivity during training. Our method achieves state-of-the-art performance, with a Dice score of 90.01% and an IoU of 81.83%, significantly improving robustness and accuracy in varying environmental conditions. These advancements address key challenges in pavement crack segmentation, offering a more reliable and efficient solution. For access to the codes, data, and models from this study, visit https://github.com/sheauhuu/IRFusionFormer
Authors: Lingling Cai, Kang Zhao, Hangjie Yuan, Yingya Zhang, Shiwei Zhang, Kejie Huang
Abstract: Text-to-video diffusion models have made remarkable advancements. Driven by their ability to generate temporally coherent videos, research on zero-shot video editing using these fundamental models has expanded rapidly. To enhance editing quality, structural controls are frequently employed in video editing. Among these techniques, cross-attention mask control stands out for its effectiveness and efficiency. However, when cross-attention masks are naively applied to video editing, they can introduce artifacts such as blurring and flickering. Our experiments uncover a critical factor overlooked in previous video editing research: cross-attention masks are not consistently clear but vary with model structure and denoising timestep. To address this issue, we propose the metric Mask Matching Cost (MMC) that quantifies this variability and propose FreeMask, a method for selecting optimal masks tailored to specific video editing tasks. Using MMC-selected masks, we further improve the masked fusion mechanism within comprehensive attention features, e.g., temp, cross, and self-attention modules. Our approach can be seamlessly integrated into existing zero-shot video editing frameworks with better performance, requiring no control assistance or parameter fine-tuning but enabling adaptive decoupling of unedited semantic layouts with mask precision control. Extensive experiments demonstrate that FreeMask achieves superior semantic fidelity, temporal consistency, and editing quality compared to state-of-the-art methods.
Authors: Madhumita Veeramreddy, Ashok Kumar Pradhan, Swetha Ghanta, Laavanya Rachakonda, Saraju P Mohanty
Abstract: Maintaining health and fitness through a balanced diet is essential for preventing non communicable diseases such as heart disease, diabetes, and cancer. NutriVision combines smart healthcare with computer vision and machine learning to address the challenges of nutrition and dietary management. This paper introduces a novel system that can identify food items, estimate quantities, and provide comprehensive nutritional information. NutriVision employs the Faster Region based Convolutional Neural Network, a deep learning algorithm that improves object detection by generating region proposals and then classifying those regions, making it highly effective for accurate and fast food identification even in complex and disorganized meal settings. Through smartphone based image capture, NutriVision delivers instant nutritional data, including macronutrient breakdown, calorie count, and micronutrient details. One of the standout features of NutriVision is its personalized nutritional analysis and diet recommendations, which are tailored to each user's dietary preferences, nutritional needs, and health history. By providing customized advice, NutriVision helps users achieve specific health and fitness goals, such as managing dietary restrictions or controlling weight. In addition to offering precise food detection and nutritional assessment, NutriVision supports smarter dietary decisions by integrating user data with recommendations that promote a balanced, healthful diet. This system presents a practical and advanced solution for nutrition management and has the potential to significantly influence how people approach their dietary choices, promoting healthier eating habits and overall well being. This paper discusses the design, performance evaluation, and prospective applications of the NutriVision system.
Authors: King-Siong Si, Lu Sun, Weizhan Zhang, Tieliang Gong, Jiahao Wang, Jiang Liu, Hao Sun
Abstract: Non-maximum suppression (NMS) is an indispensable post-processing step in object detection. With the continuous optimization of network models, NMS has become the ``last mile'' to enhance the efficiency of object detection. This paper systematically analyzes NMS from a graph theory perspective for the first time, revealing its intrinsic structure. Consequently, we propose two optimization methods, namely QSI-NMS and BOE-NMS. The former is a fast recursive divide-and-conquer algorithm with negligible mAP loss, and its extended version (eQSI-NMS) achieves optimal complexity of $\mathcal{O}(n\log n)$. The latter, concentrating on the locality of NMS, achieves an optimization at a constant level without an mAP loss penalty. Moreover, to facilitate rapid evaluation of NMS methods for researchers, we introduce NMS-Bench, the first benchmark designed to comprehensively assess various NMS methods. Taking the YOLOv8-N model on MS COCO 2017 as the benchmark setup, our method QSI-NMS provides $6.2\times$ speed of original NMS on the benchmark, with a $0.1\%$ decrease in mAP. The optimal eQSI-NMS, with only a $0.3\%$ mAP decrease, achieves $10.7\times$ speed. Meanwhile, BOE-NMS exhibits $5.1\times$ speed with no compromise in mAP.
Authors: Bahri Batuhan Bilecen, Ahmet Berke Gokmen, Aysegul Dundar
Abstract: 3D GAN inversion aims to project a single image into the latent space of a 3D Generative Adversarial Network (GAN), thereby achieving 3D geometry reconstruction. While there exist encoders that achieve good results in 3D GAN inversion, they are predominantly built on EG3D, which specializes in synthesizing near-frontal views and is limiting in synthesizing comprehensive 3D scenes from diverse viewpoints. In contrast to existing approaches, we propose a novel framework built on PanoHead, which excels in synthesizing images from a 360-degree perspective. To achieve realistic 3D modeling of the input image, we introduce a dual encoder system tailored for high-fidelity reconstruction and realistic generation from different viewpoints. Accompanying this, we propose a stitching framework on the triplane domain to get the best predictions from both. To achieve seamless stitching, both encoders must output consistent results despite being specialized for different tasks. For this reason, we carefully train these encoders using specialized losses, including an adversarial loss based on our novel occlusion-aware triplane discriminator. Experiments reveal that our approach surpasses the existing encoder training methods qualitatively and quantitatively. Please visit the project page: https://berkegokmen1.github.io/dual-enc-3d-gan-inv.
Authors: Bowei Chen, Yifan Wang, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz
Abstract: Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas" is iteratively updated. The model learns from real artists by training on many painting videos. Our approach incorporates text and region understanding to define a set of painting "instructions" and updates the canvas with a novel diffusion-based renderer. The method extrapolates beyond the limited, acrylic style paintings on which it has been trained, showing plausible results for a wide range of artistic styles and genres.
Authors: Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Fu-Jen Chu, Kris Kitani, Gedas Bertasius, Xitong Yang
Abstract: Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem presents significant challenges due to the need for comprehensive knowledge of temporal and hierarchical task structures, as well as strong capabilities in reasoning and planning. To achieve this, prior work typically relies on extensive training on the target dataset, which often results in significant dataset bias and a lack of generalization to unseen tasks. In this work, we introduce VidAssist, an integrated framework designed for zero/few-shot goal-oriented planning in instructional videos. VidAssist leverages large language models (LLMs) as both the knowledge base and the assessment tool for generating and evaluating action plans, thus overcoming the challenges of acquiring procedural knowledge from small-scale, low-diversity datasets. Moreover, VidAssist employs a breadth-first search algorithm for optimal plan generation, in which a composite of value functions designed for goal-oriented planning is utilized to assess the predicted actions at each step. Extensive experiments demonstrate that VidAssist offers a unified framework for different goal-oriented planning setups, e.g., visual planning for assistance (VPA) and procedural planning (PP), and achieves remarkable performance in zero-shot and few-shot setups. Specifically, our few-shot model outperforms the prior fully supervised state-of-the-art method by +7.7% in VPA and +4.81% PP task on the COIN dataset while predicting 4 future actions. Code, and models are publicly available at https://sites.google.com/view/vidassist.
Authors: Yubin Wang, Zhikang Zou, Xiaoqing Ye, Xiao Tan, Errui Ding, Cairong Zhao
Abstract: We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains. Due to substantial disparities in data distribution and variations in taxonomy across diverse domains, training such a detector by simply merging datasets poses a significant challenge. Motivated by this observation, we introduce multi-stage prompting modules for multi-dataset 3D detection, which leverages prompts based on the characteristics of corresponding datasets to mitigate existing differences. This elegant design facilitates seamless plug-and-play integration within various advanced 3D detection frameworks in a unified manner, while also allowing straightforward adaptation for universal applicability across datasets. Experiments are conducted across multiple dataset consolidation scenarios involving KITTI, Waymo, and nuScenes, demonstrating that our Uni$^2$Det outperforms existing methods by a large margin in multi-dataset training. Notably, results on zero-shot cross-dataset transfer validate the generalization capability of our proposed method.
Authors: Tianchang Shen, Zhaoshuo Li, Marc Law, Matan Atzmon, Sanja Fidler, James Lucas, Jun Gao, Nicholas Sharp
Abstract: Meshes are ubiquitous in visual computing and simulation, yet most existing machine learning techniques represent meshes only indirectly, e.g. as the level set of a scalar field or deformation of a template, or as a disordered triangle soup lacking local structure. This work presents a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network. Our key innovation is to define a continuous latent connectivity space at each mesh vertex, which implies the discrete mesh. In particular, our vertex embeddings generate cyclic neighbor relationships in a halfedge mesh representation, which gives a guarantee of edge-manifoldness and the ability to represent general polygonal meshes. This representation is well-suited to machine learning and stochastic optimization, without restriction on connectivity or topology. We first explore the basic properties of this representation, then use it to fit distributions of meshes from large datasets. The resulting models generate diverse meshes with tessellation structure learned from the dataset population, with concise details and high-quality mesh elements. In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
Authors: Jeff Tan, Donglai Xiang, Shubham Tulsiani, Deva Ramanan, Gengshan Yang
Abstract: We present a method to reconstruct time-consistent human body models from monocular videos, focusing on extremely loose clothing or handheld object interactions. Prior work in human reconstruction is either limited to tight clothing with no object interactions, or requires calibrated multi-view captures or personalized template scans which are costly to collect at scale. Our key insight for high-quality yet flexible reconstruction is the careful combination of generic human priors about articulated body shape (learned from large-scale training data) with video-specific articulated "bag-of-bones" deformation (fit to a single video via test-time optimization). We accomplish this by learning a neural implicit model that disentangles body versus clothing deformations as separate motion model layers. To capture subtle geometry of clothing, we leverage image-based priors such as human body pose, surface normals, and optical flow during optimization. The resulting neural fields can be extracted into time-consistent meshes, or further optimized as explicit 3D Gaussians for high-fidelity interactive rendering. On datasets with highly challenging clothing deformations and object interactions, DressRecon yields higher-fidelity 3D reconstructions than prior art. Project page: https://jefftan969.github.io/dressrecon/
Authors: Haotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang, Afshin Dehghan, Peter Grasch, Yinfei Yang
Abstract: We present MM1.5, a new family of multimodal large language models (MLLMs) designed to enhance capabilities in text-rich image understanding, visual referring and grounding, and multi-image reasoning. Building upon the MM1 architecture, MM1.5 adopts a data-centric approach to model training, systematically exploring the impact of diverse data mixtures across the entire model training lifecycle. This includes high-quality OCR data and synthetic captions for continual pre-training, as well as an optimized visual instruction-tuning data mixture for supervised fine-tuning. Our models range from 1B to 30B parameters, encompassing both dense and mixture-of-experts (MoE) variants, and demonstrate that careful data curation and training strategies can yield strong performance even at small scales (1B and 3B). Additionally, we introduce two specialized variants: MM1.5-Video, designed for video understanding, and MM1.5-UI, tailored for mobile UI understanding. Through extensive empirical studies and ablations, we provide detailed insights into the training processes and decisions that inform our final designs, offering valuable guidance for future research in MLLM development.
Authors: Haokai Zhao, Haowei Lou, Lina Yao, Yu Zhang
Abstract: Functional magnetic resonance imaging (fMRI) is an emerging neuroimaging modality that is commonly modeled as networks of Regions of Interest (ROIs) and their connections, named functional connectivity, for understanding the brain functions and mental disorders. However, due to the high cost of fMRI data acquisition and labeling, the amount of fMRI data is usually small, which largely limits the performance of recognition models. With the rise of generative models, especially diffusion models, the ability to generate realistic samples close to the real data distribution has been widely used for data augmentations. In this work, we present a transformer-based latent diffusion model for functional connectivity generation and demonstrate the effectiveness of the diffusion model as an augmentation tool for fMRI functional connectivity. Furthermore, extended experiments are conducted to provide detailed analysis of the generation quality and interpretations for the learned feature pattern. Our code will be made public upon acceptance.
Authors: Hongcheng Guo, Wei Zhang, Junhao Chen, Yaonan Gu, Jian Yang, Junjia Du, Binyuan Hui, Tianyu Liu, Jianxin Ma, Chang Zhou, Zhoujun Li
Abstract: Recently advancements in large multimodal models have led to significant strides in image comprehension capabilities. Despite these advancements, there is a lack of the robust benchmark specifically for assessing the Image-to-Web conversion proficiency of these large models. Primarily, it is essential to ensure the integrity of the web elements generated. These elements comprise visible and invisible categories. Previous evaluation methods (e.g., BLEU) are notably susceptible to significant alterations due to the presence of invisible elements in Web. Furthermore, it is crucial to measure the layout information of web pages, referring to the positional relationships between elements, which is overlooked by previous work. To address challenges, we have curated and aligned a benchmark of images and corresponding web codes (IW-Bench). Specifically, we propose the Element Accuracy, which tests the completeness of the elements by parsing the Document Object Model (DOM) tree. Layout Accuracy is also proposed to analyze the positional relationships of elements by converting DOM tree into a common subsequence. Besides, we design a five-hop multimodal Chain-of-Thought Prompting for better performance, which contains five hop: 1) SoM prompt injection. 2) Inferring Elements. 3) Inferring Layout. 4) Inferring Web code. 5) Reflection. Our benchmark comprises 1200 pairs of images and web codes with varying levels of difficulty. We have conducted extensive experiments on existing large multimodal models, offering insights into their performance and areas for improvement in image-to-web domain.
Authors: Tan T. Nguyen
Abstract: This review examines theoretical assumptions and computational models of event comprehension, tracing the evolution from discourse comprehension theories to contemporary event cognition frameworks. The review covers key discourse comprehension accounts, including Construction-Integration, Event Indexing, Causal Network, and Resonance models, highlighting their contributions to understanding cognitive processes in comprehension. I then discuss contemporary theoretical frameworks of event comprehension, including Event Segmentation Theory (Zacks et al., 2007), the Event Horizon Model (Radvansky & Zacks, 2014), and Hierarchical Generative Framework (Kuperberg, 2021), which emphasize prediction, causality, and multilevel representations in event understanding. Building on these theories, I evaluate five computational models of event comprehension: REPRISE (Butz et al., 2019), Structured Event Memory (SEM; Franklin et al., 2020), the Lu model (Lu et al., 2022), the Gumbsch model (Gumbsch et al., 2022), and the Elman and McRae model (2019). The analysis focuses on their approaches to hierarchical processing, prediction mechanisms, and representation learning. Key themes that emerge include the use of hierarchical structures as inductive biases, the importance of prediction in comprehension, and diverse strategies for learning event dynamics. The review identifies critical areas for future research, including the need for more sophisticated approaches to learning structured representations, integrating episodic memory mechanisms, and developing adaptive updating algorithms for working event models. By synthesizing insights from both theoretical frameworks and computational implementations, this review aims to advance our understanding of human event comprehension and guide future modeling efforts in cognitive science.
Authors: Shengsheng Qian, Zuyi Zhou, Dizhan Xue, Bing Wang, Changsheng Xu
Abstract: Cross-modal reasoning (CMR), the intricate process of synthesizing and drawing inferences across divergent sensory modalities, is increasingly recognized as a crucial capability in the progression toward more sophisticated and anthropomorphic artificial intelligence systems. Large Language Models (LLMs) represent a class of AI algorithms specifically engineered to parse, produce, and engage with human language on an extensive scale. The recent trend of deploying LLMs to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced exposition of current methodologies applied in CMR using LLMs, classifying these into a detailed three-tiered taxonomy. Moreover, the survey delves into the principal design strategies and operational techniques of prototypical models within this domain. Additionally, it articulates the prevailing challenges associated with the integration of LLMs in CMR and identifies prospective research directions. To sum up, this survey endeavors to expedite progress within this burgeoning field by endowing scholars with a holistic and detailed vista, showcasing the vanguard of current research whilst pinpointing potential avenues for advancement. An associated GitHub repository that collects the relevant papers can be found at https://github.com/ZuyiZhou/Awesome-Cross-modal-Reasoning-with-LLMs
URLs: https://github.com/ZuyiZhou/Awesome-Cross-modal-Reasoning-with-LLMs
Authors: Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch
Abstract: Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points. While effort has been put into characterizing the memorized data and linking encoder memorization to downstream utility, little is known about where the memorization happens inside SSL encoders. To close this gap, we propose two metrics for localizing memorization in SSL encoders on a per-layer (layermem) and per-unit basis (unitmem). Our localization methods are independent of the downstream task, do not require any label information, and can be performed in a forward pass. By localizing memorization in various encoder architectures (convolutional and transformer-based) trained on diverse datasets with contrastive and non-contrastive SSL frameworks, we find that (1) while SSL memorization increases with layer depth, highly memorizing units are distributed across the entire encoder, (2) a significant fraction of units in SSL encoders experiences surprisingly high memorization of individual data points, which is in contrast to models trained under supervision, (3) atypical (or outlier) data points cause much higher layer and unit memorization than standard data points, and (4) in vision transformers, most memorization happens in the fully-connected layers. Finally, we show that localizing memorization in SSL has the potential to improve fine-tuning and to inform pruning strategies.
Authors: Kun Su, Xiulong Liu, Eli Shlizerman
Abstract: Video encompasses both visual and auditory data, creating a perceptually rich experience where these two modalities complement each other. As such, videos are a valuable type of media for the investigation of the interplay between audio and visual elements. Previous studies of audio-visual modalities primarily focused on either audio-visual representation learning or generative modeling of a modality conditioned on the other, creating a disconnect between these two branches. A unified framework that learns representation and generates modalities has not been developed yet. In this work, we introduce a novel framework called Vision to Audio and Beyond (VAB) to bridge the gap between audio-visual representation learning and vision-to-audio generation. The key approach of VAB is that rather than working with raw video frames and audio data, VAB performs representation learning and generative modeling within latent spaces. In particular, VAB uses a pre-trained audio tokenizer and an image encoder to obtain audio tokens and visual features, respectively. It then performs the pre-training task of visual-conditioned masked audio token prediction. This training strategy enables the model to engage in contextual learning and simultaneous video-to-audio generation. After the pre-training phase, VAB employs the iterative-decoding approach to rapidly generate audio tokens conditioned on visual features. Since VAB is a unified model, its backbone can be fine-tuned for various audio-visual downstream tasks. Our experiments showcase the efficiency of VAB in producing high-quality audio from video, and its capability to acquire semantic audio-visual features, leading to competitive results in audio-visual retrieval and classification.
Authors: Dai Shimizu, Ko Watanabe, Andreas Dengel
Abstract: Understanding the correlation between EEG features and cognitive tasks is crucial for elucidating brain function. Brain activity synchronizes during speaking and listening tasks. However, it is challenging to estimate task-dependent brain activity characteristics with methods with low spatial resolution but high temporal resolution, such as EEG, rather than methods with high spatial resolution, like fMRI. This study introduces a novel approach to EEG feature estimation that utilizes the weights of deep learning models to explore this association. We demonstrate that attention maps generated from Vision Transformers and EEGNet effectively identify features that align with findings from prior studies. EEGNet emerged as the most accurate model regarding subject independence and the classification of Listening and Speaking tasks. The application of Mel-Spectrogram with ViTs enhances the resolution of temporal and frequency-related EEG characteristics. Our findings reveal that the characteristics discerned through attention maps vary significantly based on the input data, allowing for tailored feature extraction from EEG signals. By estimating features, our study reinforces known attributes and predicts new ones, potentially offering fresh perspectives in utilizing EEG for medical purposes, such as early disease detection. These techniques will make substantial contributions to cognitive neuroscience.
Authors: Kartik Gupta, Kimberley Faria, Vikas Mehta
Abstract: While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient features needed for such tasks. Decompression of images have taken a back seat in recent years while the focus has shifted to an image's utility in performing machine learning based analysis on top of them. Thus the demand for compression pipelines that incorporate such features from images has become ever present. The methods outlined in the report build on the recent work done on learning based image compression techniques to incorporate downstream tasks in them. We propose various methods of finetuning and enhancing different parts of pretrained compression encoding pipeline and present the results of our investigation regarding the performance of vision tasks using compression based pipelines.
Authors: Shihua Qin, Ming Zhang, Juan Shan, Taehoon Shin, Jonghye Woo, Fangxu Xing
Abstract: Bone marrow lesions (BMLs) are critical indicators of knee osteoarthritis (OA). Since they often appear as small, irregular structures with indistinguishable edges in knee magnetic resonance images (MRIs), effective detection of BMLs in MRI is vital for OA diagnosis and treatment. This paper proposes a semi-supervised local anomaly detection method using mask inpainting models for identification of BMLs in high-resolution knee MRI, effectively integrating a 3D femur bone segmentation model, a large mask inpainting model, and a series of post-processing techniques. The method was evaluated using MRIs at various resolutions from a subset of the public Osteoarthritis Initiative database. Dice score, Intersection over Union (IoU), and pixel-level sensitivity, specificity, and accuracy showed an advantage over the multiresolution knowledge distillation method-a state-of-the-art global anomaly detection method. Especially, segmentation performance is enhanced on higher-resolution images, achieving an over two times performance increase on the Dice score and the IoU score at a 448x448 resolution level. We also demonstrate that with increasing size of the BML region, both the Dice and IoU scores improve as the proportion of distinguishable boundary decreases. The identified BML masks can serve as markers for downstream tasks such as segmentation and classification. The proposed method has shown a potential in improving BML detection, laying a foundation for further advances in imaging-based OA research.
Authors: Xin Li, Zhihong Xia, Hongkun Zhang
Abstract: We have developed a novel activation function, named the Cauchy Activation Function. This function is derived from the Cauchy Integral Theorem in complex analysis and is specifically tailored for problems requiring high precision. This innovation has led to the creation of a new class of neural networks, which we call (Comple)XNet, or simply XNet. We will demonstrate that XNet is particularly effective for high-dimensional challenges such as image classification and solving Partial Differential Equations (PDEs). Our evaluations show that XNet significantly outperforms established benchmarks like MNIST and CIFAR-10 in computer vision, and offers substantial advantages over Physics-Informed Neural Networks (PINNs) in both low-dimensional and high-dimensional PDE scenarios.
Authors: Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen, Bailan He, Volker Tresp, Zhiqiang Xu, Jindong Gu
Abstract: Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the question decomposition capability of Multimodal Large Language Models (MLLMs) has yet to be explored. To this end, this paper explores visual question decomposition on MLLMs. Specifically, we introduce a systematic evaluation framework including a dataset and several evaluation criteria to assess the quality of the decomposed sub-questions, revealing that existing MLLMs struggle to produce high-quality sub-questions. To address this limitation, we propose a specific finetuning dataset, DecoVQA+, for enhancing the model's question decomposition capability. Aiming at enabling models to perform appropriate selective decomposition, we propose an efficient finetuning pipeline. The finetuning pipeline consists of our proposed dataset and a training objective for selective decomposition. Finetuned MLLMs demonstrate significant improvements in the quality of sub-questions and the policy of selective question decomposition. Additionally, the models also achieve higher accuracy with selective decomposition on VQA benchmark datasets.
Authors: Jiarui Jiang, Wei Huang, Miao Zhang, Taiji Suzuki, Liqiang Nie
Abstract: Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments on the experimental side. However, their theoretical capabilities, particularly in terms of generalization when trained to overfit training data, are still not fully understood. To address this gap, this work delves deeply into the benign overfitting perspective of transformers in vision. To this end, we study the optimization of a Transformer composed of a self-attention layer with softmax followed by a fully connected layer under gradient descent on a certain data distribution model. By developing techniques that address the challenges posed by softmax and the interdependent nature of multiple weights in transformer optimization, we successfully characterized the training dynamics and achieved generalization in post-training. Our results establish a sharp condition that can distinguish between the small test error phase and the large test error regime, based on the signal-to-noise ratio in the data model. The theoretical results are further verified by experimental simulation.
Authors: Maryam Tavakol Elahi (The University of Ottawa)
Abstract: This research proposal discusses two challenges in the field of medical image analysis: the multi-parametric investigation on microstructural and macrostructural characteristics of the cervical spinal cord and deep learning-based medical image segmentation. First, we conduct a thorough analysis of the cervical spinal cord within a healthy population. Unlike most previous studies, which required medical professionals to perform functional examinations using metrics like the modified Japanese Orthopaedic Association (mJOA) score or the American Spinal Injury Association (ASIA) impairment scale, this research focuses solely on Magnetic Resonance (MR) images of the cervical spinal cord. Second, we employ cutting-edge deep learning-based segmentation methods to achieve highly accurate macrostructural measurements from MR images. To this end, we propose an enhanced UNet-like Transformer-based framework with attentive skip connections. This paper reports on the problem domain, proposed solutions, current status of research, and expected contributions.
Authors: Harish Neelam, Koushik Sai Veerella, Souradip Biswas
Abstract: This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse modeling techniques, particularly Lasso and proximal gradient methods, into a comprehensive pipeline for efficient and interpretable feature selection. Leveraging pre-trained models such as VGG19 and incorporating anomaly detection methods like Isolation Forest and Local Outlier Factor, our methodology addresses the challenge of extracting meaningful features from complex datasets. Evaluation metrics such as accuracy and F1 score, alongside visualizations, are employed to assess the performance of the sparse modeling techniques. Through this work, we aim to advance the understanding and application of sparse modeling in machine learning, particularly in the context of wood surface defect detection.
Authors: Tianyi Liu, Zhaorui Tan, Haochuan Jiang, Xi Yang, Kaizhu Huang
Abstract: Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents an even more difficult scenario. To cope with this challenge, knowledge distillation has emerged as one promising strategy. However, recent efforts typically overlook the modality gaps and thus fail to learn invariant feature representations across different modalities. Such drawback consequently leads to limited performance for both teachers and students. To ameliorate these problems, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce a teacher with narrowed modality gaps. This further offers superior guidance for missing modality students, achieving an average improvement of 1.75 on dice score.
Authors: Xiaoxiang Han, Xinyu Li, Jiang Shang, Yiman Liu, Keyan Chen, Qiaohong Liu, Qi Zhang
Abstract: Segmenting anatomical structures and lesions from ultrasound images contributes to disease assessment, diagnosis, and treatment. Weakly supervised learning (WSL) based on sparse annotation has achieved encouraging performance and demonstrated the potential to reduce annotation costs. However, ultrasound images often suffer from issues such as poor contrast, unclear edges, as well as varying sizes and locations of lesions. This makes it challenging for convolutional networks with local receptive fields to extract global morphological features from the sparse information provided by scribble annotations. Recently, the visual Mamba based on state space sequence models (SSMs) has significantly reduced computational complexity while ensuring long-range dependencies compared to Transformers. Consequently, for the first time, we apply scribble-based WSL to ultrasound image segmentation and propose a novel hybrid CNN-Mamba framework. Furthermore, due to the characteristics of ultrasound images and insufficient supervision signals, existing consistency regularization often filters out predictions near decision boundaries, leading to unstable predictions of edges. Hence, we introduce the Dempster-Shafer theory (DST) of evidence to devise an Evidence-Guided Consistency (EGC) strategy, which leverages high-evidence predictions more likely to occur near high-density regions to guide low-evidence predictions potentially present near decision boundaries for optimization. During training, the collaboration between the CNN branch and the Mamba branch in the proposed framework draws inspiration from each other based on the EGC strategy. Extensive experiments on four ultrasound public datasets for binary-class and multi-class segmentation demonstrate the competitiveness of the proposed method. The scribble-annotated dataset and code will be made available on https://github.com/GtLinyer/MambaEviScrib.
Authors: David Stojanovski, Mariana da Silva, Pablo Lamata, Arian Beqiri, Alberto Gomez
Abstract: We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $\Gamma$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models.
Authors: Zongbo Han, Jialong Yang, Junfan Li, Qinghua Hu, Qianli Xu, Mike Zheng Shou, Changqing Zhang
Abstract: Vision-language foundation models (e.g., CLIP) have shown remarkable performance across a wide range of tasks. However, deploying these models may be unreliable when significant distribution gaps exist between the training and test data. The training-free test-time dynamic adapter (TDA) is a promising approach to address this issue by storing representative test samples to guide the classification of subsequent ones. However, TDA only naively maintains a limited number of reference samples in the cache, leading to severe test-time catastrophic forgetting when the cache is updated by dropping samples. In this paper, we propose a simple yet effective method for DistributiOnal Test-time Adaptation (Dota). Instead of naively memorizing representative test samples, Dota continually estimates the distributions of test samples, allowing the model to continually adapt to the deployment environment. The test-time posterior probabilities are then computed using the estimated distributions based on Bayes' theorem for adaptation purposes. To further enhance the adaptability on the uncertain samples, we introduce a new human-in-the-loop paradigm which identifies uncertain samples, collects human-feedback, and incorporates it into the Dota framework. Extensive experiments validate that Dota enables CLIP to continually learn, resulting in a significant improvement compared to current state-of-the-art methods.
Authors: Zhiwen Chen, Siwen Mo, Haobin Ke, Steven X. Ding, Zhaohui Jiang, Chunhua Yang, Weihua Gui
Abstract: Learning representations of two views of data such that the resulting representations are highly linearly correlated is appealing in machine learning. In this paper, we present a canonical correlation guided learning framework, which allows to be realized by deep neural networks (CCDNN), to learn such a correlated representation. It is also a novel merging of multivariate analysis (MVA) and machine learning, which can be viewed as transforming MVA into end-to-end architectures with the aid of neural networks. Unlike the linear canonical correlation analysis (CCA), kernel CCA and deep CCA, in the proposed method, the optimization formulation is not restricted to maximize correlation, instead we make canonical correlation as a constraint, which preserves the correlated representation learning ability and focuses more on the engineering tasks endowed by optimization formulation, such as reconstruction, classification and prediction. Furthermore, to reduce the redundancy induced by correlation, a redundancy filter is designed. We illustrate the performance of CCDNN on various tasks. In experiments on MNIST dataset, the results show that CCDNN has better reconstruction performance in terms of mean squared error and mean absolute error than DCCA and DCCAE. Also, we present the application of the proposed network to industrial fault diagnosis and remaining useful life cases for the classification and prediction tasks accordingly. The proposed method demonstrates superior performance in both tasks when compared to existing methods. Extension of CCDNN to much more deeper with the aid of residual connection is also presented in appendix.
Authors: Katherine Keegan, Elizabeth Newman
Abstract: Tensor decompositions have become essential tools for feature extraction and compression of multiway data. Recent advances in tensor operators have enabled desirable properties of standard matrix algebra to be retained for multilinear factorizations. Behind this matrix-mimetic tensor operation is an invertible matrix whose size depends quadratically on certain dimensions of the data. As a result, for large-scale multiway data, the invertible matrix can be computationally demanding to apply and invert and can lead to inefficient tensor representations in terms of construction and storage costs. In this work, we propose a new projected tensor-tensor product that relaxes the invertibility restriction to reduce computational overhead and still preserves fundamental linear algebraic properties. The transformation behind the projected product is a tall-and-skinny matrix with unitary columns, which depends only linearly on certain dimensions of the data, thereby reducing computational complexity by an order of magnitude. We provide extensive theory to prove the matrix mimeticity and the optimality of compressed representations within the projected product framework. We further prove that projected-product-based approximations outperform a comparable, non-matrix-mimetic tensor factorization. We support the theoretical findings and demonstrate the practical benefits of projected products through numerical experiments on video and hyperspectral imaging data.
Authors: Zijian Dong, Ruilin Li, Yilei Wu, Thuan Tinh Nguyen, Joanna Su Xian Chong, Fang Ji, Nathanael Ren Jie Tong, Christopher Li Hsian Chen, Juan Helen Zhou
Abstract: We introduce Brain-JEPA, a brain dynamics foundation model with the Joint-Embedding Predictive Architecture (JEPA). This pioneering model achieves state-of-the-art performance in demographic prediction, disease diagnosis/prognosis, and trait prediction through fine-tuning. Furthermore, it excels in off-the-shelf evaluations (e.g., linear probing) and demonstrates superior generalizability across different ethnic groups, surpassing the previous large model for brain activity significantly. Brain-JEPA incorporates two innovative techniques: Brain Gradient Positioning and Spatiotemporal Masking. Brain Gradient Positioning introduces a functional coordinate system for brain functional parcellation, enhancing the positional encoding of different Regions of Interest (ROIs). Spatiotemporal Masking, tailored to the unique characteristics of fMRI data, addresses the challenge of heterogeneous time-series patches. These methodologies enhance model performance and advance our understanding of the neural circuits underlying cognition. Overall, Brain-JEPA is paving the way to address pivotal questions of building brain functional coordinate system and masking brain activity at the AI-neuroscience interface, and setting a potentially new paradigm in brain activity analysis through downstream adaptation.
Authors: Lingting Zhu, Yizheng Chen, Lianli Liu, Lei Xing, Lequan Yu
Abstract: Multi-modality imaging is widely used in clinical practice and biomedical research to gain a comprehensive understanding of an imaging subject. Currently, multi-modality imaging is accomplished by post hoc fusion of independently reconstructed images under the guidance of mutual information or spatially registered hardware, which limits the accuracy and utility of multi-modality imaging. Here, we investigate a data-driven multi-modality imaging (DMI) strategy for synergetic imaging of CT and MRI. We reveal two distinct types of features in multi-modality imaging, namely intra- and inter-modality features, and present a multi-sensor learning (MSL) framework to utilize the crossover inter-modality features for augmented multi-modality imaging. The MSL imaging approach breaks down the boundaries of traditional imaging modalities and allows for optimal hybridization of CT and MRI, which maximizes the use of sensory data. We showcase the effectiveness of our DMI strategy through synergetic CT-MRI brain imaging. The principle of DMI is quite general and holds enormous potential for various DMI applications across disciplines.
Authors: Sikai Yang, Gang Yan
Abstract: Losing track of reading progress during line switching can be frustrating. Eye gaze tracking technology offers a potential solution by highlighting read paragraphs, aiding users in avoiding wrong line switches. However, the gap between gaze tracking accuracy (2-3 cm) and text line spacing (3-5 mm) makes direct application impractical. Existing methods leverage the linear reading pattern but fail during jump reading. This paper presents a reading tracking and highlighting system that supports both linear and jump reading. Based on experimental insights from the gaze nature study of 16 users, two gaze error models are designed to enable both jump reading detection and relocation. The system further leverages the large language model's contextual perception capability in aiding reading tracking. A reading tracking domain-specific line-gaze alignment opportunity is also exploited to enable dynamic and frequent calibration of the gaze results. Controlled experiments demonstrate reliable linear reading tracking, as well as 84% accuracy in tracking jump reading. Furthermore, real field tests with 18 volunteers demonstrated the system's effectiveness in tracking and highlighting read paragraphs, improving reading efficiency, and enhancing user experience.
Authors: Cody Simons, Zhichao Liu, Brandon Marcus, Amit K. Roy-Chowdhury, Konstantinos Karydis
Abstract: In this paper, we develop an embodied AI system for human-in-the-loop navigation with a wheeled mobile robot. We propose a direct yet effective method of monitoring the robot's current plan to detect changes in the environment that impact the intended trajectory of the robot significantly and then query a human for feedback. We also develop a means to parse human feedback expressed in natural language into local navigation waypoints and integrate it into a global planning system, by leveraging a map of semantic features and an aligned obstacle map. Extensive testing in simulation and physical hardware experiments with a resource-constrained wheeled robot tasked to navigate in a real-world environment validate the efficacy and robustness of our method. This work can support applications like precision agriculture and construction, where persistent monitoring of the environment provides a human with information about the environment state.
Authors: Florentin Guth, Brice M\'enard
Abstract: We explore the universality of neural encodings in convolutional neural networks trained on image classification tasks. We develop a procedure to directly compare the learned weights rather than their representations. It is based on a factorization of spatial and channel dimensions and measures the similarity of aligned weight covariances. We show that, for a range of layers of VGG-type networks, the learned eigenvectors appear to be universal across different natural image datasets. Our results suggest the existence of a universal neural encoding for natural images. They explain, at a more fundamental level, the success of transfer learning. Our work shows that, instead of aiming at maximizing the performance of neural networks, one can alternatively attempt to maximize the universality of the learned encoding, in order to build a principled foundation model.
Authors: Shrey Bavishi, Shrey Modi
Abstract: The escalating frequency and scale of recent malware attacks underscore the urgent need for swift and precise malware classification in the ever-evolving cybersecurity landscape. Key challenges include accurately categorizing closely related malware families. To tackle this evolving threat landscape, this paper proposes a novel architecture LeViT-MC which produces state-of-the-art results in malware detection and classification. LeViT-MC leverages a vision transformer-based architecture, an image-based visualization approach, and advanced transfer learning techniques. Experimental results on multi-class malware classification using the MaleVis dataset indicate LeViT-MC's significant advantage over existing models. This study underscores the critical importance of combining image-based and transfer learning techniques, with vision transformers at the forefront of the ongoing battle against evolving cyber threats. We propose a novel architecture LeViT-MC which not only achieves state of the art results on image classification but is also more time efficient.
Authors: Soofiyan Atar, Yuheng Zhi, Florian Richter, Michael Yip
Abstract: Depth perception is essential for a robot's spatial and geometric understanding of its environment, with many tasks traditionally relying on hardware-based depth sensors like RGB-D or stereo cameras. However, these sensors face practical limitations, including issues with transparent and reflective objects, high costs, calibration complexity, spatial and energy constraints, and increased failure rates in compound systems. While monocular depth estimation methods offer a cost-effective and simpler alternative, their adoption in robotics is limited due to their output of relative rather than metric depth, which is crucial for robotics applications. In this paper, we propose a method that utilizes a single calibrated camera, enabling the robot to act as a ``measuring stick" to convert relative depth estimates into metric depth in real-time as tasks are performed. Our approach employs an LSTM-based metric depth regressor, trained online and refined through probabilistic filtering, to accurately restore the metric depth across the monocular depth map, particularly in areas proximal to the robot's motion. Experiments with real robots demonstrate that our method significantly outperforms current state-of-the-art monocular metric depth estimation techniques, achieving a 22.1% reduction in depth error and a 52% increase in success rate for a downstream task.
Authors: Soofiyan Atar, Yi Li, Markus Grotz, Michael Wolf, Dieter Fox, Joshua Smith
Abstract: In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects. Effective deployment demands minimal hardware, strong generalization to new products, and resilience in diverse settings. Current methods often rely on depth sensors for structural information, which suffer from high costs, complex setups, and technical limitations. Inspired by recent advancements in computer vision, we propose an innovative approach that leverages foundation models to enhance suction grasping using only RGB images. Trained solely on a synthetic dataset, our method generalizes its grasp prediction capabilities to real-world robots and a diverse range of novel objects not included in the training set. Our network achieves an 82.3\% success rate in real-world applications. The project website with code and data will be available at http://optigrasp.github.io.
Authors: Kaixin Deng
Abstract: In the expanding field of digital media, maintaining the strength and integrity of watermarking technology is becoming increasingly challenging. This paper, inspired by the Idempotent Generative Network (IGN), explores the prospects of introducing idempotency into image watermark processing and proposes an innovative neural network model - the Idempotent Watermarking Network (IWN). The proposed model, which focuses on enhancing the recovery quality of color image watermarks, leverages idempotency to ensure superior image reversibility. This feature ensures that, even if color image watermarks are attacked or damaged, they can be effectively projected and mapped back to their original state. Therefore, the extracted watermarks have unquestionably increased quality. The IWN model achieves a balance between embedding capacity and robustness, alleviating to some extent the inherent contradiction between these two factors in traditional watermarking techniques and steganography methods.
Authors: Kuanrong Liu, Siyuan Liang, Jiawei Liang, Pengwen Dai, Xiaochun Cao
Abstract: Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors during training, which are activated by specific triggers during inference, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the malicious impacts of such attacks, these defenses frequently necessitate extensive training time and degrade clean accuracy. In this study, we propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities, known as Unlearn Backdoor Threats (UBT). We specifically use overfit training to improve backdoor shortcuts and accurately detect suspicious samples in the potential poisoning data set. Then, we select fewer unlearned samples from suspicious samples for rapid forgetting in order to eliminate the backdoor effect and thus improve backdoor defense efficiency. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime. This technique focuses on the model's compromised elements, dissociating backdoor correlations while maintaining the model's overall integrity. Extensive experimental results show that our method effectively defends against various backdoor attack methods in the CLIP model. Compared to SoTA backdoor defense methods, UBT achieves the lowest attack success rate while maintaining a high clean accuracy of the model (attack success rate decreases by 19% compared to SOTA, while clean accuracy increases by 2.57%).
Authors: Zongrong Li, Yunlei Su, Chenyuan Zhu, Wufan Zhao
Abstract: Urban Building Exteriors are increasingly important in urban analytics, driven by advancements in Street View Imagery and its integration with urban research. Multimodal Large Language Models (LLMs) offer powerful tools for urban annotation, enabling deeper insights into urban environments. However, challenges remain in creating accurate and detailed urban building exterior databases, identifying critical indicators for energy efficiency, environmental sustainability, and human-centric design, and systematically organizing these indicators. To address these challenges, we propose BuildingView, a novel approach that integrates high-resolution visual data from Google Street View with spatial information from OpenStreetMap via the Overpass API. This research improves the accuracy of urban building exterior data, identifies key sustainability and design indicators, and develops a framework for their extraction and categorization. Our methodology includes a systematic literature review, building and Street View sampling, and annotation using the ChatGPT-4O API. The resulting database, validated with data from New York City, Amsterdam, and Singapore, provides a comprehensive tool for urban studies, supporting informed decision-making in urban planning, architectural design, and environmental policy. The code for BuildingView is available at https://github.com/Jasper0122/BuildingView.
Authors: Jun Liu, Geng Yuan, Weihao Zeng, Hao Tang, Wenbin Zhang, Xue Lin, XiaoLin Xu, Dong Huang, Yanzhi Wang
Abstract: In research findings, co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas. The ability to predict 1p19q status is critical for treatment planning and patient follow-up. This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection. Although public networks such as RestNet and AlexNet can effectively diagnose brain cancers using transfer learning, the model includes quite a few weights that have nothing to do with medical images. As a result, the diagnostic results are unreliable by the transfer learning model. To deal with the problem of trustworthiness, we create the model from the ground up, rather than depending on a pre-trained model. To enable flexibility, we combined convolution stacking with a dropout and full connect operation, it improved performance by reducing overfitting. During model training, we also supplement the given dataset and inject Gaussian noise. We use three--fold cross-validation to train the best selection model. Comparing InceptionV3, VGG16, and MobileNetV2 fine-tuned with pre-trained models, our model produces better results. On an validation set of 125 codeletion vs. 31 not codeletion images, the proposed network achieves 96.37\% percent F1-score, 97.46\% percent precision, and 96.34\% percent recall when classifying 1p/19q codeletion and not codeletion images.
Authors: Abhijeet Patil, Harsh Diwakar, Jay Sawant, Nikhil Cherian Kurian, Subhash Yadav, Swapnil Rane, Tripti Bameta, Amit Sethi
Abstract: Histopathology whole slide images (WSIs) are being widely used to develop deep learning-based diagnostic solutions, especially for precision oncology. Most of these diagnostic softwares are vulnerable to biases and impurities in the training and test data which can lead to inaccurate diagnoses. For instance, WSIs contain multiple types of tissue regions, at least some of which might not be relevant to the diagnosis. We introduce HistoROI, a robust yet lightweight deep learning-based classifier to segregate WSI into six broad tissue regions -- epithelium, stroma, lymphocytes, adipose, artifacts, and miscellaneous. HistoROI is trained using a novel human-in-the-loop and active learning paradigm that ensures variations in training data for labeling-efficient generalization. HistoROI consistently performs well across multiple organs, despite being trained on only a single dataset, demonstrating strong generalization. Further, we have examined the utility of HistoROI in improving the performance of downstream deep learning-based tasks using the CAMELYON breast cancer lymph node and TCGA lung cancer datasets. For the former dataset, the area under the receiver operating characteristic curve (AUC) for metastasis versus normal tissue of a neural network trained using weakly supervised learning increased from 0.88 to 0.92 by filtering the data using HistoROI. Similarly, the AUC increased from 0.88 to 0.93 for the classification between adenocarcinoma and squamous cell carcinoma on the lung cancer dataset. We also found that the performance of the HistoROI improves upon HistoQC for artifact detection on a test dataset of 93 annotated WSIs. The limitations of the proposed model are analyzed, and potential extensions are also discussed.
Authors: Defa Zhu, Hongzhi Huang, Zihao Huang, Yutao Zeng, Yunyao Mao, Banggu Wu, Qiyang Min, Xun Zhou
Abstract: We present hyper-connections, a simple yet effective method that can serve as an alternative to residual connections. This approach specifically addresses common drawbacks observed in residual connection variants, such as the seesaw effect between gradient vanishing and representation collapse. Theoretically, hyper-connections allow the network to adjust the strength of connections between features at different depths and dynamically rearrange layers. We conduct experiments focusing on the pre-training of large language models, including dense and sparse models, where hyper-connections show significant performance improvements over residual connections. Additional experiments conducted on vision tasks also demonstrate similar improvements. We anticipate that this method will be broadly applicable and beneficial across a wide range of AI problems.
Authors: Bikang Pan, Wei Huang, Ye Shi
Abstract: Integrating pretrained vision-language foundation models like CLIP into federated learning has attracted significant attention for enhancing generalization across diverse tasks. Typically, federated learning of vision-language models employs prompt learning to reduce communication and computational costs, i.e., prompt-based federated learning. However, there is limited theoretical analysis to understand the performance of prompt-based federated learning. In this work, we construct a theoretical analysis framework for prompt-based federated learning via feature learning theory. Specifically, we monitor the evolution of signal learning and noise memorization in prompt-based federated learning, demonstrating that performance can be assessed by the ratio of task-relevant to task-irrelevant coefficients. Furthermore, we draw an analogy between income and risk in portfolio optimization and the task-relevant and task-irrelevant terms in feature learning. Leveraging inspiration from portfolio optimization that combining two independent assets will maintain the income while reducing the risk, we introduce two prompts: global prompt and local prompt to construct a prompt portfolio to balance the generalization and personalization. Consequently, we showed the performance advantage of the prompt portfolio and derived the optimal mixing coefficient. These theoretical claims have been further supported by empirical experiments.
Authors: Vivek Kumar Trivedi, Bheeshm Sharma, P. Balamurugan
Abstract: Detecting anomalies in brain MRI scans using supervised deep learning methods presents challenges due to anatomical diversity and labor-intensive requirement of pixel-level annotations. Generative models like Denoising Diffusion Probabilistic Model (DDPM) and their variants like pDDPM, mDDPM, cDDPM have recently emerged to be powerful alternatives to perform unsupervised anomaly detection in brain MRI scans. These methods leverage frame-level labels of healthy brains to generate healthy tissues in brain MRI scans. During inference, when an anomalous (or unhealthy) scan image is presented as an input, these models generate a healthy scan image corresponding to the input anomalous scan, and the difference map between the generated healthy scan image and the original anomalous scan image provide the necessary pixel level identification of abnormal tissues. The generated healthy images from the DDPM, pDDPM and mDDPM models however suffer from fidelity issues and contain artifacts that do not have medical significance. While cDDPM achieves slightly better fidelity and artifact suppression, it requires huge memory footprint and is computationally expensive than the other DDPM based models. In this work, we propose an improved version of DDPM called Multichannel Conditional Denoising Diffusion Probabilistic Model (MCDDPM) for unsupervised anomaly detection in brain MRI scans. Our proposed model achieves high fidelity by making use of additional information from the healthy images during the training process, enriching the representation power of DDPM models, with a computational cost and memory requirements on par with DDPM, pDDPM and mDDPM models. Experimental results on multiple datasets (e.g. BraTS20, BraTS21) demonstrate promising performance of the proposed method. The code is available at https://github.com/vivekkumartri/MCDDPM.
Authors: Yucheng Wang, Peiliang Gong, Min Wu, Felix Ott, Xiaoli Li, Lihua Xie, Zhenghua Chen
Abstract: Source-Free Unsupervised Domain Adaptation (SFUDA) has gained popularity for its ability to adapt pretrained models to target domains without accessing source domains, ensuring source data privacy. While SFUDA is well-developed in visual tasks, its application to Time-Series SFUDA (TS-SFUDA) remains limited due to the challenge of transferring crucial temporal dependencies across domains. Although a few researchers begin to explore this area, they rely on specific source domain designs, which are impractical as source data owners cannot be expected to follow particular pretraining protocols. To solve this, we propose Temporal Source Recovery (TemSR), a framework that transfers temporal dependencies for effective TS-SFUDA without requiring source-specific designs. TemSR features a recovery process that leverages masking, recovery, and optimization to generate a source-like distribution with recovered source temporal dependencies. To ensure effective recovery, we further design segment-based regularization to restore local dependencies and anchor-based recovery diversity maximization to enhance the diversity of the source-like distribution. The source-like distribution is then adapted to the target domain using traditional UDA techniques. Extensive experiments across multiple TS tasks demonstrate the effectiveness of TemSR, even surpassing existing TS-SFUDA method that requires source domain designs. Code is available in https://github.com/Frank-Wang-oss/TemSR.
Authors: Mengze Hong, Chen Jason Zhang, Lingxiao Yang, Yuanfeng Song, Di Jiang
Abstract: Understanding the meaning of infant cries is a significant challenge for young parents in caring for their newborns. The presence of background noise and the lack of labeled data present practical challenges in developing systems that can detect crying and analyze its underlying reasons. In this paper, we present a novel data-driven framework, "InfantCryNet," for accomplishing these tasks. To address the issue of data scarcity, we employ pre-trained audio models to incorporate prior knowledge into our model. We propose the use of statistical pooling and multi-head attention pooling techniques to extract features more effectively. Additionally, knowledge distillation and model quantization are applied to enhance model efficiency and reduce the model size, better supporting industrial deployment in mobile devices. Experiments on real-life datasets demonstrate the superior performance of the proposed framework, outperforming state-of-the-art baselines by 4.4% in classification accuracy. The model compression effectively reduces the model size by 7% without compromising performance and by up to 28% with only an 8% decrease in accuracy, offering practical insights for model selection and system design.
Authors: Tong Wei, Hao-Tian Li, Chun-Shu Li, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang
Abstract: Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DeFT, for adapting vision-language models. DeFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DeFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DeFT in both noisy label detection and image classification.
Authors: Vytautas Paura, Virginijus Marcinkevi\v{c}ius
Abstract: The hyperspectral unmixing method is an algorithm that extracts material (usually called endmember) data from hyperspectral data cube pixels along with their abundances. Due to a lower spatial resolution of hyperspectral sensors data in each of the pixels may contain mixed information from multiple endmembers. In this paper we create a hyperspectral unmixing dataset, created from blueberry field data gathered by a hyperspectral camera mounted on a UAV. We also propose a hyperspectral unmixing algorithm based on U-Net network architecture to achieve more accurate unmixing results on existing and newly created hyperspectral unmixing datasets.
Authors: Jonathan von Rad, Florian Seuffert
Abstract: Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification performance and interpretability of GoogLeNet. We systematically apply unstructured and structured pruning, as well as connection sparsity (pruning of input weights) methods to the network and analyze the outcomes regarding the network's performance on the validation set of ImageNet. We also compare different retraining strategies, such as iterative pruning and one-shot pruning. We find that with sufficient retraining epochs, the performance of the networks can approximate the performance of the default GoogLeNet - and even surpass it in some cases. To assess interpretability, we employ the Mechanistic Interpretability Score (MIS) developed by Zimmermann et al. . Our experiments reveal that there is no significant relationship between interpretability and pruning rate when using MIS as a measure. Additionally, we observe that networks with extremely low accuracy can still achieve high MIS scores, suggesting that the MIS may not always align with intuitive notions of interpretability, such as understanding the basis of correct decisions.
Authors: Salaar Saraj (California Institute for Telecommunications,Information Technology), Gregory Shklovski (California Institute for Telecommunications,Information Technology), Kristopher Irizarry (California Institute for Telecommunications,Information Technology), Jonathan Vet (California Institute for Telecommunications,Information Technology), Yutian Ren (California Institute for Telecommunications,Information Technology)
Abstract: Human-Robot Collaboration (HRC) is vital in Industry 4.0, using sensors, digital twins, collaborative robots (cobots), and intention-recognition models to have efficient manufacturing processes. However, Concept Drift is a significant challenge, where robots struggle to adapt to new environments. We address concept drift by integrating Adaptive Intelligence and self-labeling (SLB) to improve the resilience of intention-recognition in an HRC system. Our methodology begins with data collection using cameras and weight sensors, which is followed by annotation of intentions and state changes. Then we train various deep learning models with different preprocessing techniques for recognizing and predicting the intentions. Additionally, we developed a custom state detection algorithm for enhancing the accuracy of SLB, offering precise state-change definitions and timestamps to label intentions. Our results show that the MViT2 model with skeletal posture preprocessing achieves an accuracy of 83% on our data environment, compared to the 79% accuracy of MViT2 without skeleton posture extraction. Additionally, our SLB mechanism achieves a labeling accuracy of 91%, reducing a significant amount of time that would've been spent on manual annotation. Lastly, we observe swift scaling of model performance that combats concept drift by fine tuning on different increments of self-labeled data in a shifted domain that has key differences from the original training environment.. This study demonstrates the potential for rapid deployment of intelligent cobots in manufacturing through the steps shown in our methodology, paving a way for more adaptive and efficient HRC systems.
Authors: Shiyu Yuan, Jiali Cui, Hanao Li, Tian Han
Abstract: Multimodal generative models have recently gained significant attention for their ability to learn representations across various modalities, enhancing joint and cross-generation coherence. However, most existing works use standard Gaussian or Laplacian distributions as priors, which may struggle to capture the diverse information inherent in multiple data types due to their unimodal and less informative nature. Energy-based models (EBMs), known for their expressiveness and flexibility across various tasks, have yet to be thoroughly explored in the context of multimodal generative models. In this paper, we propose a novel framework that integrates the multimodal latent generative model with the EBM. Both models can be trained jointly through a variational scheme. This approach results in a more expressive and informative prior, better-capturing of information across multiple modalities. Our experiments validate the proposed model, demonstrating its superior generation coherence.
Authors: Samia Belhadj, Sanguk Park, Ambika Seth, Hesham Dar, Thijs Kooi
Abstract: Fairness in medical AI is increasingly recognized as a crucial aspect of healthcare delivery. While most of the prior work done on fairness emphasizes the importance of equal performance, we argue that decreases in fairness can be either harmful or non-harmful, depending on the type of change and how sensitive attributes are used. To this end, we introduce the notion of positive-sum fairness, which states that an increase in performance that results in a larger group disparity is acceptable as long as it does not come at the cost of individual subgroup performance. This allows sensitive attributes correlated with the disease to be used to increase performance without compromising on fairness. We illustrate this idea by comparing four CNN models that make different use of the race attribute in the training phase. The results show that removing all demographic encodings from the images helps close the gap in performance between the different subgroups, whereas leveraging the race attribute as a model's input increases the overall performance while widening the disparities between subgroups. These larger gaps are then put in perspective of the collective benefit through our notion of positive-sum fairness to distinguish harmful from non harmful disparities.
Authors: Kunal Deo, Deval Mehta, Kshitij Jadhav
Abstract: Long tail problems frequently arise in the medical field, particularly due to the scarcity of medical data for rare conditions. This scarcity often leads to models overfitting on such limited samples. Consequently, when training models on datasets with heavily skewed classes, where the number of samples varies significantly, a problem emerges. Training on such imbalanced datasets can result in selective detection, where a model accurately identifies images belonging to the majority classes but disregards those from minority classes. This causes the model to lack generalizability, preventing its use on newer data. This poses a significant challenge in developing image detection and diagnosis models for medical image datasets. To address this challenge, the One Shot GANs model was employed to augment the tail class of HAM10000 dataset by generating additional samples. Furthermore, to enhance accuracy, a novel metric tailored to suit One Shot GANs was utilized.
Authors: Masato Fujitake
Abstract: In this paper, we create benchmarks and assess the effectiveness of error correction methods for Japanese vouchers in OCR (Optical Character Recognition) systems. It is essential for automation processing to correctly recognize scanned voucher text, such as the company name on invoices. However, perfect recognition is complex due to the noise, such as stamps. Therefore, it is crucial to correctly rectify erroneous OCR results. However, no publicly available OCR error correction benchmarks for Japanese exist, and methods have not been adequately researched. In this study, we measured text recognition accuracy by existing services on Japanese vouchers and developed a post-OCR correction benchmark. Then, we proposed simple baselines for error correction using language models and verified whether the proposed method could effectively correct these errors. In the experiments, the proposed error correction algorithm significantly improved overall recognition accuracy.
Authors: Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong, Chenguang Zhu, Zhengxing Chen, Liang Tan, Chloe Bi, Mike Lewis, Sravya Popuri, Sharan Narang, Melanie Kambadur, Dhruv Mahajan, Sergey Edunov, Jiawei Han, Laurens van der Maaten
Abstract: The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term cross capabilities. To systematically explore this concept, we first define seven core individual capabilities and then pair them to form seven common cross capabilities, each supported by a manually constructed taxonomy. Building on these definitions, we introduce CrossEval, a benchmark comprising 1,400 human-annotated prompts, with 100 prompts for each individual and cross capability. To ensure reliable evaluation, we involve expert annotators to assess 4,200 model responses, gathering 8,400 human ratings with detailed explanations to serve as reference examples. Our findings reveal that, in both static evaluations and attempts to enhance specific abilities, current LLMs consistently exhibit the "Law of the Weakest Link," where cross-capability performance is significantly constrained by the weakest component. Specifically, across 58 cross-capability scores from 17 models, 38 scores are lower than all individual capabilities, while 20 fall between strong and weak, but closer to the weaker ability. These results highlight the under-performance of LLMs in cross-capability tasks, making the identification and improvement of the weakest capabilities a critical priority for future research to optimize performance in complex, multi-dimensional scenarios.
Authors: Minghao Wang
Abstract: Milk is a highly important consumer for Americans and the health of the cows' teats directly affects the quality of the milk. Traditionally, veterinarians manually assessed teat health by visually inspecting teat-end hyperkeratosis during the milking process which is limited in time, usually only tens of seconds, and weakens the accuracy of the health assessment of cows' teats. Convolutional neural networks (CNNs) have been used for cows' teat-end health assessment. However, there are challenges in using CNNs for cows' teat-end health assessment, such as complex environments, changing positions and postures of cows' teats, and difficulty in identifying cows' teats from images. To address these challenges, this paper proposes a cows' teats self-attention residual convolutional neural network (CTSAR-CNN) model that combines residual connectivity and self-attention mechanisms to assist commercial farms in the health assessment of cows' teats by classifying the magnitude of teat-end hyperkeratosis using digital images. The results showed that upon integrating residual connectivity and self-attention mechanisms, the accuracy of CTSAR-CNN has been improved. This research illustrates that CTSAR-CNN can be more adaptable and speedy to assist veterinarians in assessing the health of cows' teats and ultimately benefit the dairy industry.
Authors: Adri\'an Rodr\'iguez-Mu\~noz, Tongzhou Wang, Antonio Torralba
Abstract: Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training, which explicitly enforces models to perform well on perturbed examples. In this work, we show the surprising effectiveness of instead regularizing the gradient with respect to model inputs on natural examples only. Penalizing input Gradient Norm is commonly believed to be a much inferior approach. Our analyses identify that the performance of Gradient Norm regularization critically depends on the smoothness of activation functions, and are in fact extremely effective on modern vision transformers that adopt smooth activations over piecewise linear ones (eg, ReLU), contrary to prior belief. On ImageNet-1k, Gradient Norm training achieves > 90% the performance of state-of-the-art PGD-3 Adversarial Training} (52% vs.~56%), while using only 60% computation cost of the state-of-the-art without complex adversarial optimization. Our analyses also highlight the relationship between model robustness and properties of natural input gradients, such as asymmetric sample and channel statistics. Surprisingly, we find model robustness can be significantly improved by simply regularizing its gradients to concentrate on image edges without explicit conditioning on the gradient norm.
Authors: Petr Vanc, Giovanni Franzese, Jan Kristof Behrens, Cosimo Della Santina, Karla Stepanova, Jens Kober
Abstract: Learning from demonstration is a promising way of teaching robots new skills. However, a central problem when executing acquired skills is to recognize risks and failures. This is essential since the demonstrations usually cover only a few mostly successful cases. Inevitable errors during execution require specific reactions that were not apparent in the demonstrations. In this paper, we focus on teaching the robot situational awareness from an initial skill demonstration via kinesthetic teaching and sparse labeling of autonomous skill executions as safe or risky. At runtime, our system, called ILeSiA, detects risks based on the perceived camera images by encoding the images into a low-dimensional latent space representation and training a classifier based on the encoding and the provided labels. In this way, ILeSiA boosts the confidence and safety with which robotic skills can be executed. Our experiments demonstrate that classifiers, trained with only a small amount of user-provided data, can successfully detect numerous risks. The system is flexible because the risk cases are defined by labeling data. This also means that labels can be added as soon as risks are identified by a human supervisor. We provide all code and data required to reproduce our experiments at imitrob.ciirc.cvut.cz/publications/ilesia.
Authors: Aiman Farooq, Deepak Mishra, Santanu Chaudhury
Abstract: Survival prediction is a crucial task associated with cancer diagnosis and treatment planning. This paper presents a novel approach to survival prediction by harnessing comprehensive information from CT and PET scans, along with associated Genomic data. Current methods rely on either a single modality or the integration of multiple modalities for prediction without adequately addressing associations across patients or modalities. We aim to develop a robust predictive model for survival outcomes by integrating multi-modal imaging data with genetic information while accounting for associations across patients and modalities. We learn representations for each modality via a self-supervised module and harness the semantic similarities across the patients to ensure the embeddings are aligned closely. However, optimizing solely for global relevance is inadequate, as many pairs sharing similar high-level semantics, such as tumor type, are inadvertently pushed apart in the embedding space. To address this issue, we use a cross-patient module (CPM) designed to harness inter-subject correspondences. The CPM module aims to bring together embeddings from patients with similar disease characteristics. Our experimental evaluation of the dataset of Non-Small Cell Lung Cancer (NSCLC) patients demonstrates the effectiveness of our approach in predicting survival outcomes, outperforming state-of-the-art methods.
Authors: Tillmann Rheude, Andreas Wirtz, Arjan Kuijper, Stefan Wesarg
Abstract: Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the understanding of the accurate decision-making process of a CNN is rather unknown. The research area of explainable artificial intelligence (xAI) primarily revolves around understanding and interpreting this black-box behavior. One way of interpreting a CNN is the use of class activation maps (CAMs) that represent heatmaps to indicate the importance of image areas for the prediction of the CNN. For classification tasks, a variety of CAM algorithms exist. But for segmentation tasks, only one CAM algorithm for the interpretation of the output of a CNN exist. We propose a transfer between existing classification- and segmentation-based methods for more detailed, explainable, and consistent results which show salient pixels in semantic segmentation tasks. The resulting Seg-HiRes-Grad CAM is an extension of the segmentation-based Seg-Grad CAM with the transfer to the classification-based HiRes CAM. Our method improves the previously-mentioned existing segmentation-based method by adjusting it to recently published classification-based methods. Especially for medical image segmentation, this transfer solves existing explainability disadvantages.
Authors: Hongrui Zhao, Boris Ivanovic, Negar Mehr
Abstract: Effective environment perception is crucial for enabling downstream robotic applications. Individual robotic agents often face occlusion and limited visibility issues, whereas multi-agent systems can offer a more comprehensive mapping of the environment, quicker coverage, and increased fault tolerance. In this paper, we propose a collaborative multi-agent perception system where agents collectively learn a neural radiance field (NeRF) from posed RGB images to represent a scene. Each agent processes its local sensory data and shares only its learned NeRF model with other agents, reducing communication overhead. Given NeRF's low memory footprint, this approach is well-suited for robotic systems with limited bandwidth, where transmitting all raw data is impractical. Our distributed learning framework ensures consistency across agents' local NeRF models, enabling convergence to a unified scene representation. We show the effectiveness of our method through an extensive set of experiments on datasets containing challenging real-world scenes, achieving performance comparable to centralized mapping of the environment where data is sent to a central server for processing. Additionally, we find that multi-agent learning provides regularization benefits, improving geometric consistency in scenarios with sparse input views. We show that in such scenarios, multi-agent mapping can even outperform centralized training.
Authors: Yuran Wang, Zhijing Wan, Yansheng Qiu, Zheng Wang
Abstract: In the realm of medical image analysis, self-supervised learning (SSL) techniques have emerged to alleviate labeling demands, while still facing the challenge of training data scarcity owing to escalating resource requirements and privacy constraints. Numerous efforts employ generative models to generate high-fidelity, unlabeled 3D volumes across diverse modalities and anatomical regions. However, the intricate and indistinguishable anatomical structures within the abdomen pose a unique challenge to abdominal CT volume generation compared to other anatomical regions. To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation. We design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports. Volumes generated through our method demonstrate remarkable fidelity in reproducing abdominal structures, achieving a decrease in FID score from 0.0034 to 0.0002 on AbdomenCT-1K dataset, closely mirroring authentic data and surpassing current methods. Extensive experiments demonstrate the effectiveness of our method in self-supervised organ segmentation tasks, resulting in an improvement in mean Dice scores on two abdominal datasets effectively. These results underscore the potential of synthetic data to advance self-supervised learning in medical image analysis.
Authors: Osama Mustafa
Abstract: The application of deep learning in cancer research, particularly in early diagnosis, case understanding, and treatment strategy design, emphasizes the need for high-quality data. Generative AI, especially Generative Adversarial Networks (GANs), has emerged as a leading solution to challenges like class imbalance, robust learning, and model training, while addressing issues stemming from patient privacy and the scarcity of real data. Despite their promise, GANs face several challenges, both inherent and specific to histopathology data. Inherent issues include training imbalance, mode collapse, linear learning from insufficient discriminator feedback, and hard boundary convergence due to stringent feedback. Histopathology data presents a unique challenge with its complex representation, high spatial resolution, and multiscale features. To address these challenges, we propose a framework consisting of two components. First, we introduce a contrastive learning-based Multistage Progressive Finetuning Siamese Neural Network (MFT-SNN) for assessing the similarity between histopathology patches. Second, we implement a Reinforcement Learning-based External Optimizer (RL-EO) within the GAN training loop, serving as a reward signal generator. The modified discriminator loss function incorporates a weighted reward, guiding the GAN to maximize this reward while minimizing loss. This approach offers an external optimization guide to the discriminator, preventing generator overfitting and ensuring smooth convergence. Our proposed solution has been benchmarked against state-of-the-art (SOTA) GANs and a Denoising Diffusion Probabilistic model, outperforming previous SOTA across various metrics, including FID score, KID score, Perceptual Path Length, and downstream classification tasks.
Authors: Gowtham Krishnan Murugesan, Diana McCrumb, Rahul Soni, Jithendra Kumar, Leonard Nuernberg, Linmin Pei, Ulrike Wagner, Sutton Granger, Andrey Y. Fedorov, Stephen Moore, Jeff Van Oss
Abstract: AI in Medical Imaging project aims to enhance the National Cancer Institute's (NCI) Image Data Commons (IDC) by developing nnU-Net models and providing AI-assisted segmentations for cancer radiology images. We created high-quality, AI-annotated imaging datasets for 11 IDC collections. These datasets include images from various modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), covering the lungs, breast, brain, kidneys, prostate, and liver. The nnU-Net models were trained using open-source datasets. A portion of the AI-generated annotations was reviewed and corrected by radiologists. Both the AI and radiologist annotations were encoded in compliance with the the Digital Imaging and Communications in Medicine (DICOM) standard, ensuring seamless integration into the IDC collections. All models, images, and annotations are publicly accessible, facilitating further research and development in cancer imaging. This work supports the advancement of imaging tools and algorithms by providing comprehensive and accurate annotated datasets.
Authors: Yizhou Huang, Yihua Cheng, Kezhi Wang
Abstract: Deep learning architectures with powerful reasoning capabilities have driven significant advancements in autonomous driving technology. Large language models (LLMs) applied in this field can describe driving scenes and behaviors with a level of accuracy similar to human perception, particularly in visual tasks. Meanwhile, the rapid development of edge computing, with its advantage of proximity to data sources, has made edge devices increasingly important in autonomous driving. Edge devices process data locally, reducing transmission delays and bandwidth usage, and achieving faster response times. In this work, we propose a driving behavior narration and reasoning framework that applies LLMs to edge devices. The framework consists of multiple roadside units, with LLMs deployed on each unit. These roadside units collect road data and communicate via 5G NSR/NR networks. Our experiments show that LLMs deployed on edge devices can achieve satisfactory response speeds. Additionally, we propose a prompt strategy to enhance the narration and reasoning performance of the system. This strategy integrates multi-modal information, including environmental, agent, and motion data. Experiments conducted on the OpenDV-Youtube dataset demonstrate that our approach significantly improves performance across both tasks.
Authors: Chenglin Fang, Kaigui Wu
Abstract: The U-Net model has consistently demonstrated strong performance in the field of medical image segmentation, with various improvements and enhancements made since its introduction. This paper presents a novel architecture that integrates KAN networks with U-Net, leveraging the powerful nonlinear representation capabilities of KAN networks alongside the established strengths of U-Net. We introduce a KAN-convolution dual-channel structure that enables the model to more effectively capture both local and global features. We explore effective methods for fusing features extracted by KAN with those obtained through convolutional layers, utilizing an auxiliary network to facilitate this integration process. Experiments conducted across multiple datasets show that our model performs well in terms of accuracy, indicating that the KAN-convolution dual-channel approach has significant potential in medical image segmentation tasks.
Authors: Fan Yuan, Chi Qin, Xiaogang Xu, Piji Li
Abstract: Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the images. Many existing work detects hallucination by directly judging whether an object exists in an image, overlooking the association between the object and semantics. To address this issue, we propose Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding (HELPD). This framework incorporates hallucination feedback at both object and sentence semantic levels. Remarkably, even with a marginal degree of training, this approach can alleviate over 15% of hallucination. Simultaneously, HELPD penalizes the output logits according to the image attention window to avoid being overly affected by generated text. HELPD can be seamlessly integrated with any LVLMs. Our experiments demonstrate that the proposed framework yields favorable results across multiple hallucination benchmarks. It effectively mitigates hallucination for different LVLMs and concurrently improves their text generation quality.
Authors: Eugenio Lomurno, Samuele Mariani, Matteo Monti, Matteo Matteucci
Abstract: Neural Architecture Search (NAS) automates neural network design, reducing dependence on human expertise. While NAS methods are computationally intensive and dataset-specific, auxiliary predictors reduce the models needing training, decreasing search time. This strategy is used to generate architectures satisfying multiple computational constraints. Recently, Transferable NAS has emerged, generalizing the search process from dataset-dependent to task-dependent. In this field, DiffusionNAG is a state-of-the-art method. This diffusion-based approach streamlines computation, generating architectures optimized for accuracy on unseen datasets without further adaptation. However, by focusing solely on accuracy, DiffusionNAG overlooks other crucial objectives like model complexity, computational efficiency, and inference latency -- factors essential for deploying models in resource-constrained environments. This paper introduces the Pareto-Optimal Many-Objective Neural Architecture Generator (POMONAG), extending DiffusionNAG via a many-objective diffusion process. POMONAG simultaneously considers accuracy, number of parameters, multiply-accumulate operations (MACs), and inference latency. It integrates Performance Predictor models to estimate these metrics and guide diffusion gradients. POMONAG's optimization is enhanced by expanding its training Meta-Dataset, applying Pareto Front Filtering, and refining embeddings for conditional generation. These enhancements enable POMONAG to generate Pareto-optimal architectures that outperform the previous state-of-the-art in performance and efficiency. Results were validated on two search spaces -- NASBench201 and MobileNetV3 -- and evaluated across 15 image classification datasets.
Authors: Divyanshu Daiya, Damon Conover, Aniket Bera
Abstract: We propose a novel framework COLLAGE for generating collaborative agent-object-agent interactions by leveraging large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-VAEs). Our model addresses the lack of rich datasets in this domain by incorporating the knowledge and reasoning abilities of LLMs to guide a generative diffusion model. The hierarchical VQ-VAE architecture captures different motion-specific characteristics at multiple levels of abstraction, avoiding redundant concepts and enabling efficient multi-resolution representation. We introduce a diffusion model that operates in the latent space and incorporates LLM-generated motion planning cues to guide the denoising process, resulting in prompt-specific motion generation with greater control and diversity. Experimental results on the CORE-4D, and InterHuman datasets demonstrate the effectiveness of our approach in generating realistic and diverse collaborative human-object-human interactions, outperforming state-of-the-art methods. Our work opens up new possibilities for modeling complex interactions in various domains, such as robotics, graphics and computer vision.
Authors: Lirui Wang, Xinlei Chen, Jialiang Zhao, Kaiming He
Abstract: One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This work studies the problem of learning policy representations through heterogeneous pre-training on robot data across different embodiments and tasks at scale. We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a large, shareable trunk of a policy neural network to learn a task and embodiment agnostic shared representation. This general architecture aligns the specific proprioception and vision inputs from distinct embodiments to a short sequence of tokens and then processes such tokens to map to control robots for different tasks. Leveraging the recent large-scale multi-embodiment real-world robotic datasets as well as simulation, deployed robots, and human video datasets, we investigate pre-training policies across heterogeneity. We conduct experiments to investigate the scaling behaviors of training objectives, to the extent of 52 datasets. HPTs outperform several baselines and enhance the fine-tuned policy performance by over 20% on unseen tasks in multiple simulator benchmarks and real-world settings. See the project website (https://liruiw.github.io/hpt/) for code and videos.
Authors: Lingchao Mao, Qi wang, Yi Su, Fleming Lure, Jing Li
Abstract: Learning from multimodal datasets can leverage complementary information and improve performance in prediction tasks. A commonly used strategy to account for feature correlations in high-dimensional datasets is the latent variable approach. Several latent variable methods have been proposed for multimodal datasets. However, these methods either focus on extracting the shared component across all modalities or on extracting both a shared component and individual components specific to each modality. To address this gap, we propose a Multi-Modal Fission Learning (MMFL) model that simultaneously identifies globally joint, partially joint, and individual components underlying the features of multimodal datasets. Unlike existing latent variable methods, MMFL uses supervision from the response variable to identify predictive latent components and has a natural extension for incorporating incomplete multimodal data. Through simulation studies, we demonstrate that MMFL outperforms various existing multimodal algorithms in both complete and incomplete modality settings. We applied MMFL to a real-world case study for early prediction of Alzheimers Disease using multimodal neuroimaging and genomics data from the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset. MMFL provided more accurate predictions and better insights into within- and across-modality correlations compared to existing methods.
Authors: Xiaopan Zhang, Hao Qin, Fuquan Wang, Yue Dong, Jiachen Li
Abstract: Language models (LMs) possess a strong capability to comprehend natural language, making them effective in translating human instructions into detailed plans for simple robot tasks. Nevertheless, it remains a significant challenge to handle long-horizon tasks, especially in subtask identification and allocation for cooperative heterogeneous robot teams. To address this issue, we propose a Language Model-Driven Multi-Agent PDDL Planner (LaMMA-P), a novel multi-agent task planning framework that achieves state-of-the-art performance on long-horizon tasks. LaMMA-P integrates the strengths of the LMs' reasoning capability and the traditional heuristic search planner to achieve a high success rate and efficiency while demonstrating strong generalization across tasks. Additionally, we create MAT-THOR, a comprehensive benchmark that features household tasks with two different levels of complexity based on the AI2-THOR environment. The experimental results demonstrate that LaMMA-P achieves a 105% higher success rate and 36% higher efficiency than existing LM-based multi-agent planners. The experimental videos, code, and datasets of this work as well as the detailed prompts used in each module are available at https://lamma-p.github.io.
Authors: Russell Mendonca, Emmanuel Panov, Bernadette Bucher, Jiuguang Wang, Deepak Pathak
Abstract: We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by 1) task-relevant autonomy, which guides exploration towards object interactions and prevents stagnation near goal states, 2) efficient policy learning by leveraging basic task knowledge in behavior priors, and 3) formulating generic rewards that combine human-interpretable semantic information with low-level, fine-grained observations. We demonstrate that our approach allows Spot robots to continually improve their performance on a set of four challenging mobile manipulation tasks, obtaining an average success rate of 80% across tasks, a 3-4 improvement over existing approaches. Videos can be found at https://continual-mobile-manip.github.io/
Authors: Guangyang Zhu, Jianfeng Zhang, Yuanzhi Feng, Hai Lan
Abstract: Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the dot product multiplication and dimension alignment among query-key-value features, which cause two problems: (1) The dot product multiplication results in exhaustive and redundant computation. (2) Due to the visual feature map often appearing as a multi-dimensional tensor, reshaping the scale of the tensor feature to adapt to the dimension alignment might destroy the internal structure of the tensor feature map. To address these problems, this paper proposes a self-attention plug-in module with its variants, namely, Synthesizing Tensor Transformations (STT), for directly processing image tensor features. Without computing the dot-product multiplication among query-key-value, the basic STT is composed of the tensor transformation to learn the synthetic attention weight from visual information. The effectiveness of STT series is validated on the image classification and image caption. Experiments show that the proposed STT achieves competitive performance while keeping robustness compared to self-attention in the aforementioned vision tasks.
Authors: Ohad Amosy, Tomer Volk, Eilam Shapira, Eyal Ben-David, Roi Reichart, Gal Chechik
Abstract: We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that learn a fixed representation of the output classes, we generate at inference time a model tailored to a query classification task. To generate task-based zero-shot classifiers, we train a hypernetwork that receives class descriptions and outputs a multi-class model. The hypernetwork is designed to be equivariant with respect to the set of descriptions and the classification layer, thus obeying the symmetries of the problem and improving generalization. Our approach generates non-linear classifiers, handles rich textual descriptions, and may be adapted to produce lightweight models efficient enough for on-device applications. We evaluate this approach in a series of zero-shot classification tasks, for image, point-cloud, and action recognition, using a range of text descriptions: From single words to rich descriptions. Our results demonstrate strong improvements over previous approaches, showing that zero-shot learning can be applied with little training data. Furthermore, we conduct an analysis with foundational vision and language models, demonstrating that they struggle to generalize when describing what attributes the class lacks.
Authors: Jie Gui, Tuo Chen, Minjing Dong, Zhengqi Liu, Hao Luo, James Tin-Yau Kwok, Yuan Yan Tang
Abstract: Recently, masked image modeling (MIM), which learns visual representations by reconstructing the masked patches of an image, has dominated self-supervised learning in computer vision. However, the pre-training of MIM always takes massive time due to the large-scale data and large-size backbones. We mainly attribute it to the random patch masking in previous MIM works, which fails to leverage the crucial semantic information for effective visual representation learning. To tackle this issue, we propose the Frequency \& Attention-driven Masking and Throwing Strategy (FAMT), which can extract semantic patches and reduce the number of training patches to boost model performance and training efficiency simultaneously. Specifically, FAMT utilizes the self-attention mechanism to extract semantic information from the image for masking during training in an unsupervised manner. However, attention alone could sometimes focus on inappropriate areas regarding the semantic information. Thus, we are motivated to incorporate the information from the frequency domain into the self-attention mechanism to derive the sampling weights for masking, which captures semantic patches for visual representation learning. Furthermore, we introduce a patch throwing strategy based on the derived sampling weights to reduce the training cost. FAMT can be seamlessly integrated as a plug-and-play module and surpasses previous works, \emph{e.g.} reducing the training phase time by nearly $50\%$ and improving the linear probing accuracy of MAE by $1.3\% \sim 3.9\%$ across various datasets, including CIFAR-10/100, Tiny ImageNet, and ImageNet-1K. FAMT also demonstrates superior performance in downstream detection and segmentation tasks.
Authors: Ning Yu, Chia-Chih Chen, Zeyuan Chen, Rui Meng, Gang Wu, Paul Josel, Juan Carlos Niebles, Caiming Xiong, Ran Xu
Abstract: Graphic layout designs play an essential role in visual communication. Yet handcrafting layout designs is skill-demanding, time-consuming, and non-scalable to batch production. Generative models emerge to make design automation scalable but it remains non-trivial to produce designs that comply with designers' multimodal desires, i.e., constrained by background images and driven by foreground content. We propose LayoutDETR that inherits the high quality and realism from generative modeling, while reformulating content-aware requirements as a detection problem: we learn to detect in a background image the reasonable locations, scales, and spatial relations for multimodal foreground elements in a layout. Our solution sets a new state-of-the-art performance for layout generation on public benchmarks and on our newly-curated ad banner dataset. We integrate our solution into a graphical system that facilitates user studies, and show that users prefer our designs over baselines by significant margins. Code, models, dataset, and demos are available at https://github.com/salesforce/LayoutDETR.
Authors: Biao Gong, Shuai Tan, Yutong Feng, Xiaoying Xie, Yuyuan Li, Chaochao Chen, Kecheng Zheng, Yujun Shen, Deli Zhao
Abstract: This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. Particularly focusing on visual and linguistic modalities, we categorize data knowledge into five unit types, namely, in-image, in-text, cross-image, cross-text, and image-text, and set up an efficient pipeline to help construct the multimodal knowledge graph from any data collection. Thanks to the logical information naturally contained in knowledge graph, organizing datasets under UKnow format opens up more possibilities of data usage compared to the commonly used image-text pairs. Following UKnow protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset that consists of 1,388,568 nodes (with 571,791 vision-related ones) and 3,673,817 triplets. The dataset is also annotated with rich event tags, including 11 coarse labels and 9,185 fine labels. Experiments on 4 benchmarks demonstrate the potential of UKnow in supporting common-sense reasoning and boosting vision-language pre-training with a single dataset, benefiting from its unified form of knowledge organization. See Appendix to download the dataset.
Authors: Daniel N. Nissani (Nissensohn)
Abstract: In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A significant portion of these consist of the presented object attributes. Contrastive learning is a semi-supervised learning scheme based on the application of identity preserving transformations on the object input representations. It is conjectured in this work that these same applied transformations preserve, in addition to the identity of the presented object, also the identity of its semantically meaningful attributes. The corollary of this is that the output representations of such a contrastive learning scheme contain valuable information not only for the classification of the presented object, but also for the presence or absence decision of any attribute of interest. Simulation results which demonstrate this idea and the feasibility of this conjecture are presented.
Authors: Jianqiu Chen, Zikun Zhou, Mingshan Sun, Tianpeng Bao, Rui Zhao, Liwei Wu, Zhenyu He
Abstract: Many robotics and industry applications have a high demand for the capability to estimate the 6D pose of novel objects from the cluttered scene. However, existing classic pose estimation methods are object-specific, which can only handle the specific objects seen during training. When applied to a novel object, these methods necessitate a cumbersome onboarding process, which involves extensive dataset preparation and model retraining. The extensive duration and resource consumption of onboarding limit their practicality in real-world applications. In this paper, we introduce ZeroPose, a novel zero-shot framework that performs pose estimation following a Discovery-Orientation-Registration (DOR) inference pipeline. This framework generalizes to novel objects without requiring model retraining. Given the CAD model of a novel object, ZeroPose enables in seconds onboarding time to extract visual and geometric embeddings from the CAD model as a prompt. With the prompting of the above embeddings, DOR can discover all related instances and estimate their 6D poses without additional human interaction or presupposing scene conditions. Compared with existing zero-shot methods solved by the render-and-compare paradigm, the DOR pipeline formulates the object pose estimation into a feature-matching problem, which avoids time-consuming online rendering and improves efficiency. Experimental results on the seven datasets show that ZeroPose as a zero-shot method achieves comparable performance with object-specific training methods and outperforms the state-of-the-art zero-shot method with 50x inference speed improvement.
Authors: Yiming Li, Sihang Li, Xinhao Liu, Moonjun Gong, Kenan Li, Nuo Chen, Zijun Wang, Zhiheng Li, Tao Jiang, Fisher Yu, Yue Wang, Hang Zhao, Zhiding Yu, Chen Feng
Abstract: Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field.
Authors: Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
Abstract: Open-vocabulary segmentation is the task of segmenting anything that can be named in an image. Recently, large-scale vision-language modelling has led to significant advances in open-vocabulary segmentation, but at the cost of gargantuan and increasing training and annotation efforts. Hence, we ask if it is possible to use existing foundation models to synthesise on-demand efficient segmentation algorithms for specific class sets, making them applicable in an open-vocabulary setting without the need to collect further data, annotations or perform training. To that end, we present OVDiff, a novel method that leverages generative text-to-image diffusion models for unsupervised open-vocabulary segmentation. OVDiff synthesises support image sets for arbitrary textual categories, creating for each a set of prototypes representative of both the category and its surrounding context (background). It relies solely on pre-trained components and outputs the synthesised segmenter directly, without training. Our approach shows strong performance on a range of benchmarks, obtaining a lead of more than 5% over prior work on PASCAL VOC.
Authors: Matt Allen, Francisco Dorr, Joseph A. Gallego-Mejia, Laura Mart\'inez-Ferrer, Anna Jungbluth, Freddie Kalaitzis, Ra\'ul Ramos-Poll\'an
Abstract: Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy decision making, but the timeliness and accuracy of these interventions is limited by use of optical data, which cannot operate at night and is affected by adverse weather conditions. Synthetic Aperture Radar (SAR) offers a robust alternative to optical data, but its associated complexities limit the scope of labelled data generation for traditional deep learning. In this work, we apply a self-supervised pretraining scheme, masked autoencoding, to SAR amplitude data covering 8.7\% of the Earth's land surface area, and tune the pretrained weights on two downstream tasks crucial to monitoring climate change - vegetation cover prediction and land cover classification. We show that the use of this pretraining scheme reduces labelling requirements for the downstream tasks by more than an order of magnitude, and that this pretraining generalises geographically, with the performance gain increasing when tuned downstream on regions outside the pretraining set. Our findings significantly advance climate change mitigation by facilitating the development of task and region-specific SAR models, allowing local communities and organizations to deploy tailored solutions for rapid, accurate monitoring of climate change effects.
Authors: Che Liu, Sibo Cheng, Miaojing Shi, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: In the field of medical Vision-Language Pre-training (VLP), significant efforts have been devoted to deriving text and image features from both clinical reports and associated medical images. However, most existing methods may have overlooked the opportunity in leveraging the inherent hierarchical structure of clinical reports, which are generally split into `findings' for descriptive content and `impressions' for conclusive observation. Instead of utilizing this rich, structured format, current medical VLP approaches often simplify the report into either a unified entity or fragmented tokens. In this work, we propose a novel clinical prior guided VLP framework named IMITATE to learn the structure information from medical reports with hierarchical vision-language alignment. The framework derives multi-level visual features from the chest X-ray (CXR) images and separately aligns these features with the descriptive and the conclusive text encoded in the hierarchical medical report. Furthermore, a new clinical-informed contrastive loss is introduced for cross-modal learning, which accounts for clinical prior knowledge in formulating sample correlations in contrastive learning. The proposed model, IMITATE, outperforms baseline VLP methods across six different datasets, spanning five medical imaging downstream tasks. Comprehensive experimental results highlight the advantages of integrating the hierarchical structure of medical reports for vision-language alignment.
Authors: Keunwoo Peter Yu, Zheyuan Zhang, Fengyuan Hu, Shane Storks, Joyce Chai
Abstract: A major reason behind the recent success of large language models (LLMs) is their \textit{in-context learning} capability, which makes it possible to rapidly adapt them to downstream text-based tasks by prompting them with a small number of relevant demonstrations. While large vision-language models (VLMs) have recently been developed for tasks requiring both text and images, they largely lack in-context learning over visual information, especially in understanding and generating text about videos. In this work, we implement \textbf{E}mergent \textbf{I}n-context \textbf{Le}arning on \textbf{V}ideos (\eilev{}), a novel training paradigm that induces in-context learning over video and text by capturing key properties of pre-training data found by prior work to be essential for in-context learning in transformers. In our experiments, we show that \eilev-trained models outperform other off-the-shelf VLMs in few-shot video narration for novel, rare actions. Furthermore, we demonstrate that these key properties of bursty distributions, skewed marginal distributions, and dynamic meaning each contribute to varying degrees to VLMs' in-context learning capability in narrating procedural videos. Our results, analysis, and \eilev{}-trained models yield numerous insights about the emergence of in-context learning over video and text, creating a foundation for future work to optimize and scale VLMs for open-domain video understanding and reasoning. Our code and demo are available at \url{https://github.com/yukw777/EILEV}.
Authors: Amber Yijia Zheng, Raymond A. Yeh
Abstract: Advancements in open-sourced text-to-image models and fine-tuning methods have led to the increasing risk of malicious adaptation, i.e., fine-tuning to generate harmful/unauthorized content. Recent works, e.g., Glaze or MIST, have developed data-poisoning techniques which protect the data against adaptation methods. In this work, we consider an alternative paradigm for protection. We propose to ``immunize'' the model by learning model parameters that are difficult for the adaptation methods when fine-tuning malicious content; in short IMMA. Specifically, IMMA should be applied before the release of the model weights to mitigate these risks. Empirical results show IMMA's effectiveness against malicious adaptations, including mimicking the artistic style and learning of inappropriate/unauthorized content, over three adaptation methods: LoRA, Textual-Inversion, and DreamBooth. The code is available at \url{https://github.com/amberyzheng/IMMA}.
Authors: Che Liu, Cheng Ouyang, Sibo Cheng, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: Recently, medical vision-language pre-training (VLP) has reached substantial progress to learn global visual representation from medical images and their paired radiology reports. However, medical imaging tasks in real world usually require finer granularity in visual features. These tasks include visual localization tasks (e.g., semantic segmentation, object detection) and visual grounding task. Yet, current medical VLP methods face challenges in learning these fine-grained features, as they primarily focus on brute-force alignment between image patches and individual text tokens for local visual feature learning, which is suboptimal for downstream dense prediction tasks. In this work, we propose a new VLP framework, named \textbf{G}lobal to \textbf{D}ense level representation learning (G2D) that achieves significantly improved granularity and more accurate grounding for the learned features, compared to existing medical VLP approaches. In particular, G2D learns dense and semantically-grounded image representations via a pseudo segmentation task parallel with the global vision-language alignment. Notably, generating pseudo segmentation targets does not incur extra trainable parameters: they are obtained on the fly during VLP with a parameter-free processor. G2D achieves superior performance across 6 medical imaging tasks and 25 diseases, particularly in semantic segmentation, which necessitates fine-grained, semantically-grounded image features. In this task, G2D surpasses peer models even when fine-tuned with just 1\% of the training data, compared to the 100\% used by these models. The code will be released upon acceptance.
Authors: Jiakai Zhang, Qihe Chen, Yan Zeng, Wenyuan Gao, Xuming He, Zhijie Liu, Jingyi Yu
Abstract: In the past decade, deep conditional generative models have revolutionized the generation of realistic images, extending their application from entertainment to scientific domains. Single-particle cryo-electron microscopy (cryo-EM) is crucial in resolving near-atomic resolution 3D structures of proteins, such as the SARS- COV-2 spike protein. To achieve high-resolution reconstruction, a comprehensive data processing pipeline has been adopted. However, its performance is still limited as it lacks high-quality annotated datasets for training. To address this, we introduce physics-informed generative cryo-electron microscopy (CryoGEM), which for the first time integrates physics-based cryo-EM simulation with a generative unpaired noise translation to generate physically correct synthetic cryo-EM datasets with realistic noises. Initially, CryoGEM simulates the cryo-EM imaging process based on a virtual specimen. To generate realistic noises, we leverage an unpaired noise translation via contrastive learning with a novel mask-guided sampling scheme. Extensive experiments show that CryoGEM is capable of generating authentic cryo-EM images. The generated dataset can used as training data for particle picking and pose estimation models, eventually improving the reconstruction resolution.
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: Kohei Yamashita, Vincent Lepetit, Ko Nishino
Abstract: Computer vision has long relied on two kinds of correspondences: pixel correspondences in images and 3D correspondences on object surfaces. Is there another kind, and if there is, what can they do for us? In this paper, we introduce correspondences of the third kind we call reflection correspondences and show that they can help estimate camera pose by just looking at objects without relying on the background. Reflection correspondences are point correspondences in the reflected world, i.e., the scene reflected by the object surface. The object geometry and reflectance alters the scene geometrically and radiometrically, respectively, causing incorrect pixel correspondences. Geometry recovered from each image is also hampered by distortions, namely generalized bas-relief ambiguity, leading to erroneous 3D correspondences. We show that reflection correspondences can resolve the ambiguities arising from these distortions. We introduce a neural correspondence estimator and a RANSAC algorithm that fully leverages all three kinds of correspondences for robust and accurate joint camera pose and object shape estimation just from the object appearance. The method expands the horizon of numerous downstream tasks, including camera pose estimation for appearance modeling (e.g., NeRF) and motion estimation of reflective objects (e.g., cars on the road), to name a few, as it relieves the requirement of overlapping background.
Authors: Jianbiao Mei, Yu Yang, Mengmeng Wang, Junyu Zhu, Jongwon Ra, Yukai Ma, Laijian Li, Yong Liu
Abstract: Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to camera-based SSC solutions due to the richer visual cues and cost-effectiveness of cameras. However, existing methods usually rely on sophisticated and heavy 3D models to process the lifted 3D features directly, which are not discriminative enough for clear segmentation boundaries. In this paper, we adopt the dense-sparse-dense design and propose a one-stage camera-based SSC framework, termed SGN, to propagate semantics from the semantic-aware seed voxels to the whole scene based on spatial geometry cues. Firstly, to exploit depth-aware context and dynamically select sparse seed voxels, we redesign the sparse voxel proposal network to process points generated by depth prediction directly with the coarse-to-fine paradigm. Furthermore, by designing hybrid guidance (sparse semantic and geometry guidance) and effective voxel aggregation for spatial geometry cues, we enhance the feature separation between different categories and expedite the convergence of semantic propagation. Finally, we devise the multi-scale semantic propagation module for flexible receptive fields while reducing the computation resources. Extensive experimental results on the SemanticKITTI and SSCBench-KITTI-360 datasets demonstrate the superiority of our SGN over existing state-of-the-art methods. And even our lightweight version SGN-L achieves notable scores of 14.80\% mIoU and 45.45\% IoU on SeamnticKITTI validation with only 12.5 M parameters and 7.16 G training memory. Code is available at https://github.com/Jieqianyu/SGN.
Authors: Minghui Zhang, Hao Zheng, Yawen Huang, Ling Shao, Yun Gu
Abstract: Shape modeling of volumetric medical images is crucial for quantitative analysis and surgical planning in computer-aided diagnosis. To alleviate the burden of expert clinicians, reconstructed shapes are typically obtained from deep learning models, such as Convolutional Neural Networks (CNNs) or transformer-based architectures, followed by the marching cube algorithm. However, automatic shape reconstruction often falls short of perfection due to the limited resolution of images and the absence of shape prior constraints. To overcome these limitations, we propose the Reliable Shape Interaction with Implicit Template (ReShapeIT) network, which models anatomical structures in continuous space rather than discrete voxel grids. ReShapeIT represents an anatomical structure with an implicit template field shared within the same category, complemented by a deformation field. It ensures the implicit template field generates valid templates by strengthening the constraint of the correspondence between the instance shape and the template shape. The valid template shape can then be utilized for implicit generalization. A Template Interaction Module (TIM) is introduced to reconstruct unseen shapes by interacting the valid template shapes with the instance-wise latent codes. Experimental results on three datasets demonstrate the superiority of our approach in anatomical structure reconstruction. The Chamfer Distance/Earth Mover's Distance achieved by ReShapeIT are 0.225/0.318 on Liver, 0.125/0.067 on Pancreas, and 0.414/0.098 on Lung Lobe.
Authors: Zihao Wang, Jing Zhao, Xuetong Ding, Hui Zhang
Abstract: Face plays an important role in humans visual perception, and reconstructing perceived faces from brain activities is challenging because of its difficulty in extracting high-level features and maintaining consistency of multiple face attributes, such as expression, identity, gender, etc. In this study, we proposed a novel reconstruction framework, which we called Double-Flow GAN, that can enhance the capability of discriminator and handle imbalances in images from certain domains that are too easy for generators. We also designed a pretraining process that uses features extracted from images as conditions for making it possible to pretrain the conditional reconstruction model from fMRI in a larger pure image dataset. Moreover, we developed a simple pretrained model for fMRI alignment to alleviate the problem of cross-subject reconstruction due to the variations of brain structure among different subjects. We conducted experiments by using our proposed method and traditional reconstruction models. Results showed that the proposed method is significant at accurately reconstructing multiple face attributes, outperforms the previous reconstruction models, and exhibited state-of-the-art reconstruction abilities.
Authors: Haifeng Huang, Yilun Chen, Zehan Wang, Rongjie Huang, Runsen Xu, Tai Wang, Luping Liu, Xize Cheng, Yang Zhao, Jiangmiao Pang, Zhou Zhao
Abstract: Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in general referencing and grounding capabilities for intricate scene comprehension. In this paper, we introduce the use of object identifiers and object-centric representations to interact with scenes at the object level. Specifically, we decompose the input 3D scene into a set of object proposals, each assigned a unique identifier token, which enables efficient object referencing and grounding during user-assistant interactions. Given the scarcity of scene-language data, we model the scene embeddings as a sequence of explicit object-level embeddings, derived from semantic-rich 2D or 3D representations. By employing object identifiers, we transform diverse 3D scene-language tasks into a unified question-answering format, facilitating joint training without the need for additional task-specific heads. With minimal fine-tuning on all downstream tasks, our model significantly outperforms existing methods on benchmarks including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.
Authors: Payam Jome Yazdian, Eric Liu, Rachel Lagasse, Hamid Mohammadi, Li Cheng, Angelica Lim
Abstract: This paper proposes MotionScript, a motion-to-text conversion algorithm and natural language representation for human body motions. MotionScript provides more detailed and accurate descriptions of human body movements compared to previous natural language methods. Most motion datasets focus on basic, well-defined actions, with limited variation in expression (e.g., sitting, walking, dribbling a ball). But for expressive actions that contain a diversity of movements in the class (e.g. being sad, dancing), or for actions outside the domain of standard motion capture datasets (e.g. stylistic walking, sign-language, interactions with animals), more specific and granular natural language descriptions are needed. Our proposed MotionScript descriptions differ from existing natural language representations in that it provides detailed descriptions in natural language rather than simple action labels or generalized captions. To the best of our knowledge, this is the first attempt at translating 3D motions to natural language descriptions without requiring training data. Our experiments demonstrate that MotionScript descriptions, when applied to text-to-motion tasks, enable large language models to generate complex, previously unseen motions. Additional examples, dataset, and code can be accessed at https://pjyazdian.github.io/MotionScript
Authors: Kaichen Zhou, Jia-Wang Bian, Qian Xie, Jian-Qing Zheng, Niki Trigoni, Andrew Markham
Abstract: Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, to achieve precise depth estimation for both dynamic objects and static backgrounds, all while maintaining computational efficiency. To tackle the challenges posed by dynamic content, we incorporate optical flow and coarse monocular depth to create a pseudo-static reference frame. This frame is then utilized to build a motion-aware cost volume in collaboration with the vanilla target frame. Additionally, to enhance the accuracy and resilience of the network structure, we introduce an attention-based depth net architecture to effectively integrate information from feature maps with varying resolutions. Compared to methods with similar computational costs, Manydepth2 achieves a significant reduction of approximately five percent in root-mean-square error for self-supervised monocular depth estimation on the KITTI-2015 dataset. The code could found https://github.com/kaichen-z/Manydepth2.
Authors: Woochul Kang, Hyungseop Lee
Abstract: Predictable adaptation of network depths can be an effective way to control inference latency and meet the resource condition of various devices. However, previous adaptive depth networks do not provide general principles and a formal explanation on why and which layers can be skipped, and, hence, their approaches are hard to be generalized and require long and complex training steps. In this paper, we present a practical approach to adaptive depth networks that is applicable to various networks with minimal training effort. In our approach, every hierarchical residual stage is divided into two sub-paths, and they are trained to acquire different properties through a simple self-distillation strategy. While the first sub-path is essential for hierarchical feature learning, the second one is trained to refine the learned features and minimize performance degradation if it is skipped. Unlike prior adaptive networks, our approach does not train every target sub-network in an iterative manner. At test time, however, we can connect these sub-paths in a combinatorial manner to select sub-networks of various accuracy-efficiency trade-offs from a single network. We provide a formal rationale for why the proposed training method can reduce overall prediction errors while minimizing the impact of skipping sub-paths. We demonstrate the generality and effectiveness of our approach with convolutional neural networks and transformers.
Authors: Wenyi Tan, Yang Li, Chenxing Zhao, Zhunga Liu, Quan Pan
Abstract: Object detection is a fundamental task in various applications ranging from autonomous driving to intelligent security systems. However, recognition of a person can be hindered when their clothing is decorated with carefully designed graffiti patterns, leading to the failure of object detection. To achieve greater attack potential against unknown black-box models, adversarial patches capable of affecting the outputs of multiple-object detection models are required. While ensemble models have proven effective, current research in the field of object detection typically focuses on the simple fusion of the outputs of all models, with limited attention being given to developing general adversarial patches that can function effectively in the physical world. In this paper, we introduce the concept of energy and treat the adversarial patches generation process as an optimization of the adversarial patches to minimize the total energy of the ``person'' category. Additionally, by adopting adversarial training, we construct a dynamically optimized ensemble model. During training, the weight parameters of the attacked target models are adjusted to find the balance point at which the generated adversarial patches can effectively attack all target models. We carried out six sets of comparative experiments and tested our algorithm on five mainstream object detection models. The adversarial patches generated by our algorithm can reduce the recognition accuracy of YOLOv2 and YOLOv3 to 13.19\% and 29.20\%, respectively. In addition, we conducted experiments to test the effectiveness of T-shirts covered with our adversarial patches in the physical world and could achieve that people are not recognized by the object detection model. Finally, leveraging the Grad-CAM tool, we explored the attack mechanism of adversarial patches from an energetic perspective.
Authors: Libin Lan, Pengzhou Cai, Lu Jiang, Xiaojuan Liu, Yongmei Li, Yudong Zhang
Abstract: Accurate medical image segmentation is essential for clinical quantification, disease diagnosis, treatment planning and many other applications. Both convolution-based and transformer-based u-shaped architectures have made significant success in various medical image segmentation tasks. The former can efficiently learn local information of images while requiring much more image-specific inductive biases inherent to convolution operation. The latter can effectively capture long-range dependency at different feature scales using self-attention, whereas it typically encounters the challenges of quadratic compute and memory requirements with sequence length increasing. To address this problem, through integrating the merits of these two paradigms in a well-designed u-shaped architecture, we propose a hybrid yet effective CNN-Transformer network, named BRAU-Net++, for an accurate medical image segmentation task. Specifically, BRAU-Net++ uses bi-level routing attention as the core building block to design our u-shaped encoder-decoder structure, in which both encoder and decoder are hierarchically constructed, so as to learn global semantic information while reducing computational complexity. Furthermore, this network restructures skip connection by incorporating channel-spatial attention which adopts convolution operations, aiming to minimize local spatial information loss and amplify global dimension-interaction of multi-scale features. Extensive experiments on three public benchmark datasets demonstrate that our proposed approach surpasses other state-of-the-art methods including its baseline: BRAU-Net under almost all evaluation metrics. We achieve the average Dice-Similarity Coefficient (DSC) of 82.47, 90.10, and 92.94 on Synapse multi-organ segmentation, ISIC-2018 Challenge, and CVC-ClinicDB, as well as the mIoU of 84.01 and 88.17 on ISIC-2018 Challenge and CVC-ClinicDB, respectively.
Authors: Yingbin Zhou, Yaping Sun, Guanying Chen, Xiaodong Xu, Hao Chen, Binhong Huang, Shuguang Cui, Ping Zhang
Abstract: Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face challenges with conflicting requirements between codebook design and digital constellation modulation. Traditional codebooks need wide index ranges, while modulation favors few discrete states. To address this, we propose a multilevel generative semantic communication system with a two-stage training framework. In the first stage, we train a high-quality codebook, using a multi-head octonary codebook (MOC) to compress the index range. In addition, a residual vector quantization (RVQ) mechanism is also integrated for effective multilevel communication. In the second stage, a noise reduction block (NRB) based on Swin Transformer is introduced, coupled with the multilevel codebook from the first stage, serving as a high-quality semantic knowledge base (SKB) for generative feature restoration. Finally, to simulate modern image transmission scenarios, we employ a diverse collection of high-resolution 2K images as the test set. The experimental results consistently demonstrate the superior performance of MOC-RVQ over conventional methods such as BPG or JPEG. Additionally, MOC-RVQ achieves comparable performance to an analog JSCC scheme, while needing only one-sixth of the channel bandwidth ratio (CBR) and being directly compatible with digital transmission systems.
Authors: Qingyuan Yang, Guanzhou Chen, Xiaoliang Tan, Tong Wang, Jiaqi Wang, Xiaodong Zhang
Abstract: Stereo matching and semantic segmentation are significant tasks in binocular satellite 3D reconstruction. However, previous studies primarily view these as independent parallel tasks, lacking an integrated multitask learning framework. This work introduces a solution, the Single-branch Semantic Stereo Network (S3Net), which innovatively combines semantic segmentation and stereo matching using Self-Fuse and Mutual-Fuse modules. Unlike preceding methods that utilize semantic or disparity information independently, our method dentifies and leverages the intrinsic link between these two tasks, leading to a more accurate understanding of semantic information and disparity estimation. Comparative testing on the US3D dataset proves the effectiveness of our S3Net. Our model improves the mIoU in semantic segmentation from 61.38 to 67.39, and reduces the D1-Error and average endpoint error (EPE) in disparity estimation from 10.051 to 9.579 and 1.439 to 1.403 respectively, surpassing existing competitive methods. Our codes are available at:https://github.com/CVEO/S3Net.
Authors: Mei Wang, Weihong Deng, Jiani Hu, Sen Su
Abstract: Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair behavior and arising controversy in the modern pluralistic and egalitarian society. In this paper, we propose a novel marginal debiased network (MDN) to learn debiased representations. More specifically, a marginal softmax loss (MSL) is designed by introducing the idea of margin penalty into the fairness problem, which assigns a larger margin for bias-conflicting samples (data without spurious correlations) than for bias-aligned ones, so as to deemphasize the spurious correlations and improve generalization on unbiased test criteria. To determine the margins, our MDN is optimized through a meta learning framework. We propose a meta equalized loss (MEL) to perceive the model fairness, and adaptively update the margin parameters by meta-optimization which requires the trained model guided by the optimal margins should minimize MEL computed on an unbiased meta-validation set. Extensive experiments on BiasedMNIST, Corrupted CIFAR-10, CelebA and UTK-Face datasets demonstrate that our MDN can achieve a remarkable performance on under-represented samples and obtain superior debiased results against the previous approaches.
Authors: Yufei Guo, Yuanpei Chen, Zecheng Hao, Weihang Peng, Zhou Jie, Yuhan Zhang, Xiaode Liu, Zhe Ma
Abstract: The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to transmit information, thereby replacing multiplications with additions and resulting in high energy efficiency. However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process. Although prior works have employed various surrogate gradient training methods that use an alternative function to replace the firing process during back-propagation, these approaches ignore an intrinsic problem: gradient vanishing. To address this issue, we propose a shortcut back-propagation method in our paper, which advocates for transmitting the gradient directly from the loss to the shallow layers. This enables us to present the gradient to the shallow layers directly, thereby significantly mitigating the gradient vanishing problem. Additionally, this method does not introduce any burden during the inference phase. To strike a balance between final accuracy and ease of training, we also propose an evolutionary training framework and implement it by inducing a balance coefficient that dynamically changes with the training epoch, which further improves the network's performance. Extensive experiments conducted over static and dynamic datasets using several popular network structures reveal that our method consistently outperforms state-of-the-art methods.
Authors: Chen Wu, Zhuoran Zheng, Yuning Cui, Wenqi Ren
Abstract: Recent advancements in image restoration methods employing global modeling have shown promising results. However, these approaches often incur substantial memory requirements, particularly when processing ultra-high-definition (UHD) images. In this paper, we propose a novel image restoration method called MixNet, which introduces an alternative approach to global modeling approaches and is more effective for UHD image restoration. To capture the longrange dependency of features without introducing excessive computational complexity, we present the Global Feature Modulation Layer (GFML). GFML associates features from different views by permuting the feature maps, enabling efficient modeling of long-range dependency. In addition, we also design the Local Feature Modulation Layer (LFML) and Feed-forward Layer (FFL) to capture local features and transform features into a compact representation. This way, our MixNetachieves effective restoration with low inference time overhead and computational complexity. We conduct extensive experiments on four UHD image restoration tasks, including low-light image enhancement, underwater image enhancement, image deblurring and image demoireing, and the comprehensive results demonstrate that our proposed method surpasses the performance of current state-of-the-art methods. The code will be available at \url{https://github.com/5chen/MixNet}.
Authors: Mingyuan Zhou, Rakib Hyder, Ziwei Xuan, Guojun Qi
Abstract: Recent advances in 3D avatar generation have gained significant attentions. These breakthroughs aim to produce more realistic animatable avatars, narrowing the gap between virtual and real-world experiences. Most of existing works employ Score Distillation Sampling (SDS) loss, combined with a differentiable renderer and text condition, to guide a diffusion model in generating 3D avatars. However, SDS often generates oversmoothed results with few facial details, thereby lacking the diversity compared with ancestral sampling. On the other hand, other works generate 3D avatar from a single image, where the challenges of unwanted lighting effects, perspective views, and inferior image quality make them difficult to reliably reconstruct the 3D face meshes with the aligned complete textures. In this paper, we propose a novel 3D avatar generation approach termed UltrAvatar with enhanced fidelity of geometry, and superior quality of physically based rendering (PBR) textures without unwanted lighting. To this end, the proposed approach presents a diffuse color extraction model and an authenticity guided texture diffusion model. The former removes the unwanted lighting effects to reveal true diffuse colors so that the generated avatars can be rendered under various lighting conditions. The latter follows two gradient-based guidances for generating PBR textures to render diverse face-identity features and details better aligning with 3D mesh geometry. We demonstrate the effectiveness and robustness of the proposed method, outperforming the state-of-the-art methods by a large margin in the experiments.
Authors: Behnood Rasti (HZDR), Alexandre Zouaoui (Thoth), Julien Mairal (Thoth), Jocelyn Chanussot (Thoth)
Abstract: In this paper, we introduce a novel linear model tailored for semisupervised/library-based unmixing. Our model incorporates considerations for library mismatch while enabling the enforcement of the abundance sum-to-one constraint (ASC). Unlike conventional sparse unmixing methods, this model involves nonconvex optimization, presenting significant computational challenges. We demonstrate the efficacy of Alternating Methods of Multipliers (ADMM) in cyclically solving these intricate problems. We propose two semisupervised unmixing approaches, each relying on distinct priors applied to the new model in addition to the ASC: sparsity prior and convexity constraint. Our experimental results validate that enforcing the convexity constraint outperforms the sparsity prior for the endmember library. These results are corroborated across three simulated datasets (accounting for spectral variability and varying pixel purity levels) and the Cuprite dataset. Additionally, our comparison with conventional sparse unmixing methods showcases considerable advantages of our proposed model, which entails nonconvex optimization. Notably, our implementations of the proposed algorithms-fast semisupervised unmixing (FaSUn) and sparse unmixing using soft-shrinkage (SUnS)-prove considerably more efficient than traditional sparse unmixing methods. SUnS and FaSUn were implemented using PyTorch and provided in a dedicated Python package called Fast Semisupervised Unmixing (FUnmix), which is open-source and available at https://github.com/BehnoodRasti/FUnmix
Authors: Tim Br\"odermann, David Bruggemann, Christos Sakaridis, Kevin Ta, Odysseas Liagouris, Jason Corkill, Luc Van Gool
Abstract: Achieving level-5 driving automation in autonomous vehicles necessitates a robust semantic visual perception system capable of parsing data from different sensors across diverse conditions. However, existing semantic perception datasets often lack important non-camera modalities typically used in autonomous vehicles, or they do not exploit such modalities to aid and improve semantic annotations in challenging conditions. To address this, we introduce MUSES, the MUlti-SEnsor Semantic perception dataset for driving in adverse conditions under increased uncertainty. MUSES includes synchronized multimodal recordings with 2D panoptic annotations for 2500 images captured under diverse weather and illumination. The dataset integrates a frame camera, a lidar, a radar, an event camera, and an IMU/GNSS sensor. Our new two-stage panoptic annotation protocol captures both class-level and instance-level uncertainty in the ground truth and enables the novel task of uncertainty-aware panoptic segmentation we introduce, along with standard semantic and panoptic segmentation. MUSES proves both effective for training and challenging for evaluating models under diverse visual conditions, and it opens new avenues for research in multimodal and uncertainty-aware dense semantic perception. Our dataset and benchmark are publicly available at https://muses.vision.ee.ethz.ch.
Authors: Yongwei Nie, Hao Huang, Chengjiang Long, Qing Zhang, Pradipta Maji, Hongmin Cai
Abstract: Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper, we study Unsupervised VAD (UVAD) that does not depend on any label by combining OCC and WS into a unified training framework. Specifically, we extend OCC to weighted OCC (wOCC) and propose a wOCC-WS interleaving training module, where the two models automatically generate pseudo-labels for each other. We face two challenges to make the combination effective: (1) Models' performance fluctuates occasionally during the training process due to the inevitable randomness of the pseudo labels. (2) Thresholds are needed to divide pseudo labels, making the training depend on the accuracy of user intervention. For the first problem, we propose to use wOCC requiring soft labels instead of OCC trained with hard zero/one labels, as soft labels exhibit high consistency throughout different training cycles while hard labels are prone to sudden changes. For the second problem, we repeat the interleaving training module multiple times, during which we propose an adaptive thresholding strategy that can progressively refine a rough threshold to a relatively optimal threshold, which reduces the influence of user interaction. A benefit of employing OCC and WS methods to compose a UVAD method is that we can incorporate the most recent OCC or WS model into our framework. Experiments demonstrate the effectiveness of the proposed UVAD framework.
Authors: Xinyue Xu, Yi Qin, Lu Mi, Hao Wang, Xiaomeng Li
Abstract: Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work by predicting concepts given the input and then predicting the final class label given the predicted concepts. However, (1) they often fail to capture the high-order, nonlinear interaction between concepts, e.g., correcting a predicted concept (e.g., "yellow breast") does not help correct highly correlated concepts (e.g., "yellow belly"), leading to suboptimal final accuracy; (2) they cannot naturally quantify the complex conditional dependencies between different concepts and class labels (e.g., for an image with the class label "Kentucky Warbler" and a concept "black bill", what is the probability that the model correctly predicts another concept "black crown"), therefore failing to provide deeper insight into how a black-box model works. In response to these limitations, we propose Energy-based Concept Bottleneck Models (ECBMs). Our ECBMs use a set of neural networks to define the joint energy of candidate (input, concept, class) tuples. With such a unified interface, prediction, concept correction, and conditional dependency quantification are then represented as conditional probabilities, which are generated by composing different energy functions. Our ECBMs address both limitations of existing CBMs, providing higher accuracy and richer concept interpretations. Empirical results show that our approach outperforms the state-of-the-art on real-world datasets.
Authors: Lixing Xiao, Ruixiao Shi, Xiaoyang Tang, Yi Zhou
Abstract: Previous works on object detection have achieved high accuracy in closed-set scenarios, but their performance in open-world scenarios is not satisfactory. One of the challenging open-world problems is corner case detection in autonomous driving. Existing detectors struggle with these cases, relying heavily on visual appearance and exhibiting poor generalization ability. In this paper, we propose a solution by reducing the discrepancy between known and unknown classes and introduce a multimodal-enhanced objectness notion learner. Leveraging both vision-centric and image-text modalities, our semi-supervised learning framework imparts objectness knowledge to the student model, enabling class-aware detection. Our approach, Multimodal-Enhanced Objectness Learner (MENOL) for Corner Case Detection, significantly improves recall for novel classes with lower training costs. By achieving a 76.6% mAR-corner and 79.8% mAR-agnostic on the CODA-val dataset with just 5100 labeled training images, MENOL outperforms the baseline ORE by 71.3% and 60.6%, respectively. The code will be available at https://github.com/tryhiseyyysum/MENOL.
Authors: Kei Iino, Shunsuke Akamatsu, Hiroshi Watanabe, Shohei Enomoto, Akira Sakamoto, Takeharu Eda
Abstract: Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is important for the encoder to recognize and compress the information necessary for the machine recognition task. There are two main approaches in learned ICM; optimization of the compression model based on task loss, and Region of Interest (ROI) based bit allocation. These approaches provide the encoder with the recognition capability. However, optimization with task loss becomes difficult when the recognition model is deep, and ROI-based methods often involve extra overhead during evaluation. In this study, we propose a novel training method for learned ICM models that applies auxiliary loss to the encoder to improve its recognition capability and rate-distortion performance. Our method achieves Bjontegaard Delta rate improvements of 27.7% and 20.3% in object detection and semantic segmentation tasks, compared to the conventional training method. \c{opyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Authors: Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Enkaer Xieerke, Jen-Shiun Chiang
Abstract: Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first and prepare for it based on the analysis of the radiologist. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection as computer-assisted diagnosis (CAD). In 2023, Ultralytics presented the latest version of the YOLO models, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the hottest methods to improve the model performance. This research work proposes YOLOv8-AM, which incorporates the attention mechanism into the original YOLOv8 architecture. Specifically, we respectively employ four attention modules, Convolutional Block Attention Module (CBAM), Global Attention Mechanism (GAM), Efficient Channel Attention (ECA), and Shuffle Attention (SA), to design the improved models and train them on GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP 50) of the YOLOv8-AM model based on ResBlock + CBAM (ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. Conversely, YOLOv8-AM model incorporating GAM obtains the mAP 50 value of 64.2%, which is not a satisfactory enhancement. Therefore, we combine ResBlock and GAM, introducing ResGAM to design another new YOLOv8-AM model, whose mAP 50 value is increased to 65.0%. The implementation code for this study is available on GitHub at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
URLs: https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
Authors: James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Jiankang Deng, Ioannis Patras
Abstract: The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. In this paper, we propose the Multilinear Mixture of Experts ($\mu$MoE) layer to address this, focusing on vision models. $\mu$MoE layers enable scalable expert specialization by performing an implicit computation on prohibitively large weight tensors entirely in factorized form. Consequently, $\mu$MoEs (1) avoid the restrictively high inference-time costs of dense MoEs, yet (2) do not inherit the training issues of the popular sparse MoEs' discrete (non-differentiable) expert routing. We present both qualitative and quantitative evidence that scaling $\mu$MoE layers when fine-tuning foundation models for vision tasks leads to more specialized experts at the class-level, further enabling manual bias correction in CelebA attribute classification. Finally, we show qualitative results demonstrating the expert specialism achieved when pre-training large GPT2 and MLP-Mixer models with parameter-matched $\mu$MoE blocks at every layer, maintaining comparable accuracy. Our code is available at: https://github.com/james-oldfield/muMoE.
Authors: Seungwon Seo, Suho Lee, Sangheum Hwang
Abstract: Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"{\i}ve fine-tuning may not fully leverage knowledge embedded in pretrained models. In this study, we introduce a novel fine-tuning method, called stochastic cross-attention (StochCA), specific to Transformer architectures. This method modifies the Transformer's self-attention mechanism to selectively utilize knowledge from pretrained models during fine-tuning. Specifically, in each block, instead of self-attention, cross-attention is performed stochastically according to the predefined probability, where keys and values are extracted from the corresponding block of a pretrained model. By doing so, queries and channel-mixing multi-layer perceptron layers of a target model are fine-tuned to target tasks to learn how to effectively exploit rich representations of pretrained models. To verify the effectiveness of StochCA, extensive experiments are conducted on benchmarks in the areas of transfer learning and domain generalization, where the exploitation of pretrained models is critical. Our experimental results show the superiority of StochCA over state-of-the-art approaches in both areas. Furthermore, we demonstrate that StochCA is complementary to existing approaches, i.e., it can be combined with them to further improve performance. Our code is available at https://github.com/daintlab/stochastic_cross_attention
URLs: https://github.com/daintlab/stochastic_cross_attention
Authors: Wen-Jia Tang, Xiao Liu, Peng Gao, Fei Wang, Ru-Yue Yuan
Abstract: Manually-designed network architectures for thermal infrared pedestrian tracking (TIR-PT) require substantial effort from human experts. AlexNet and ResNet are widely used as backbone networks in TIR-PT applications. However, these architectures were originally designed for image classification and object detection tasks, which are less complex than the challenges presented by TIR-PT. This paper makes an early attempt to search an optimal network architecture for TIR-PT automatically, employing single-bottom and dual-bottom cells as basic search units and incorporating eight operation candidates within the search space. To expedite the search process, a random channel selection strategy is employed prior to assessing operation candidates. Classification, batch hard triplet, and center loss are jointly used to retrain the searched architecture. The outcome is a high-performance network architecture that is both parameter- and computation-efficient. Extensive experiments proved the effectiveness of the automated method.
Authors: Karen Efremyan, Elizaveta Petrova, Evgeny Kaskov, Alexander Kapitanov
Abstract: A common problem for composite images is the incompatibility of their foreground and background components. Image harmonization aims to solve this problem, making the whole image look more authentic and coherent. Most existing solutions predict lookup tables (LUTs) or reconstruct images, utilizing various attributes of composite images. Recent approaches have primarily focused on employing global transformations like normalization and color curve rendering to achieve visual consistency, and they often overlook the importance of local visual coherence. We present a patch-based harmonization network consisting of novel Patch-based normalization (PN) blocks and a feature extractor based on statistical color transfer. Extensive experiments demonstrate the network's high generalization capability for different domains. Our network achieves state-of-the-art results on the iHarmony4 dataset. Also, we created a new human portrait harmonization dataset based on FFHQ and checked the proposed method to show the generalization ability by achieving the best metrics on it. The benchmark experiments confirm that the suggested patch-based normalization block and feature extractor effectively improve the network's capability to harmonize portraits. Our code and model baselines are publicly available.
Authors: Jinfeng Wang, Sifan Song, Xinkun Wang, Yiyi Wang, Yiyi Miao, Jionglong Su, S. Kevin Zhou
Abstract: With the proposal of the Segment Anything Model (SAM), fine-tuning SAM for medical image segmentation (MIS) has become popular. However, due to the large size of the SAM model and the significant domain gap between natural and medical images, fine-tuning-based strategies are costly with potential risk of instability, feature damage and catastrophic forgetting. Furthermore, some methods of transferring SAM to a domain-specific MIS through fine-tuning strategies disable the model's prompting capability, severely limiting its utilization scenarios. In this paper, we propose an Auto-Prompting Module (APM), which provides SAM-based foundation model with Euclidean adaptive prompts in the target domain. Our experiments demonstrate that such adaptive prompts significantly improve SAM's non-fine-tuned performance in MIS. In addition, we propose a novel non-invasive method called Incremental Pattern Shifting (IPS) to adapt SAM to specific medical domains. Experimental results show that the IPS enables SAM to achieve state-of-the-art or competitive performance in MIS without the need for fine-tuning. By coupling these two methods, we propose ProMISe, an end-to-end non-fine-tuned framework for Promptable Medical Image Segmentation. Our experiments demonstrate that both using our methods individually or in combination achieves satisfactory performance in low-cost pattern shifting, with all of SAM's parameters frozen.
Authors: Wenhao Wang, Yi Yang
Abstract: The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 Million unique text-to-Video Prompts from real users. Additionally, this dataset includes 6.69 million videos generated by four state-of-the-art diffusion models, alongside some related data. We initially discuss the curation of this large-scale dataset, a process that is both time-consuming and costly. Subsequently, we underscore the need for a new prompt dataset specifically designed for text-to-video generation by illustrating how VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Our extensive and diverse dataset also opens up many exciting new research areas. For instance, we suggest exploring text-to-video prompt engineering, efficient video generation, and video copy detection for diffusion models to develop better, more efficient, and safer models. The project (including the collected dataset VidProM and related code) is publicly available at https://vidprom.github.io under the CC-BY-NC 4.0 License.
Authors: Yuxuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang
Abstract: Synthetic Aperture Radar (SAR) object detection has gained significant attention recently due to its irreplaceable all-weather imaging capabilities. However, this research field suffers from both limited public datasets (mostly comprising <2K images with only mono-category objects) and inaccessible source code. To tackle these challenges, we establish a new benchmark dataset and an open-source method for large-scale SAR object detection. Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets, providing a large-scale and diverse dataset for research purposes. To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created. With this high-quality dataset, we conducted comprehensive experiments and uncovered a crucial challenge in SAR object detection: the substantial disparities between the pretraining on RGB datasets and finetuning on SAR datasets in terms of both data domain and model structure. To bridge these gaps, we propose a novel Multi-Stage with Filter Augmentation (MSFA) pretraining framework that tackles the problems from the perspective of data input, domain transition, and model migration. The proposed MSFA method significantly enhances the performance of SAR object detection models while demonstrating exceptional generalizability and flexibility across diverse models. This work aims to pave the way for further advancements in SAR object detection. The dataset and code is available at https://github.com/zcablii/SARDet_100K.
Authors: Qiyuan Wang, Yanzhe Liu, Shang Zhao, Rong Liu, S. Kevin Zhou
Abstract: For robotic surgical videos, instrument presence annotations are typically recorded with video streams, which offering the potential to reduce the manually annotated costs for segmentation. However, weakly supervised surgical instrument segmentation with only instrument presence labels has been rarely explored in surgical domain due to the highly under-constrained challenges. Temporal properties can enhance representation learning by capturing sequential dependencies and patterns over time even in incomplete supervision situations. From this, we take the inherent temporal attributes of surgical video into account and extend a two-stage weakly supervised segmentation paradigm from different perspectives. Firstly, we make temporal equivariance constraint to enhance pixel-wise temporal consistency between adjacent features. Secondly, we constrain class-aware semantic continuity between global and local regions across temporal dimension. Finally, we generate temporal-enhanced pseudo masks from consecutive frames to suppress irrelevant regions. Extensive experiments are validated on two surgical video datasets, including one cholecystectomy surgery benchmark and one real robotic left lateral segment liver surgery dataset. We annotate instance-wise instrument labels with fixed time-steps which are double checked by a clinician with 3-years experience to evaluate segmentation results. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.
Authors: Jiangshan Wang, Yifan Pu, Yizeng Han, Jiayi Guo, Yiru Wang, Xiu Li, Gao Huang
Abstract: Oriented object detection, an emerging task in recent years, aims to identify and locate objects across varied orientations. This requires the detector to accurately capture the orientation information, which varies significantly within and across images. Despite the existing substantial efforts, simultaneously ensuring model effectiveness and parameter efficiency remains challenging in this scenario. In this paper, we propose a lightweight yet effective Group-wise Rotating and Attention (GRA) module to replace the convolution operations in backbone networks for oriented object detection. GRA can adaptively capture fine-grained features of objects with diverse orientations, comprising two key components: Group-wise Rotating and Group-wise Attention. Group-wise Rotating first divides the convolution kernel into groups, where each group extracts different object features by rotating at a specific angle according to the object orientation. Subsequently, Group-wise Attention is employed to adaptively enhance the object-related regions in the feature. The collaborative effort of these components enables GRA to effectively capture the various orientation information while maintaining parameter efficiency. Extensive experimental results demonstrate the superiority of our method. For example, GRA achieves a new state-of-the-art (SOTA) on the DOTA-v2.0 benchmark, while saving the parameters by nearly 50% compared to the previous SOTA method. Code will be released.
Authors: Yuxuan Li, Xiang Li, Yimian Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang
Abstract: Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios. Such prior knowledge can be useful because remote sensing objects may be mistakenly recognized without referencing a sufficiently long-range context, which can vary for different objects. This paper considers these priors and proposes a lightweight Large Selective Kernel Network (LSKNet) backbone. LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To our knowledge, large and selective kernel mechanisms have not been previously explored in remote sensing images. Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks. Our comprehensive analysis further validated the significance of the identified priors and the effectiveness of LSKNet. The code is available at https://github.com/zcablii/LSKNet.
Authors: Kasi Viswanath, Peng Jiang, Srikanth Saripalli
Abstract: LiDAR semantic segmentation frameworks predominantly use geometry-based features to differentiate objects within a scan. Although these methods excel in scenarios with clear boundaries and distinct shapes, their performance declines in environments where boundaries are indistinct, particularly in off-road contexts. To address this issue, recent advances in 3D segmentation algorithms have aimed to leverage raw LiDAR intensity readings to improve prediction precision. However, despite these advances, existing learning-based models face challenges in linking the complex interactions between raw intensity and variables such as distance, incidence angle, material reflectivity, and atmospheric conditions. Building upon our previous work, this paper explores the advantages of employing calibrated intensity (also referred to as reflectivity) within learning-based LiDAR semantic segmentation frameworks. We start by demonstrating that adding reflectivity as input enhances the LiDAR semantic segmentation model by providing a better data representation. Extensive experimentation with the Rellis-3d off-road dataset shows that replacing intensity with reflectivity results in a 4\% improvement in mean Intersection over Union (mIoU) for off-road scenarios. We demonstrate the potential benefits of using calibrated intensity for semantic segmentation in urban environments (SemanticKITTI) and for cross-sensor domain adaptation. Additionally, we tested the Segment Anything Model (SAM) using reflectivity as input, resulting in improved segmentation masks for LiDAR images.
Authors: Chen Yang, Yangfan He, Aaron Xuxiang Tian, Dong Chen, Tianyu Shi, Arsalan Heydarian
Abstract: In this paper, we introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models (a.k.a., diffusion models) and transformers. Our proposed framework, termed the "World-Centric Diffusion Transformer"(WcDT), optimizes the entire trajectory generation process, from feature extraction to model inference. To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed into "Agent Move Statement" and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks. Then, the latent features, historical trajectories, HD map features, and historical traffic signal information are fused with various transformer-based encoders that are used to enhance the interaction of agents with other elements in the traffic scene. The encoded traffic scenes are then decoded by a trajectory decoder to generate multimodal future trajectories. Comprehensive experimental results show that the proposed approach exhibits superior performance in generating both realistic and diverse trajectories, showing its potential for integration into automatic driving simulation systems. Our code is available at \url{https://github.com/yangchen1997/WcDT}.
Authors: Danfeng Qin, Chas Leichner, Manolis Delakis, Marco Fornoni, Shixin Luo, Fan Yang, Weijun Wang, Colby Banbury, Chengxi Ye, Berkin Akin, Vaibhav Aggarwal, Tenghui Zhu, Daniele Moro, Andrew Howard
Abstract: We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the Universal Inverted Bottleneck (UIB) search block, a unified and flexible structure that merges Inverted Bottleneck (IB), ConvNext, Feed Forward Network (FFN), and a novel Extra Depthwise (ExtraDW) variant. Alongside UIB, we present Mobile MQA, an attention block tailored for mobile accelerators, delivering a significant 39% speedup. An optimized neural architecture search (NAS) recipe is also introduced which improves MNv4 search effectiveness. The integration of UIB, Mobile MQA and the refined NAS recipe results in a new suite of MNv4 models that are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU - a characteristic not found in any other models tested. Finally, to further boost accuracy, we introduce a novel distillation technique. Enhanced by this technique, our MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms.
Authors: Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang
Abstract: This paper explores in-context learning for image copy detection (ICD), i.e., prompting an ICD model to identify replicated images with new tampering patterns without the need for additional training. The prompts (or the contexts) are from a small set of image-replica pairs that reflect the new patterns and are used at inference time. Such in-context ICD has good realistic value, because it requires no fine-tuning and thus facilitates fast reaction against the emergence of unseen patterns. To accommodate the "seen $\rightarrow$ unseen" generalization scenario, we construct the first large-scale pattern dataset named AnyPattern, which has the largest number of tamper patterns ($90$ for training and $10$ for testing) among all the existing ones. We benchmark AnyPattern with popular ICD methods and reveal that existing methods barely generalize to novel patterns. We further propose a simple in-context ICD method named ImageStacker. ImageStacker learns to select the most representative image-replica pairs and employs them as the pattern prompts in a stacking manner (rather than the popular concatenation manner). Experimental results show (1) training with our large-scale dataset substantially benefits pattern generalization ($+26.66 \%$ $\mu AP$), (2) the proposed ImageStacker facilitates effective in-context ICD (another round of $+16.75 \%$ $\mu AP$), and (3) AnyPattern enables in-context ICD, i.e., without such a large-scale dataset, in-context learning does not emerge even with our ImageStacker. Beyond the ICD task, we also demonstrate how AnyPattern can benefit artists, i.e., the pattern retrieval method trained on AnyPattern can be generalized to identify style mimicry by text-to-image models. The project is publicly available at https://anypattern.github.io.
Authors: Achyut Paudel, Jostan Brown, Priyanka Upadhyaya, Atif Bilal Asad, Safal Kshetri, Joseph R. Davidson, Cindy Grimm, Ashley Thompson, Bernardita Sallato, Matthew D. Whiting, Manoj Karkee
Abstract: Apple trees, being deciduous, shed leaves each year. This process is preceded by the change in leaf color from green to yellow (also known as senescence) during the fall season. The rate and timing of color change are affected by factors including nitrogen (N) concentration in leaves. The green color of leaves and the speed at which it turns yellow during senescence are highly dependent on chlorophyll content, which in turn depends on nitrogen concentration in the leaves. The assessment of leaf color during this period can therefore provide important information on the nitrogen status of apple trees. This study focused on a machine vision-based system to quantify the timing and change in leaf color during the fall and correlate that information to leaf nitrogen content. The color and 3D image dataset used in this study was collected over five weeks in the fall of 2021 and 2023 at a commercial orchard (tall spindle architecture) using a ground-vehicle-based stereo vision sensor. First, the point cloud obtained from the sensor was used to segment the tree canopies using color and depth thresholding methods in the natural orchard environment. Then, the color information of the segmented canopy area was quantified using a custom-defined metric, \textit{yellowness index} (a normalized ratio of yellow to green foliage in the tree) that varied from $-1$ to $+1$ ($-1$ being completely green and $+1$ being completely yellow), which gives the proportion of yellow leaves on a tree. A K-means-based method and a gradient boosting method were used to estimate the \textit{yellowness index}. The gradient boosting method proposed in this study was found to be superior to the K-means-based method, achieving an $R^2$ of 0.72 in estimating the \textit{yellowness index}. The results showed that the metric was able to capture the gradual color transition from green to yellow over the study period.
Authors: Ye Mao, Junpeng Jing, Krystian Mikolajczyk
Abstract: Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for this alignment often lack realism and texture variation, compromising alignment robustness. Moreover, the volume discrepancy between 3D and 2D pretraining datasets highlights the need for effective strategies to transfer the representational abilities of VLMs to 3D learning. In this paper, we present OpenDlign, a novel open-world 3D model using depth-aligned images generated from a diffusion model for robust multimodal alignment. These images exhibit greater texture diversity than CAD renderings due to the stochastic nature of the diffusion model. By refining the depth map projection pipeline and designing depth-specific prompts, OpenDlign leverages rich knowledge in pre-trained VLM for 3D representation learning with streamlined fine-tuning. Our experiments show that OpenDlign achieves high zero-shot and few-shot performance on diverse 3D tasks, despite only fine-tuning 6 million parameters on a limited ShapeNet dataset. In zero-shot classification, OpenDlign surpasses previous models by 8.0% on ModelNet40 and 16.4% on OmniObject3D. Additionally, using depth-aligned images for multimodal alignment consistently enhances the performance of other state-of-the-art models.
Authors: Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
Abstract: Generating face image with specific gaze information has attracted considerable attention. Existing approaches typically input gaze values directly for face generation, which is unnatural and requires annotated gaze datasets for training, thereby limiting its application. In this paper, we present a novel gaze-controllable face generation task. Our approach inputs textual descriptions that describe human gaze and head behavior and generates corresponding face images. Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses. We further propose a gaze-controllable text-to-face method. Our method contains a sketch-conditioned face diffusion module and a model-based sketch diffusion module. We define a face sketch based on facial landmarks and eye segmentation map. The face diffusion module generates face images from the face sketch, and the sketch diffusion module employs a 3D face model to generate face sketch from text description. Experiments on the FFHQ dataset show the effectiveness of our method. We will release our dataset and code for future research.
Authors: Delong Chen, Samuel Cahyawijaya, Etsuko Ishii, Ho Shu Chan, Yejin Bang, Pascale Fung
Abstract: This paper establishes a formal information-theoretic framework for image captioning, conceptualizing captions as compressed linguistic representations that selectively encode semantic units in images. Our framework posits that good image captions should balance three key aspects: informationally sufficient, minimally redundant, and readily comprehensible by humans. By formulating these aspects as quantitative measures with adjustable weights, our framework provides a flexible foundation for analyzing and optimizing image captioning systems across diverse task requirements. To demonstrate its applicability, we introduce the Pyramid of Captions (PoCa) method, which generates enriched captions by integrating local and global visual information. We present both theoretical proof that PoCa improves caption quality under certain assumptions, and empirical validation of its effectiveness across various image captioning models and datasets.
Authors: Huihong Shi, Haikuo Shao, Wendong Mao, Zhongfeng Wang
Abstract: Motivated by the huge success of Transformers in the field of natural language processing (NLP), Vision Transformers (ViTs) have been rapidly developed and achieved remarkable performance in various computer vision tasks. However, their huge model sizes and intensive computations hinder ViTs' deployment on embedded devices, calling for effective model compression methods, such as quantization. Unfortunately, due to the existence of hardware-unfriendly and quantization-sensitive non-linear operations, particularly {Softmax}, it is non-trivial to completely quantize all operations in ViTs, yielding either significant accuracy drops or non-negligible hardware costs. In response to challenges associated with \textit{standard ViTs}, we focus our attention towards the quantization and acceleration for \textit{efficient ViTs}, which not only eliminate the troublesome Softmax but also integrate linear attention with low computational complexity, and propose Trio-ViT accordingly. Specifically, at the algorithm level, we develop a {tailored post-training quantization engine} taking the unique activation distributions of Softmax-free efficient ViTs into full consideration, aiming to boost quantization accuracy. Furthermore, at the hardware level, we build an accelerator dedicated to the specific Convolution-Transformer hybrid architecture of efficient ViTs, thereby enhancing hardware efficiency. Extensive experimental results consistently prove the effectiveness of our Trio-ViT framework. {Particularly, we can gain up to $\uparrow$$\mathbf{3.6}\times$, $\uparrow$$\mathbf{5.0}\times$, and $\uparrow$$\mathbf{7.3}\times$ FPS under comparable accuracy over state-of-the-art ViT accelerators, as well as $\uparrow$$\mathbf{6.0}\times$, $\uparrow$$\mathbf{1.5}\times$, and $\uparrow$$\mathbf{2.1}\times$ DSP efficiency.} Codes are available at \url{https://github.com/shihuihong214/Trio-ViT}.
Authors: Fengjie Wang, Chengming Liu, Lei Shi, Pang Haibo
Abstract: Previous unsupervised anomaly detection (UAD) methods often struggle to handle the extensive diversity in training sets, particularly when they contain stylistically diverse and feature-rich samples, which we categorize as feature-rich anomaly detection datasets (FRADs). This challenge is evident in applications such as multi-view and multi-class scenarios. To address this challenge, we developed MiniMaxAD, a lightweight autoencoder designed to efficiently compress and memorize extensive information from normal images. Our model employs a technique that enhances feature diversity, thereby increasing the effective capacity of the network. It also utilizes large kernel convolution to extract highly abstract patterns, which contribute to efficient and compact feature embedding. Moreover, we introduce an Adaptive Contraction Hard Mining Loss (ADCLoss), specifically tailored to FRADs. In our methodology, any dataset can be unified under the framework of feature-rich anomaly detection, in a way that the benefits far outweigh the drawbacks. Our approach has achieved state-of-the-art performance in multiple challenging benchmarks.
Authors: Bing Cao, Haiyu Yao, Pengfei Zhu, Qinghua Hu
Abstract: Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features of tiny objects. Existing methods usually perform generation-based feature enhancement, which is seriously affected by spurious textures and artifacts, making it difficult to make the tiny-object-specific features visible and clear for detection. To address this issue, we propose a self-reconstructed tiny object detection (SR-TOD) framework. We for the first time introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. This inspires us to enhance the weak representations of tiny objects under the guidance of the difference maps. Thus, improving the visibility of tiny objects for the detectors. Building on this, we further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear. In addition, we further propose a new multi-instance anti-UAV dataset, which is called DroneSwarms dataset and contains a large number of tiny drones with the smallest average size to date. Extensive experiments on the DroneSwarms dataset and other datasets demonstrate the effectiveness of the proposed method. The code and dataset will be publicly available.
Authors: Victoria Manousaki, Konstantinos Bacharidis, Filippos Gouidis, Konstantinos Papoutsakis, Dimitris Plexousakis, Antonis Argyros
Abstract: In this work, we introduce (a) the new problem of anticipating object state changes in images and videos during procedural activities, (b) new curated annotation data for object state change classification based on the Ego4D dataset, and (c) the first method for addressing this challenging problem. Solutions to this new task have important implications in vision-based scene understanding, automated monitoring systems, and action planning. The proposed novel framework predicts object state changes that will occur in the near future due to yet unseen human actions by integrating learned visual features that represent recent visual information with natural language (NLP) features that represent past object state changes and actions. Leveraging the extensive and challenging Ego4D dataset which provides a large-scale collection of first-person perspective videos across numerous interaction scenarios, we introduce an extension noted Ego4D-OSCA that provides new curated annotation data for the object state change anticipation task (OSCA). An extensive experimental evaluation is presented demonstrating the proposed method's efficacy in predicting object state changes in dynamic scenarios. The performance of the proposed approach also underscores the potential of integrating video and linguistic cues to enhance the predictive performance of video understanding systems and lays the groundwork for future research on the new task of object state change anticipation. The source code and the new annotation data (Ego4D-OSCA) will be made publicly available.
Authors: Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui
Abstract: The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation, they often face challenges when confronted with out-of-distribution data, such as which can hardly distinguish orientation, quantity, color, structure, etc. This is primarily due to their reliance on image encoders trained to encode images into task-relevant features, which may lead them to disregard irrelevant details. Delving into the modeling capabilities of diffusion models for images naturally prompts the question: Can diffusion models serve as the eyes of large language models for image perception? In this paper, we propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. This addresses the drawbacks of previous methods that solely relied on image encoders like CLIP-ViT, thereby enhancing the model's resilience against out-of-distribution samples and reducing visual hallucinations. Importantly, this is achieved without requiring additional training modules and with fewer training parameters. We extensively evaluated DEEM on both our newly constructed RobustVQA benchmark and other well-known benchmarks, POPE and MMVP, for visual hallucination and perception. In particular, DEEM improves LMM's visual perception performance to a large extent (e.g., 4% higher on RobustVQA, 6.5% higher on MMVP and 12.8 % higher on POPE ). Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data (10%), and a smaller base model size.
Authors: T. Berriel Martins, Javier Civera
Abstract: 3D Gaussian Splatting has emerged as a very promising scene representation, achieving state-of-the-art quality in novel view synthesis significantly faster than competing alternatives. However, its use of spherical harmonics to represent scene colors limits the expressivity of 3D Gaussians and, as a consequence, the capability of the representation to generalize as we move away from the training views. In this paper, we propose to encode the color information of 3D Gaussians into per-Gaussian feature vectors, which we denote as Feature Splatting (FeatSplat). To synthesize a novel view, Gaussians are first "splatted" into the image plane, then the corresponding feature vectors are alpha-blended, and finally the blended vector is decoded by a small MLP to render the RGB pixel values. To further inform the model, we concatenate a camera embedding to the blended feature vector, to condition the decoding also on the viewpoint information. Our experiments show that these novel model for encoding the radiance considerably improves novel view synthesis for low overlap views that are distant from the training views. Finally, we also show the capacity and convenience of our feature vector representation, demonstrating its capability not only to generate RGB values for novel views, but also their per-pixel semantic labels. Code available at https://github.com/tberriel/FeatSplat . Keywords: Gaussian Splatting, Novel View Synthesis, Feature Splatting
Authors: Dvir Samuel, Rami Ben-Ari, Matan Levy, Nir Darshan, Gal Chechik
Abstract: Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data for training. Recently, self-supervised foundation models have been introduced to these tasks showing comparable results to supervised methods. However, a significant flaw in these models is evident: they struggle to locate a desired instance when other instances within the same class are presented. In this paper, we explore text-to-image diffusion models for these tasks. Specifically, we propose a novel approach called PDM for Personalized Features Diffusion Matching, that leverages intermediate features of pre-trained text-to-image models for personalization tasks without any additional training. PDM demonstrates superior performance on popular retrieval and segmentation benchmarks, outperforming even supervised methods. We also highlight notable shortcomings in current instance and segmentation datasets and propose new benchmarks for these tasks.
Authors: Jiangning Zhang, Haoyang He, Zhenye Gan, Qingdong He, Yuxuan Cai, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong Liu
Abstract: Visual anomaly detection aims to identify anomalous regions in images through unsupervised learning paradigms, with increasing application demand and value in fields such as industrial inspection and medical lesion detection. Despite significant progress in recent years, there is a lack of comprehensive benchmarks to adequately evaluate the performance of various mainstream methods across different datasets under the practical multi-class setting. The absence of standardized experimental setups can lead to potential biases in training epochs, resolution, and metric results, resulting in erroneous conclusions. This paper addresses this issue by proposing a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework that is highly extensible for new methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. Additionally, we have proposed the GPU-assisted ADEval package to address the slow evaluation problem of metrics like time-consuming mAU-PRO on large-scale data, significantly reducing evaluation time by more than \textit{1000-fold}. Through extensive experimental results, we objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection. We hope that ADer will become a valuable resource for researchers and practitioners in the field, promoting the development of more robust and generalizable anomaly detection systems. Full codes are open-sourced at https://github.com/zhangzjn/ader.
Authors: Aditya Jain, Fagner Cunha, Michael James Bunsen, Juan Sebasti\'an Ca\~nas, L\'eonard Pasi, Nathan Pinoy, Flemming Helsing, JoAnne Russo, Marc Botham, Michael Sabourin, Jonathan Fr\'echette, Alexandre Anctil, Yacksecari Lopez, Eduardo Navarro, Filonila Perez Pimentel, Ana Cecilia Zamora, Jos\'e Alejandro Ramirez Silva, Jonathan Gagnon, Tom August, Kim Bjerge, Alba Gomez Segura, Marc B\'elisle, Yves Basset, Kent P. McFarland, David Roy, Toke Thomas H{\o}ye, Maxim Larriv\'ee, David Rolnick
Abstract: Insects represent half of all global biodiversity, yet many of the world's insects are disappearing, with severe implications for ecosystems and agriculture. Despite this crisis, data on insect diversity and abundance remain woefully inadequate, due to the scarcity of human experts and the lack of scalable tools for monitoring. Ecologists have started to adopt camera traps to record and study insects, and have proposed computer vision algorithms as an answer for scalable data processing. However, insect monitoring in the wild poses unique challenges that have not yet been addressed within computer vision, including the combination of long-tailed data, extremely similar classes, and significant distribution shifts. We provide the first large-scale machine learning benchmarks for fine-grained insect recognition, designed to match real-world tasks faced by ecologists. Our contributions include a curated dataset of images from citizen science platforms and museums, and an expert-annotated dataset drawn from automated camera traps across multiple continents, designed to test out-of-distribution generalization under field conditions. We train and evaluate a variety of baseline algorithms and introduce a combination of data augmentation techniques that enhance generalization across geographies and hardware setups.
Authors: Gabriel Sarch, Lawrence Jang, Michael J. Tarr, William W. Cohen, Kenneth Marino, Katerina Fragkiadaki
Abstract: Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot in-context learning for decision making and instruction following. However, they require high-quality exemplar demonstrations to be included in their context window. In this work, we ask: Can LLMs and VLMs generate their own prompt examples from generic, sub-optimal demonstrations? We propose In-Context Abstraction Learning (ICAL), a method that builds a memory of multimodal experience insights from sub-optimal demonstrations and human feedback. Given a noisy demonstration in a new domain, VLMs abstract the trajectory into a general program by fixing inefficient actions and annotating cognitive abstractions: task relationships, object state changes, temporal subgoals, and task construals. These abstractions are refined and adapted interactively through human feedback while the agent attempts to execute the trajectory in a similar environment. The resulting abstractions, when used as exemplars in the prompt, significantly improve decision-making in retrieval-augmented LLM and VLM agents. Our ICAL agent surpasses the state-of-the-art in dialogue-based instruction following in TEACh, multimodal web agents in VisualWebArena, and action anticipation in Ego4D. In TEACh, we achieve a 12.6% improvement in goal-condition success. In VisualWebArena, our task success rate improves over the SOTA from 18.9% to 23.4%. In Ego4D action forecasting, we improve over few-shot GPT-4V and remain competitive with supervised models. We show finetuning our retrieval-augmented in-context agent yields additional improvements. Our approach significantly reduces reliance on expert-crafted examples and consistently outperforms in-context learning from action plans that lack such insights.
Authors: Yuhang Ma, Wenting Xu, Jiji Tang, Qinfeng Jin, Rongsheng Zhang, Zeng Zhao, Changjie Fan, Zhipeng Hu
Abstract: Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods. Our code will be released at https://github.com/Character-Adapter/Character-Adapter.
URLs: https://github.com/Character-Adapter/Character-Adapter.
Authors: Meiying Zhang, Weiyuan Peng, Guangyao Ding, Chenyang Lei, Chunlin Ji, Qi Hao
Abstract: Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality (sim-to-real),cross-domain object detection algorithms usually suffer from dramatic performance drops. While numerous unsupervised domain adaptation (UDA) methods have been developed to address cross-domain tasks between real-world datasets, progress in sim-to-real remains limited. This paper presents a novel Complex-to-Simple (CTS) framework to transfer models from labeled simulation (source) to unlabeled reality (target) domains. Based on a two-stage detector, the novelty of this work is threefold: 1) developing fixed-size anchor heads and RoI augmentation to address size bias and feature diversity between two domains, thereby improving the quality of pseudo-label; 2) developing a novel corner-format representation of aleatoric uncertainty (AU) for the bounding box, to uniformly quantify pseudo-label quality; 3) developing a noise-aware mean teacher domain adaptation method based on AU, as well as object-level and frame-level sampling strategies, to migrate the impact of noisy labels. Experimental results demonstrate that our proposed approach significantly enhances the sim-to-real domain adaptation capability of 3D object detection models, outperforming state-of-the-art cross-domain algorithms, which are usually developed for real-to-real UDA tasks.
Authors: Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, Benyou Wang
Abstract: The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an 'unblinded' capacity to denoise and reformat the data, resulting in the creation of the PubMedVision dataset with 1.3 million medical VQA samples. Our validation demonstrates that: (1) PubMedVision can significantly enhance the medical multimodal capabilities of current MLLMs, showing significant improvement in benchmarks including the MMMU Health & Medicine track; (2) manual checks by medical experts and empirical results validate the superior data quality of our dataset compared to other data construction methods. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios among open-source MLLMs.
Authors: Dingkang Yang, Mingcheng Li, Linhao Qu, Kun Yang, Peng Zhai, Song Wang, Lihua Zhang
Abstract: Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach.
Authors: Yuanhong Chen, Chong Wang, Yuyuan Liu, Hu Wang, Gustavo Carneiro
Abstract: Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement can be naturally fulfilled by leveraging transformer-based segmentation architecture due to its inherent ability to capture long-range dependencies and flexibility in handling different modalities. However, the inherent training issues of transformer-based methods, such as the low efficacy of cross-attention and unstable bipartite matching, can be amplified in AVS, particularly when the learned audio query does not provide a clear semantic clue. In this paper, we address these two issues with the new Class-conditional Prompting Machine (CPM). CPM improves the bipartite matching with a learning strategy combining class-agnostic queries with class-conditional queries. The efficacy of cross-modal attention is upgraded with new learning objectives for the audio, visual and joint modalities. We conduct experiments on AVS benchmarks, demonstrating that our method achieves state-of-the-art (SOTA) segmentation accuracy.
Authors: Felix Hsieh, Huy H. Nguyen, AprilPyone MaungMaung, Dmitrii Usynin, Isao Echizen
Abstract: Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor mitigation approach via machine unlearning to counter such backdoor attacks. The proposed method utilizes model activation of domain-equivalent unseen data to guide the editing of the model's weights. Unlike the previous unlearning-based mitigation methods, ours is computationally inexpensive and achieves state-of-the-art performance while only requiring a handful of unseen samples for unlearning. In addition, we also point out that unlearning the backdoor may cause the whole targeted class to be unlearned, thus introducing an additional repair step to preserve the model's utility after editing the model. Experiment results show that the proposed method is effective in unlearning the backdoor on different datasets and trigger patterns.
Authors: Congrong Xu, Justin Kerr, Angjoo Kanazawa
Abstract: Novel view synthesis from unconstrained in-the-wild image collections remains a significant yet challenging task due to photometric variations and transient occluders that complicate accurate scene reconstruction. Previous methods have approached these issues by integrating per-image appearance features embeddings in Neural Radiance Fields (NeRFs). Although 3D Gaussian Splatting (3DGS) offers faster training and real-time rendering, adapting it for unconstrained image collections is non-trivial due to the substantially different architecture. In this paper, we introduce Splatfacto-W, an approach that integrates per-Gaussian neural color features and per-image appearance embeddings into the rasterization process, along with a spherical harmonics-based background model to represent varying photometric appearances and better depict backgrounds. Our key contributions include latent appearance modeling, efficient transient object handling, and precise background modeling. Splatfacto-W delivers high-quality, real-time novel view synthesis with improved scene consistency in in-the-wild scenarios. Our method improves the Peak Signal-to-Noise Ratio (PSNR) by an average of 5.3 dB compared to 3DGS, enhances training speed by 150 times compared to NeRF-based methods, and achieves a similar rendering speed to 3DGS. Additional video results and code integrated into Nerfstudio are available at https://kevinxu02.github.io/splatfactow/.
Authors: Aryan Singh, Pepijn Van de Ven, Ciar\'an Eising, Patrick Denny
Abstract: In this study, we present the Graph Sub-Graph Network (GSN), a novel hybrid image classification model merging the strengths of Convolutional Neural Networks (CNNs) for feature extraction and Graph Neural Networks (GNNs) for structural modeling. GSN employs k-means clustering to group graph nodes into clusters, facilitating the creation of subgraphs. These subgraphs are then utilized to learn representative `atoms` for dictionary learning, enabling the identification of sparse, class-distinguishable features. This integrated approach is particularly relevant in domains like medical imaging, where discerning subtle feature differences is crucial for accurate classification. To evaluate the performance of our proposed GSN, we conducted experiments on benchmark datasets, including PascalVOC and HAM10000. Our results demonstrate the efficacy of our model in optimizing dictionary configurations across varied classes, which contributes to its effectiveness in medical classification tasks. This performance enhancement is primarily attributed to the integration of CNNs, GNNs, and graph learning techniques, which collectively improve the handling of datasets with limited labeled examples. Specifically, our experiments show that the model achieves a higher accuracy on benchmark datasets such as Pascal VOC and HAM10000 compared to conventional CNN approaches.
Authors: Chunsan Hong, Tae-Hyun Oh, Minhyuk Sung
Abstract: Diffusion models have achieved remarkable success in Text-to-Image generation tasks, leading to the development of many commercial models. However, recent studies have reported that diffusion models often generate replicated images in train data when triggered by specific prompts, potentially raising social issues ranging from copyright to privacy concerns. To sidestep the memorization, there have been recent studies for developing memorization mitigation methods for diffusion models. Nevertheless, the lack of benchmarks impedes the assessment of the true effectiveness of these methods. In this work, we present MemBench, the first benchmark for evaluating image memorization mitigation methods. Our benchmark includes a large number of memorized image trigger prompts in various Text-to-Image diffusion models. Furthermore, in contrast to the prior work evaluating mitigation performance only on trigger prompts, we present metrics evaluating on both trigger prompts and general prompts, so that we can see whether mitigation methods address the memorization issue while maintaining performance for general prompts. This is an important development considering the practical applications which previous works have overlooked. Through evaluation on MemBench, we verify that the performance of existing image memorization mitigation methods is still insufficient for application to diffusion models. The code and datasets are available at https://github.com/chunsanHong/MemBench\_code.
Authors: Diego Thomas, Briac Toussaint, Jean-Sebastien Franco, Edmond Boyer
Abstract: Volumetric shape representations have become ubiquitous in multi-view reconstruction tasks. They often build on regular voxel grids as discrete representations of 3D shape functions, such as SDF or radiance fields, either as the full shape model or as sampled instantiations of continuous representations, as with neural networks. Despite their proven efficiency, voxel representations come with the precision versus complexity trade-off. This inherent limitation can significantly impact performance when moving away from simple and uncluttered scenes. In this paper we investigate an alternative discretization strategy with the Centroidal Voronoi Tesselation (CVT). CVTs allow to better partition the observation space with respect to shape occupancy and to focus the discretization around shape surfaces. To leverage this discretization strategy for multi-view reconstruction, we introduce a volumetric optimization framework that combines explicit SDF fields with a shallow color network, in order to estimate 3D shape properties over tetrahedral grids. Experimental results with Chamfer statistics validate this approach with unprecedented reconstruction quality on various scenarios such as objects, open scenes or human.
Authors: Waseem Shariff, Paul Kielty, Joseph Lemley, Peter Corcoran
Abstract: Event camera-based driver monitoring is emerging as a pivotal area of research, driven by its significant advantages such as rapid response, low latency, power efficiency, enhanced privacy, and prevention of undersampling. Effective detection of driver distraction is crucial in driver monitoring systems to enhance road safety and reduce accident rates. The integration of an optimized sensor such as Event Camera with an optimized network is essential for maximizing these benefits. This paper introduces the innovative concept of sensing without seeing to detect driver distraction, leveraging computationally efficient spiking neural networks (SNN). To the best of our knowledge, this study is the first to utilize event camera data with spiking neural networks for driver distraction. The proposed Spiking-DD network not only achieve state of the art performance but also exhibit fewer parameters and provides greater accuracy than current event-based methodologies.
Authors: Mingrui Wu, Xinyue Cai, Jiayi Ji, Jiale Li, Oucheng Huang, Gen Luo, Hao Fei, Guannan Jiang, Xiaoshuai Sun, Rongrong Ji
Abstract: In this work, we propose a training-free method to inject visual referring into Multimodal Large Language Models (MLLMs) through learnable visual token optimization. We observe the relationship between text prompt tokens and visual tokens in MLLMs, where attention layers model the connection between them. Our approach involves adjusting visual tokens from the MLP output during inference, controlling which text prompt tokens attend to which visual tokens. We optimize a learnable visual token based on an energy function, enhancing the strength of referential regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referential abilities into MLLMs. Our method support referring with box, mask, scribble and point. The results demonstrate that our method exhibits controllability and interpretability.
Authors: Yanbo Ding, Shaobin Zhuang, Kunchang Li, Zhengrong Yue, Yu Qiao, Yali Wang
Abstract: Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES addresses this challenging task by developing a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, we find that existing benchmarks lack detailed descriptions of complex 3D spatial relationships of multiple objects. To fill this gap, we further construct a new benchmark of T2I-3DisBench (3D image scene), which describes diverse 3D image scenes with 50 detailed prompts. Extensive experiments show the state-of-the-art performance of MUSES on both T2I-CompBench and T2I-3DisBench, outperforming recent strong competitors such as DALL-E 3 and Stable Diffusion 3. These results demonstrate a significant step of MUSES forward in bridging natural language, 2D image generation, and 3D world. Our codes and models will be released soon.
Authors: Shuhong Liu, Xiang Chen, Hongming Chen, Quanfeng Xu, Mingrui Li
Abstract: Reconstruction under adverse rainy conditions poses significant challenges due to reduced visibility and the distortion of visual perception. These conditions can severely impair the quality of geometric maps, which is essential for applications ranging from autonomous planning to environmental monitoring. In response to these challenges, this study introduces the novel task of 3D Reconstruction in Rainy Environments (3DRRE), specifically designed to address the complexities of reconstructing 3D scenes under rainy conditions. To benchmark this task, we construct the HydroViews dataset that comprises a diverse collection of both synthesized and real-world scene images characterized by various intensities of rain streaks and raindrops. Furthermore, we propose DeRainGS, the first 3DGS method tailored for reconstruction in adverse rainy environments. Extensive experiments across a wide range of rain scenarios demonstrate that our method delivers state-of-the-art performance, remarkably outperforming existing occlusion-free methods.
Authors: Antonyo Musabini, Ivan Novikov, Sana Soula, Christel Leonet, Lihao Wang, Rachid Benmokhtar, Fabian Burger, Thomas Boulay, Xavier Perrotton
Abstract: Current parking area perception algorithms primarily focus on detecting vacant slots within a limited range, relying on error-prone homographic projection for both labeling and inference. However, recent advancements in Advanced Driver Assistance System (ADAS) require interaction with end-users through comprehensive and intelligent Human-Machine Interfaces (HMIs). These interfaces should present a complete perception of the parking area going from distinguishing vacant slots' entry lines to the orientation of other parked vehicles. This paper introduces Multi-Task Fisheye Cross View Transformers (MT F-CVT), which leverages features from a four-camera fisheye Surround-view Camera System (SVCS) with multihead attentions to create a detailed Bird-Eye View (BEV) grid feature map. Features are processed by both a segmentation decoder and a Polygon-Yolo based object detection decoder for parking slots and vehicles. Trained on data labeled using LiDAR, MT F-CVT positions objects within a 25m x 25m real open-road scenes with an average error of only 20 cm. Our larger model achieves an F-1 score of 0.89. Moreover the smaller model operates at 16 fps on an Nvidia Jetson Orin embedded board, with similar detection results to the larger one. MT F-CVT demonstrates robust generalization capability across different vehicles and camera rig configurations. A demo video from an unseen vehicle and camera rig is available at: https://streamable.com/jjw54x.
Authors: Shubhendu Jena, Franck Multon, Adnane Boukhayma
Abstract: This paper presents a novel approach for sparse 3D reconstruction by leveraging the expressive power of Neural Radiance Fields (NeRFs) and fast transfer of their features to learn accurate occupancy fields. Existing 3D reconstruction methods from sparse inputs still struggle with capturing intricate geometric details and can suffer from limitations in handling occluded regions. On the other hand, NeRFs excel in modeling complex scenes but do not offer means to extract meaningful geometry. Our proposed method offers the best of both worlds by transferring the information encoded in NeRF features to derive an accurate occupancy field representation. We utilize a pre-trained, generalizable state-of-the-art NeRF network to capture detailed scene radiance information, and rapidly transfer this knowledge to train a generalizable implicit occupancy network. This process helps in leveraging the knowledge of the scene geometry encoded in the generalizable NeRF prior and refining it to learn occupancy fields, facilitating a more precise generalizable representation of 3D space. The transfer learning approach leads to a dramatic reduction in training time, by orders of magnitude (i.e. from several days to 3.5 hrs), obviating the need to train generalizable sparse surface reconstruction methods from scratch. Additionally, we introduce a novel loss on volumetric rendering weights that helps in the learning of accurate occupancy fields, along with a normal loss that helps in global smoothing of the occupancy fields. We evaluate our approach on the DTU dataset and demonstrate state-of-the-art performance in terms of reconstruction accuracy, especially in challenging scenarios with sparse input data and occluded regions. We furthermore demonstrate the generalization capabilities of our method by showing qualitative results on the Blended MVS dataset without any retraining.
Authors: Zhenye Xu, Yao Guo
Abstract: This paper addresses the critical task of gait cycle segmentation using short sequences from ear-worn IMUs, a practical and non-invasive approach for home-based monitoring and rehabilitation of patients with impaired motor function. While previous studies have focused on IMUs positioned on the lower limbs, ear-worn IMUs offer a unique advantage in capturing gait dynamics with minimal intrusion. To address the challenges of gait cycle segmentation using short sequences, we introduce the Gait Characteristic Curve Regression and Restoration (GCCRR) method, a novel two-stage approach designed for fine-grained gait phase segmentation. The first stage transforms the segmentation task into a regression task on the Gait Characteristic Curve (GCC), which is a one-dimensional feature sequence incorporating periodic information. The second stage restores the gait cycle using peak detection techniques. Our method employs Bi-LSTM-based deep learning algorithms for regression to ensure reliable segmentation for short gait sequences. Evaluation on the HamlynGait dataset demonstrates that GCCRR achieves over 80\% Accuracy, with a Timestamp Error below one sampling interval. Despite its promising results, the performance lags behind methods using more extensive sensor systems, highlighting the need for larger, more diverse datasets. Future work will focus on data augmentation using motion capture systems and improving algorithmic generalizability.
Authors: Minh-Duc Nguyen, Hyung-Jeong Yang, Soo-Hyung Kim, Ji-Eun Shin, Seung-Won Kim
Abstract: Accurate pain assessment is crucial in healthcare for effective diagnosis and treatment; however, traditional methods relying on self-reporting are inadequate for populations unable to communicate their pain. Cutting-edge AI is promising for supporting clinicians in pain recognition using facial video data. In this paper, we enhance pain recognition by employing facial video analysis within a Transformer-based deep learning model. By combining a powerful Masked Autoencoder with a Transformers-based classifier, our model effectively captures pain level indicators through both expressions and micro-expressions. We conducted our experiment on the AI4Pain dataset, which produced promising results that pave the way for innovative healthcare solutions that are both comprehensive and objective.
Authors: Youngeun Kim, Jun Fang, Qin Zhang, Zhaowei Cai, Yantao Shen, Rahul Duggal, Dripta S. Raychaudhuri, Zhuowen Tu, Yifan Xing, Onkar Dabeer
Abstract: The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significant challenge in effectively generalizing to unseen test-time classes. To address this challenge, we introduce a new practical CL setting tailored for open-world visual representation learning. In this setting, subsequent data streams systematically introduce novel classes that are disjoint from those seen in previous training phases, while also remaining distinct from the unseen test classes. In response, we present Dynamic Prompt and Representation Learner (DPaRL), a simple yet effective Prompt-based CL (PCL) method. Our DPaRL learns to generate dynamic prompts for inference, as opposed to relying on a static prompt pool in previous PCL methods. In addition, DPaRL jointly learns dynamic prompt generation and discriminative representation at each training stage whereas prior PCL methods only refine the prompt learning throughout the process. Our experimental results demonstrate the superiority of our approach, surpassing state-of-the-art methods on well-established open-world image retrieval benchmarks by an average of 4.7% improvement in Recall@1 performance.
Authors: Qiyuan Wang, Shang Zhao, Zikang Xu, S Kevin Zhou
Abstract: Surgical instrument segmentation is instrumental to minimally invasive surgeries and related applications. Most previous methods formulate this task as single-frame-based instance segmentation while ignoring the natural temporal and stereo attributes of a surgical video. As a result, these methods are less robust against the appearance variation through temporal motion and view change. In this work, we propose a novel LACOSTE model that exploits Location-Agnostic COntexts in Stereo and TEmporal images for improved surgical instrument segmentation. Leveraging a query-based segmentation model as core, we design three performance-enhancing modules. Firstly, we design a disparity-guided feature propagation module to enhance depth-aware features explicitly. To generalize well for even only a monocular video, we apply a pseudo stereo scheme to generate complementary right images. Secondly, we propose a stereo-temporal set classifier, which aggregates stereo-temporal contexts in a universal way for making a consolidated prediction and mitigates transient failures. Finally, we propose a location-agnostic classifier to decouple the location bias from mask prediction and enhance the feature semantics. We extensively validate our approach on three public surgical video datasets, including two benchmarks from EndoVis Challenges and one real radical prostatectomy surgery dataset GraSP. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.
Authors: Xiaolei Qin, Xin Su, Liangpei Zhang
Abstract: Satellite image time series (SITS) data provides continuous observations over time, allowing for the tracking of vegetation changes and growth patterns throughout the seasons and years. Numerous deep learning (DL) approaches using SITS for crop classification have emerged recently, with the latest approaches adopting Transformer for SITS classification. However, the quadratic complexity of self-attention in Transformer poses challenges for classifying long time series. While the cutting-edge Mamba architecture has demonstrated strength in various domains, including remote sensing image interpretation, its capacity to learn temporal representations in SITS data remains unexplored. Moreover, the existing SITS classification methods often depend solely on crop labels as supervision signals, which fails to fully exploit the temporal information. In this paper, we proposed a Satellite Image Time Series Mamba (SITSMamba) method for crop classification based on remote sensing time series data. The proposed SITSMamba contains a spatial encoder based on Convolutional Neural Networks (CNN) and a Mamba-based temporal encoder. To exploit richer temporal information from SITS, we design two branches of decoder used for different tasks. The first branch is a crop Classification Branch (CBranch), which includes a ConvBlock to decode the feature to a crop map. The second branch is a SITS Reconstruction Branch that uses a Linear layer to transform the encoded feature to predict the original input values. Furthermore, we design a Positional Weight (PW) applied to the RBranch to help the model learn rich latent knowledge from SITS. We also design two weighting factors to control the balance of the two branches during training. The code of SITSMamba is available at: https://github.com/XiaoleiQinn/SITSMamba.
Authors: Youngsun Lim, Hojun Choi, Pin-Yu Chen, Hyunjung Shim
Abstract: Despite the impressive success of text-to-image (TTI) generation models, existing studies overlook the issue of whether these models accurately convey factual information. In this paper, we focus on the problem of image hallucination, where images created by generation models fail to faithfully depict factual content. To address this, we introduce I-HallA (Image Hallucination evaluation with Question Answering), a novel automated evaluation metric that measures the factuality of generated images through visual question answering (VQA). We also introduce I-HallA v1.0, a curated benchmark dataset for this purpose. As part of this process, we develop a pipeline that generates high-quality question-answer pairs using multiple GPT-4 Omni-based agents, with human judgments to ensure accuracy. Our evaluation protocols measure image hallucination by testing if images from existing text-to-image models can correctly respond to these questions. The I-HallA v1.0 dataset comprises 1.2K diverse image-text pairs across nine categories with 1,000 rigorously curated questions covering various compositional challenges. We evaluate five text-to-image models using I-HallA and reveal that these state-of-the-art models often fail to accurately convey factual information. Moreover, we validate the reliability of our metric by demonstrating a strong Spearman correlation (rho=0.95) with human judgments. We believe our benchmark dataset and metric can serve as a foundation for developing factually accurate text-to-image generation models.
Authors: Jinze Yu, Xin Peng, Zhengda Lu, Laurent Kneip, Yiqun Wang
Abstract: A spike camera is a specialized high-speed visual sensor that offers advantages such as high temporal resolution and high dynamic range compared to conventional frame cameras. These features provide the camera with significant advantages in many computer vision tasks. However, the tasks of 3D reconstruction and novel view synthesis based on spike cameras remain underdeveloped. Although there are existing methods for learning neural radiance fields from spike stream, they either lack robustness in extremely noisy, low-quality lighting conditions or suffer from high computational complexity due to the deep fully connected neural networks and ray marching rendering strategies used in neural radiance fields, making it difficult to recover fine texture details. In contrast, the latest advancements in 3DGS have achieved high-quality real-time rendering by optimizing the point cloud representation into Gaussian ellipsoids. Building on this, we introduce SpikeGS, the method to learn 3D Gaussian fields solely from spike stream. We designed a differentiable spike stream rendering framework based on 3DGS, incorporating noise embedding and spiking neurons. By leveraging the multi-view consistency of 3DGS and the tile-based multi-threaded parallel rendering mechanism, we achieved high-quality real-time rendering results. Additionally, we introduced a spike rendering loss function that generalizes under varying illumination conditions. Our method can reconstruct view synthesis results with fine texture details from a continuous spike stream captured by a moving spike camera, while demonstrating high robustness in extremely noisy low-light scenarios. Experimental results on both real and synthetic datasets demonstrate that our method surpasses existing approaches in terms of rendering quality and speed. Our code will be available at https://github.com/520jz/SpikeGS.
Authors: Chen Guo, Tianjian Jiang, Manuel Kaufmann, Chengwei Zheng, Julien Valentin, Jie Song, Otmar Hilliges
Abstract: While previous years have seen great progress in the 3D reconstruction of humans from monocular videos, few of the state-of-the-art methods are able to handle loose garments that exhibit large non-rigid surface deformations during articulation. This limits the application of such methods to humans that are dressed in standard pants or T-shirts. Our method, ReLoo, overcomes this limitation and reconstructs high-quality 3D models of humans dressed in loose garments from monocular in-the-wild videos. To tackle this problem, we first establish a layered neural human representation that decomposes clothed humans into a neural inner body and outer clothing. On top of the layered neural representation, we further introduce a non-hierarchical virtual bone deformation module for the clothing layer that can freely move, which allows the accurate recovery of non-rigidly deforming loose clothing. A global optimization jointly optimizes the shape, appearance, and deformations of the human body and clothing via multi-layer differentiable volume rendering. To evaluate ReLoo, we record subjects with dynamically deforming garments in a multi-view capture studio. This evaluation, both on existing and our novel dataset, demonstrates ReLoo's clear superiority over prior art on both indoor datasets and in-the-wild videos.
Authors: Chuqiao Li, Julian Chibane, Yannan He, Naama Pearl, Andreas Geiger, Gerard Pons-moll
Abstract: We introduce Unimotion, the first unified multi-task human motion model capable of both flexible motion control and frame-level motion understanding. While existing works control avatar motion with global text conditioning, or with fine-grained per frame scripts, none can do both at once. In addition, none of the existing works can output frame-level text paired with the generated poses. In contrast, Unimotion allows to control motion with global text, or local frame-level text, or both at once, providing more flexible control for users. Importantly, Unimotion is the first model which by design outputs local text paired with the generated poses, allowing users to know what motion happens and when, which is necessary for a wide range of applications. We show Unimotion opens up new applications: 1.) Hierarchical control, allowing users to specify motion at different levels of detail, 2.) Obtaining motion text descriptions for existing MoCap data or YouTube videos 3.) Allowing for editability, generating motion from text, and editing the motion via text edits. Moreover, Unimotion attains state-of-the-art results for the frame-level text-to-motion task on the established HumanML3D dataset. The pre-trained model and code are available available on our project page at https://coral79.github.io/uni-motion/.
Authors: Tim B\"uchner, Niklas Penzel, Orlando Guntinas-Lichius, Joachim Denzler
Abstract: Understanding expressions is vital for deciphering human behavior, and nowadays, end-to-end trained black box models achieve high performance. Due to the black-box nature of these models, it is unclear how they behave when applied out-of-distribution. Specifically, these models show decreased performance for unilateral facial palsy patients. We hypothesize that one crucial factor guiding the internal decision rules is facial symmetry. In this work, we use insights from causal reasoning to investigate the hypothesis. After deriving a structural causal model, we develop a synthetic interventional framework. This approach allows us to analyze how facial symmetry impacts a network's output behavior while keeping other factors fixed. All 17 investigated expression classifiers significantly lower their output activations for reduced symmetry. This result is congruent with observed behavior on real-world data from healthy subjects and facial palsy patients. As such, our investigation serves as a case study for identifying causal factors that influence the behavior of black-box models.
Authors: Xianda Zhang, Siyuan Liang
Abstract: Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques, primarily designed for simpler models like image classifiers, often fail to effectively detect and remove backdoors in object detectors. We propose a backdoor defense framework tailored to object detection models, based on the observation that backdoor attacks cause significant inconsistencies between local modules' behaviors, such as the Region Proposal Network (RPN) and classification head. By quantifying and analyzing these inconsistencies, we develop an algorithm to detect backdoors. We find that the inconsistent module is usually the main source of backdoor behavior, leading to a removal method that localizes the affected module, resets its parameters, and fine-tunes the model on a small clean dataset. Extensive experiments with state-of-the-art two-stage object detectors show our method achieves a 90% improvement in backdoor removal rate over fine-tuning baselines, while limiting clean data accuracy loss to less than 4%. To the best of our knowledge, this work presents the first approach that addresses both the detection and removal of backdoors in two-stage object detection models, advancing the field of securing these complex systems against backdoor attacks.
Authors: Sunghyun Ahn, Youngwan Jo, Kijung Lee, Sanghyun Park
Abstract: Video anomaly detection (VAD) is a crucial task in video analysis and surveillance within computer vision. Currently, VAD is gaining attention with memory techniques that store the features of normal frames. The stored features are utilized for frame reconstruction, identifying an abnormality when a significant difference exists between the reconstructed and input frames. However, this approach faces several challenges due to the simultaneous optimization required for both the memory and encoder-decoder model. These challenges include increased optimization difficulty, complexity of implementation, and performance variability depending on the memory size. To address these challenges,we propose an effective memory method for VAD, called VideoPatchCore. Inspired by PatchCore, our approach introduces a structure that prioritizes memory optimization and configures three types of memory tailored to the characteristics of video data. This method effectively addresses the limitations of existing memory-based methods, achieving good performance comparable to state-of-the-art methods. Furthermore, our method requires no training and is straightforward to implement, making VAD tasks more accessible. Our code is available online at github.com/SkiddieAhn/Paper-VideoPatchCore.
Authors: Mengchen Zhang, Tong Wu, Tai Wang, Tengfei Wang, Ziwei Liu, Dahua Lin
Abstract: 6D object pose estimation aims at determining an object's translation, rotation, and scale, typically from a single RGBD image. Recent advancements have expanded this estimation from instance-level to category-level, allowing models to generalize across unseen instances within the same category. However, this generalization is limited by the narrow range of categories covered by existing datasets, such as NOCS, which also tend to overlook common real-world challenges like occlusion. To tackle these challenges, we introduce Omni6D, a comprehensive RGBD dataset featuring a wide range of categories and varied backgrounds, elevating the task to a more realistic context. 1) The dataset comprises an extensive spectrum of 166 categories, 4688 instances adjusted to the canonical pose, and over 0.8 million captures, significantly broadening the scope for evaluation. 2) We introduce a symmetry-aware metric and conduct systematic benchmarks of existing algorithms on Omni6D, offering a thorough exploration of new challenges and insights. 3) Additionally, we propose an effective fine-tuning approach that adapts models from previous datasets to our extensive vocabulary setting. We believe this initiative will pave the way for new insights and substantial progress in both the industrial and academic fields, pushing forward the boundaries of general 6D pose estimation.
Authors: Wenhao Yang, Jianguo Wei, Wenhuan Lu, Lei Li
Abstract: Grounding objects in images using visual cues is a well-established approach in computer vision, yet the potential of audio as a modality for object recognition and grounding remains underexplored. We introduce YOSS, "You Only Speak Once to See," to leverage audio for grounding objects in visual scenes, termed Audio Grounding. By integrating pre-trained audio models with visual models using contrastive learning and multi-modal alignment, our approach captures speech commands or descriptions and maps them directly to corresponding objects within images. Experimental results indicate that audio guidance can be effectively applied to object grounding, suggesting that incorporating audio guidance may enhance the precision and robustness of current object grounding methods and improve the performance of robotic systems and computer vision applications. This finding opens new possibilities for advanced object recognition, scene understanding, and the development of more intuitive and capable robotic systems.
Authors: Zhongwen Zhang, Yuri Boykov
Abstract: Maximization of mutual information between the model's input and output is formally related to "decisiveness" and "fairness" of the softmax predictions, motivating these unsupervised entropy-based criteria for clustering. First, in the context of linear softmax models, we discuss some general properties of entropy-based clustering. Disproving some earlier claims, we point out fundamental differences with K-means. On the other hand, we prove the margin maximizing property for decisiveness establishing a relation to SVM-based clustering. Second, we propose a new self-labeling formulation of entropy clustering for general softmax models. The pseudo-labels are introduced as auxiliary variables "splitting" the fairness and decisiveness. The derived self-labeling loss includes the reverse cross-entropy robust to pseudo-label errors and allows an efficient EM solver for pseudo-labels. Our algorithm improves the state of the art on several standard benchmarks for deep clustering.
Authors: Ziqiang Li, Hong Sun, Pengfei Xia, Beihao Xia, Xue Rui, Wei Zhang, Qinglang Guo, Zhangjie Fu, Bin Li
Abstract: Poisoning efficiency is crucial in poisoning-based backdoor attacks, as attackers aim to minimize the number of poisoning samples while maximizing attack efficacy. Recent studies have sought to enhance poisoning efficiency by selecting effective samples. However, these studies typically rely on a proxy backdoor injection task to identify an efficient set of poisoning samples. This proxy attack-based approach can lead to performance degradation if the proxy attack settings differ from those of the actual victims, due to the shortcut nature of backdoor learning. Furthermore, proxy attack-based methods are extremely time-consuming, as they require numerous complete backdoor injection processes for sample selection. To address these concerns, we present a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on the similarity between clean samples and their corresponding poisoning samples, as well as the diversity of the poisoning set. The proposed PFS is motivated by the observation that selecting samples with high similarity between clean and corresponding poisoning samples results in significantly higher attack success rates compared to using samples with low similarity. Additionally, we provide theoretical foundations to explain the proposed PFS. We comprehensively evaluate the proposed strategy across various datasets, triggers, poisoning rates, architectures, and training hyperparameters. Our experimental results demonstrate that PFS enhances backdoor attack efficiency while also offering a remarkable speed advantage over previous proxy attack-based selection methodologies.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Abstract: Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Antoine Salmona, Julie Delon, Agn\`es Desolneux
Abstract: The Gromov-Wasserstein (GW) distance is frequently used in machine learning to compare distributions across distinct metric spaces. Despite its utility, it remains computationally intensive, especially for large-scale problems. Recently, a novel Wasserstein distance specifically tailored for Gaussian mixture models (GMMs) and known as MW2 (mixture Wasserstein) has been introduced by several authors. In scenarios where data exhibit clustering, this approach simplifies to a small-scale discrete optimal transport problem, which complexity depends solely on the number of Gaussian components in the GMMs. This paper aims to incorporate invariance properties into MW2. This is done by introducing new Gromov-type distances, designed to be isometry-invariant in Euclidean spaces and applicable for comparing GMMs across different dimensional spaces. Our first contribution is the Mixture Gromov Wasserstein distance (MGW2), which can be viewed as a "Gromovized" version of MW2. This new distance has a straightforward discrete formulation, making it highly efficient for estimating distances between GMMs in practical applications. To facilitate the derivation of a transport plan between GMMs, we present a second distance, the Embedded Wasserstein distance (EW2). This distance turns out to be closely related to several recent alternatives to Gromov-Wasserstein. We show that EW2 can be adapted to derive a distance as well as optimal transportation plans between GMMs. We demonstrate the efficiency of these newly proposed distances on medium to large-scale problems, including shape matching and hyperspectral image color transfer.
Authors: Georgios Ioannides, Aman Chadha, Aaron Elkins
Abstract: We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance information aggregation across multiple modalities, including Speech, Text, and Vision. DAAM integrates learnable mean and variance into its attention mechanism, implemented in a multi-head framework, enabling it to collectively model any probability distribution for dynamic recalibration of feature significance. This method demonstrates significant improvements, especially with highly non-stationary data, surpassing the state-of-the-art attention techniques in model performance, up to approximately +20% (abs.) in accuracy. Empirically, DAAM exhibits superior adaptability and efficacy across a diverse range of tasks, including emotion recognition in speech, image classification, and text classification, thereby establishing its robustness and versatility in handling data across multiple modalities. Furthermore, we introduce the Importance Factor, a new learning-based metric that enhances the explainability of models trained with DAAM-based methods.
Authors: Xiaoyu Qiao, Weisheng Li, Guofen Wang, Yuping Huang
Abstract: Deep unfolding networks (DUNs) have demonstrated significant potential in accelerating magnetic resonance imaging (MRI). However, they often encounter high computational costs and slow convergence rates. Besides, they struggle to fully exploit the complementarity when incorporating multiple priors. In this study, we propose a multi-prior collaborative DUN, termed MCU-Net, to address these limitations. Our method features a parallel structure consisting of different optimization-inspired subnetworks based on low-rank and sparsity, respectively. We design a gates-controlled spatial attention module (GSAM), evaluating the relative confidence (RC) and overall confidence (OC) maps for intermediate reconstructions produced by different subnetworks. RC allocates greater weights to the image regions where each subnetwork excels, enabling precise element-wise collaboration. We design correction modules to enhance the effectiveness in regions where both subnetworks exhibit limited performance, as indicated by low OC values, thereby obviating the need for additional branches. The gate units within GSAMs are designed to preserve necessary information across multiple iterations, improving the accuracy of the learned confidence maps and enhancing robustness against accumulated errors. Experimental results on multiple datasets show significant improvements on PSNR and SSIM results with relatively low FLOPs compared to cutting-edge methods. Additionally, the proposed strategy can be conveniently applied to various DUN structures to enhance their performance.
Authors: Yubiao Yue, Zhenzhang Li
Abstract: Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range dependencies result in poor classification performances. In contrast, ViTs are hampered by the quadratic computational complexity of their self-attention mechanism, making them difficult to deploy in real-world settings with limited computational resources. Recent studies have shown that state space models (SSMs) represented by Mamba can effectively model long-range dependencies while maintaining linear computational complexity. Inspired by it, we proposed MedMamba, the first Vision Mamba for generalized medical image classification. Concretely, we introduced a novel hybrid basic block named SS-Conv-SSM, which purely integrates the convolutional layers for extracting local features with the abilities of SSM to capture long-range dependencies, aiming to model medical images from different image modalities efficiently. By employing the grouped convolution strategy and channel-shuffle operation, MedMamba successfully provides fewer model parameters and a lower computational burden for efficient applications without sacrificing accuracy. We thoroughly evaluated MedMamba using 16 datasets containing ten imaging modalities and 411,007 images. Experimental results show that MedMamba demonstrates competitive performance on most tasks compared with the state-of-the-art methods. This work aims to explore the potential of Vision Mamba and establish a new baseline for medical image classification, thereby providing valuable insights for developing more powerful Mamba-based artificial intelligence algorithms and applications in medicine. The source codes and all pre-trained weights of MedMamba are available at https://github.com/YubiaoYue/MedMamba.
Authors: Junbo Wang, Wenhai Liu, Qiaojun Yu, Yang You, Liu Liu, Weiming Wang, Cewu Lu
Abstract: Articulated objects are commonly found in daily life. It is essential that robots can exhibit robust perception and manipulation skills for articulated objects in real-world robotic applications. However, existing methods for articulated objects insufficiently address noise in point clouds and struggle to bridge the gap between simulation and reality, thus limiting the practical deployment in real-world scenarios. To tackle these challenges, we propose a framework towards Robust Perception and Manipulation for Articulated Objects (RPMArt), which learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. Our primary contribution is a Robust Articulation Network (RoArtNet) that is able to predict both joint parameters and affordable points robustly by local feature learning and point tuple voting. Moreover, we introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer. Finally, with the estimated affordable point and articulation joint constraint, the robot can generate robust actions to manipulate articulated objects. After learning only from synthetic data, RPMArt is able to transfer zero-shot to real-world articulated objects. Experimental results confirm our approach's effectiveness, with our framework achieving state-of-the-art performance in both noise-added simulation and real-world environments. Code, data and more results can be found on the project website at https://r-pmart.github.io.
Authors: Ziheng Deng, Hua Chen, Yongzheng Zhou, Haibo Hu, Zhiyong Xu, Jiayuan Sun, Tianling Lyu, Yan Xi, Yang Chen, Jun Zhao
Abstract: Four-dimensional cone-beam computed tomography (4D CBCT) provides respiration-resolved images and can be used for image-guided radiation therapy. However, the ability to reveal respiratory motion comes at the cost of image artifacts. As raw projection data are sorted into multiple respiratory phases, the cone-beam projections become much sparser and the reconstructed 4D CBCT images will be covered by severe streak artifacts. Although several deep learning-based methods have been proposed to address this issue, most algorithms employ 2D network models as backbones, neglecting the intrinsic structural priors within 4D CBCT images. In this paper, we first explore the origin and appearance of streak artifacts in 4D CBCT images. We find that streak artifacts exhibit a unique rotational motion along with the patient's respiration, distinguishable from diaphragm-driven respiratory motion in the spatiotemporal domain. Therefore, we propose a novel 4D neural network model, RSTAR4D-Net, designed to address Rotational STreak Artifact Reduction by integrating the spatial and temporal information within 4D CBCT images. Specifically, we overcome the computational and training difficulties of a 4D neural network. The specially designed model adopts an efficient implementation of 4D convolutions to reduce computational costs and thus can process the whole 4D image in one pass. Additionally, a Tetris training strategy pertinent to the separable 4D convolutions is proposed to effectively train the model using limited 4D training samples. Extensive experiments substantiate the effectiveness of our proposed method, and the RSTAR4D-Net shows superior performance compared to other methods. The source code and dynamic demos are available at https://github.com/ivy9092111111/RSTAR.
Authors: Liangchen Li, Jiajun He
Abstract: Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, Consistency Models (CMs) have emerged to address this challenge by approximating the integral of the PF ODE, largely reducing the number of iterations. Yet, the absence of an explicit ODE solver complicates the inversion process. To resolve this, we introduce Bidirectional Consistency Model (BCM), which learns a single neural network that enables both forward and backward traversal along the PF ODE, efficiently unifying generation and inversion tasks within one framework. We can train BCM from scratch or tune it using a pretrained consistency model, wh ich reduces the training cost and increases scalability. We demonstrate that BCM enables one-step generation and inversion while also allowing the use of additional steps to enhance generation quality or reduce reconstruction error. We further showcase BCM's capability in downstream tasks, such as interpolation, inpainting, and blind restoration of compressed images. Notably, when the number of function evaluations (NFE) is constrained, BCM surpasses domain-specific restoration methods, such as I$^2$SB and Palette, in a fully zero-shot manner, offering an efficient alternative for inversion problems. Our code and weights are available at https://github.com/Mosasaur5526/BCM-iCT-torch.
Authors: Zixi Wang, Zeyi Liu, Nicolas Ouporov, Shuran Song
Abstract: Robot-to-human object handover is an important step in many human robot collaboration tasks. A successful handover requires the robot to maintain a stable grasp on the object while making sure the human receives the object in a natural and easy-to-use manner. We propose ContactHandover, a robot to human handover system that consists of two phases: a contact-guided grasping phase and an object delivery phase. During the grasping phase, ContactHandover predicts both 6-DoF robot grasp poses and a 3D affordance map of human contact points on the object. The robot grasp poses are re-ranked by penalizing those that block human contact points, and the robot executes the highest ranking grasp. During the delivery phase, the robot end effector pose is computed by maximizing human contact points close to the human while minimizing the human arm joint torques and displacements. We evaluate our system on 27 diverse household objects and show that our system achieves better visibility and reachability of human contacts to the receiver compared to several baselines. More results can be found on https://clairezixiwang.github.io/ContactHandover.github.io
URLs: https://clairezixiwang.github.io/ContactHandover.github.io
Authors: Ted Edward Holmberg, Elias Ioup, Mahdi Abdelguerfi
Abstract: This paper proposes two new measures applicable in a spatial bipartite network model: coverage and coverage robustness. The bipartite network must consist of observer nodes, observable nodes, and edges that connect observer nodes to observable nodes. The coverage and coverage robustness scores evaluate the effectiveness of the observer node placements. This measure is beneficial for stochastic data as it may be coupled with Monte Carlo simulations to identify optimal placements for new observer nodes. In this paper, we construct a Geo-SpatioTemporal Bipartite Network (GSTBN) within the stochastic and dynamical environment of the Gulf of Mexico. This GSTBN consists of GCOOS sensor nodes and HYCOM Region of Interest (RoI) event nodes. The goal is to identify optimal placements to expand GCOOS to improve the forecasting outcomes by the HYCOM ocean prediction model.
Authors: Ted Edward Holmberg, Mahdi Abdelguerfi, Elias Ioup
Abstract: Spatiotemporal networks' observational capabilities are crucial for accurate data gathering and informed decisions across multiple sectors. This study focuses on the Spatiotemporal Ranged Observer-Observable Bipartite Network (STROOBnet), linking observational nodes (e.g., surveillance cameras) to events within defined geographical regions, enabling efficient monitoring. Using data from Real-Time Crime Camera (RTCC) systems and Calls for Service (CFS) in New Orleans, where RTCC combats rising crime amidst reduced police presence, we address the network's initial observational imbalances. Aiming for uniform observational efficacy, we propose the Proximal Recurrence approach. It outperformed traditional clustering methods like k-means and DBSCAN by offering holistic event frequency and spatial consideration, enhancing observational coverage.
Authors: Lennart Alexander Van der Goten, Jingyu Guo, Kevin Smith
Abstract: The presence of motion artifacts in magnetic resonance imaging (MRI) scans poses a significant challenge, where even minor patient movements can lead to artifacts that may compromise the scan's utility.This paper introduces MAsked MOtion Correction (MAMOC), a novel method designed to address the issue of Retrospective Artifact Correction (RAC) in motion-affected MRI brain scans. MAMOC uses masked autoencoding self-supervision, transfer learning and test-time prediction to efficiently remove motion artifacts, producing high-fidelity, native-resolution scans. Until recently, realistic, openly available paired artifact presentations for training and evaluating retrospective motion correction methods did not exist, making it necessary to simulate motion artifacts. Leveraging the MR-ART dataset and bigger unlabeled datasets (ADNI, OASIS-3, IXI), this work is the first to evaluate motion correction in MRI scans using real motion data on a public dataset, showing that MAMOC achieves improved performance over existing motion correction methods.
Authors: Yifei Chen, Zhu Zhu, Shenghao Zhu, Linwei Qiu, Binfeng Zou, Fan Jia, Yunpeng Zhu, Chenyan Zhang, Zhaojie Fang, Feiwei Qin, Jin Fan, Changmiao Wang, Yu Gao, Gang Yu
Abstract: The incidence and mortality rates of malignant tumors, such as acute leukemia, have risen significantly. Clinically, hospitals rely on cytological examination of peripheral blood and bone marrow smears to diagnose malignant tumors, with accurate blood cell counting being crucial. Existing automated methods face challenges such as low feature expression capability, poor interpretability, and redundant feature extraction when processing high-dimensional microimage data. We propose a novel fine-grained classification model, SCKansformer, for bone marrow blood cells, which addresses these challenges and enhances classification accuracy and efficiency. The model integrates the Kansformer Encoder, SCConv Encoder, and Global-Local Attention Encoder. The Kansformer Encoder replaces the traditional MLP layer with the KAN, improving nonlinear feature representation and interpretability. The SCConv Encoder, with its Spatial and Channel Reconstruction Units, enhances feature representation and reduces redundancy. The Global-Local Attention Encoder combines Multi-head Self-Attention with a Local Part module to capture both global and local features. We validated our model using the Bone Marrow Blood Cell Fine-Grained Classification Dataset (BMCD-FGCD), comprising over 10,000 samples and nearly 40 classifications, developed with a partner hospital. Comparative experiments on our private dataset, as well as the publicly available PBC and ALL-IDB datasets, demonstrate that SCKansformer outperforms both typical and advanced microcell classification methods across all datasets. Our source code and private BMCD-FGCD dataset are available at https://github.com/JustlfC03/SCKansformer.
Authors: Jiwan Chung, Sungjae Lee, Minseo Kim, Seungju Han, Ashkan Yousefpour, Jack Hessel, Youngjae Yu
Abstract: Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant to the argument, and relevance can only be understood within the context of a broader argumentative structure. While visual arguments are readily appreciated by human audiences, we ask: are today's AI capable of similar understanding? We present VisArgs, a dataset of 1,611 images annotated with 5,112 visual premises (with regions), 5,574 commonsense premises, and reasoning trees connecting them into structured arguments. We propose three tasks for evaluating visual argument understanding: premise localization, premise identification, and conclusion deduction. Experiments show that 1) machines struggle to capture visual cues: GPT-4-O achieved 78.5% accuracy, while humans reached 98.0%. Models also performed 19.5% worse when distinguishing between irrelevant objects within the image compared to external objects. 2) Providing relevant visual premises improved model performance significantly.
Authors: Inye Na, Jonghun Kim, Eun Sook Ko, Hyunjin Park
Abstract: Motivated by the question, "Can we generate tumors with desired attributes?'' this study leverages radiomics features to explore the feasibility of generating synthetic tumor images. Characterized by its low-dimensional yet biologically meaningful markers, radiomics bridges the gap between complex medical imaging data and actionable clinical insights. We present RadiomicsFill-Mammo, the first of the RadiomicsFill series, an innovative technique that generates realistic mammogram mass images mirroring specific radiomics attributes using masked images and opposite breast images, leveraging a recent stable diffusion model. This approach also allows for the incorporation of essential clinical variables, such as BI-RADS and breast density, alongside radiomics features as conditions for mass generation. Results indicate that RadiomicsFill-Mammo effectively generates diverse and realistic tumor images based on various radiomics conditions. Results also demonstrate a significant improvement in mass detection capabilities, leveraging RadiomicsFill-Mammo as a strategy to generate simulated samples. Furthermore, RadiomicsFill-Mammo not only advances medical imaging research but also opens new avenues for enhancing treatment planning and tumor simulation. Our code is available at https://github.com/nainye/RadiomicsFill.
Authors: Samuel Tonks, Cuong Nguyen, Steve Hood, Ryan Musso, Ceridwen Hopely, Steve Titus, Minh Doan, Iain Styles, Alexander Krull
Abstract: The large volume and variety of imaging data from high-throughput screening (HTS) in the pharmaceutical industry present an excellent resource for training virtual staining models. However, the potential of models trained under one set of experimental conditions to generalize to other conditions remains underexplored. This study systematically investigates whether data from three cell types (lung, ovarian, and breast) and two phenotypes (toxic and non-toxic conditions) commonly found in HTS can effectively train virtual staining models to generalize across three typical HTS distribution shifts: unseen phenotypes, unseen cell types, and the combination of both. Utilizing a dataset of 772,416 paired bright-field, cytoplasm, nuclei, and DNA-damage stain images, we evaluate the generalization capabilities of models across pixel-based, instance-wise, and biological-feature-based levels. Our findings indicate that training virtual nuclei and cytoplasm models on non-toxic condition samples not only generalizes to toxic condition samples but leads to improved performance across all evaluation levels compared to training on toxic condition samples. Generalization to unseen cell types shows variability depending on the cell type; models trained on ovarian or lung cell samples often perform well under other conditions, while those trained on breast cell samples consistently show poor generalization. Generalization to unseen cell types and phenotypes shows good generalization across all levels of evaluation compared to addressing unseen cell types alone. This study represents the first large-scale, data-centric analysis of the generalization capability of virtual staining models trained on diverse HTS datasets, providing valuable strategies for experimental training data generation.
Authors: Iris Dumeur (CESBIO), Silvia Valero (CESBIO), Jordi Inglada (CESBIO)
Abstract: Although recently several foundation models for satellite remote sensing imagery have been proposed, they fail to address major challenges of real/operational applications. Indeed, embeddings that don't take into account the spectral, spatial and temporal dimensions of the data as well as the irregular or unaligned temporal sampling are of little use for most real world uses. As a consequence, we propose an ALIgned Sits Encoder (ALISE), a novel approach that leverages the spatial, spectral, and temporal dimensions of irregular and unaligned SITS while producing aligned latent representations. Unlike SSL models currently available for SITS, ALISE incorporates a flexible query mechanism to project the SITS into a common and learned temporal projection space. Additionally, thanks to a multi-view framework, we explore integration of instance discrimination along a masked autoencoding task to SITS. The quality of the produced representation is assessed through three downstream tasks: crop segmentation (PASTIS), land cover segmentation (MultiSenGE), and a novel crop change detection dataset. Furthermore, the change detection task is performed without supervision. The results suggest that the use of aligned representations is more effective than previous SSL methods for linear probing segmentation tasks.
Authors: Hyungjun Yoon, Biniyam Aschalew Tolera, Taesik Gong, Kimin Lee, Sung-Ju Lee
Abstract: Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance degradation when handling long sensor data sequences. We propose a visual prompting approach for sensor data using multimodal LLMs (MLLMs). We design a visual prompt that directs MLLMs to utilize visualized sensor data alongside the target sensory task descriptions. Additionally, we introduce a visualization generator that automates the creation of optimal visualizations tailored to a given sensory task, eliminating the need for prior task-specific knowledge. We evaluated our approach on nine sensory tasks involving four sensing modalities, achieving an average of 10% higher accuracy than text-based prompts and reducing token costs by 15.8 times. Our findings highlight the effectiveness and cost-efficiency of visual prompts with MLLMs for various sensory tasks. The source code is available at https://github.com/diamond264/ByMyEyes.
Authors: Zhaoqing Chen, Jiawei Sun, Xinyi Ye, Bin Zhao, Xuelong Li, Juergen Czarske
Abstract: Lensless fiber endomicroscope is an emerging tool for in-vivo microscopic imaging, where quantitative phase imaging (QPI) can be utilized as a label-free method to enhance image contrast. However, existing single-shot phase reconstruction methods through lensless fiber endomicroscope typically perform well on simple images but struggle with complex microscopic structures. Here, we propose a speckle-conditioned diffusion model (SpecDiffusion), which reconstructs phase images directly from speckles captured at the detection side of a multi-core fiber (MCF). Unlike conventional neural networks, SpecDiffusion employs iterative phase denoising steps for speckle-driven phase reconstruction. The iteration scheme allows SpecDiffusion to break down the phase reconstruction process into multiple steps, gradually building up to the final phase image. This attribute alleviates the computation challenge at each step and enables the reconstruction of rich details in complex microscopic images. To validate its efficacy, we build an optical system to capture speckles from MCF and construct a dataset consisting of 100,000 paired images. SpecDiffusion provides high-fidelity phase reconstruction results and shows powerful generalization capacity for unseen objects, such as test charts and biological tissues, reducing the average mean absolute error of the reconstructed tissue images by 7 times. Furthermore, the reconstructed tissue images using SpecDiffusion shows higher accuracy in zero-shot cell segmentation tasks compared to the conventional method, demonstrating the potential for further cell morphology analysis through the learning-based lensless fiber endomicroscope. SpecDiffusion offers a precise and generalized method to phase reconstruction through scattering media, including MCFs, opening new perspective in lensless fiber endomicroscopic imaging.
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 284 datasets across 38 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 53.96%, 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.
Authors: Rohit Jena, Deeksha Sethi, Pratik Chaudhari, James C. Gee
Abstract: Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. Finally, we propose a general recipe to choose the best paradigm for a given registration problem, based on these observations.
Authors: Ashesh Ashesh, Joran Deschamps, Florian Jug
Abstract: Microscopy is routinely used to image biological structures of interest. Due to imaging constraints, acquired images, also called as micrographs, are typically low-SNR and contain noise. Over the last few years, regression-based tasks like unsupervised denoising and splitting have found utility in working with such noisy micrographs. For evaluation, Structural Similarity (SSIM) is one of the most popular measures used in the field. For such tasks, the best evaluation would be when both low-SNR noisy images and corresponding high-SNR clean images are obtained directly from a microscope. However, due to the following three peculiar properties of the microscopy data, we observe that SSIM is not well suited to this data regime: (a) high-SNR micrographs have higher intensity pixels as compared to low-SNR micrographs, (b) high-SNR micrographs have higher intensity pixels than found in natural images, images for which SSIM was developed, and (c) a digitally configurable offset is added by the detector present inside the microscope which affects the SSIM value. We show that SSIM components behave unexpectedly when the prediction generated from low-SNR input is compared with the corresponding high-SNR data. We explain this by introducing the phenomenon of saturation, where SSIM components become less sensitive to (dis)similarity between the images. We propose an intuitive way to quantify this, which explains the observed SSIM behavior. We introduce MicroSSIM, a variant of SSIM, which overcomes the above-discussed issues. We justify the soundness and utility of MicroSSIM using theoretical and empirical arguments and show the utility of MicroSSIM on two tasks: unsupervised denoising and joint image splitting with unsupervised denoising. Since our formulation can be applied to a broad family of SSIM-based measures, we also introduce MicroMS3IM, a microscopy-specific variation of MS-SSIM.
Authors: Theo Di Piazza
Abstract: The rapid increase of computed tomography (CT) scans and their time-consuming manual analysis have created an urgent need for robust automated analysis techniques in clinical settings. These aim to assist radiologists and help them managing their growing workload. Existing methods typically generate entire reports directly from 3D CT images, without explicitly focusing on observed abnormalities. This unguided approach often results in repetitive content or incomplete reports, failing to prioritize anomaly-specific descriptions. We propose a new anomaly-guided report generation model, which first predicts abnormalities and then generates targeted descriptions for each. Evaluation on a public dataset demonstrates significant improvements in report quality and clinical relevance. We extend our work by conducting an ablation study to demonstrate its effectiveness.
Authors: Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun, David Held, George Kantor, Abhisesh Silwal
Abstract: Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a critical challenge in robotics due to the significant domain shift between synthetic and real-world visual data. In this paper, we propose SplatSim, a novel framework that leverages Gaussian Splatting as the primary rendering primitive to reduce the Sim2Real gap for RGB-based manipulation policies. By replacing traditional mesh representations with Gaussian Splats in simulators, SplatSim produces highly photorealistic synthetic data while maintaining the scalability and cost-efficiency of simulation. We demonstrate the effectiveness of our framework by training manipulation policies within SplatSim and deploying them in the real world in a zero-shot manner, achieving an average success rate of 86.25%, compared to 97.5% for policies trained on real-world data. Videos can be found on our project page: https://splatsim.github.io
Authors: Pengzhou Cai, Xueyuan Zhang, Libin Lan, Ze Zhao
Abstract: In recent years, significant progress has been made in tumor segmentation within the field of digital pathology. However, variations in organs, tissue preparation methods, and image acquisition processes can lead to domain discrepancies among digital pathology images. To address this problem, in this paper, we use Rein, a fine-tuning method, to parametrically and efficiently fine-tune various vision foundation models (VFMs) for MICCAI 2024 Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS2024). The core of Rein consists of a set of learnable tokens, which are directly linked to instances, improving functionality at the instance level in each layer. In the data environment of the COSAS2024 Challenge, extensive experiments demonstrate that Rein fine-tuned the VFMs to achieve satisfactory results. Specifically, we used Rein to fine-tune ConvNeXt and DINOv2. Our team used the former to achieve scores of 0.7719 and 0.7557 on the preliminary test phase and final test phase in task1, respectively, while the latter achieved scores of 0.8848 and 0.8192 on the preliminary test phase and final test phase in task2. Code is available at GitHub.
Authors: Chuang Chen, Xiao Sun, Zhi Liu
Abstract: Visual emotion analysis holds significant research value in both computer vision and psychology. However, existing methods for visual emotion analysis suffer from limited generalizability due to the ambiguity of emotion perception and the diversity of data scenarios. To tackle this issue, we introduce UniEmoX, a cross-modal semantic-guided large-scale pretraining framework. Inspired by psychological research emphasizing the inseparability of the emotional exploration process from the interaction between individuals and their environment, UniEmoX integrates scene-centric and person-centric low-level image spatial structural information, aiming to derive more nuanced and discriminative emotional representations. By exploiting the similarity between paired and unpaired image-text samples, UniEmoX distills rich semantic knowledge from the CLIP model to enhance emotional embedding representations more effectively. To the best of our knowledge, this is the first large-scale pretraining framework that integrates psychological theories with contemporary contrastive learning and masked image modeling techniques for emotion analysis across diverse scenarios. Additionally, we develop a visual emotional dataset titled Emo8. Emo8 samples cover a range of domains, including cartoon, natural, realistic, science fiction and advertising cover styles, covering nearly all common emotional scenes. Comprehensive experiments conducted on six benchmark datasets across two downstream tasks validate the effectiveness of UniEmoX. The source code is available at https://github.com/chincharles/u-emo.