Authors: Weixi Feng, Chao Liu, Sifei Liu, William Yang Wang, Arash Vahdat, Weili Nie
Abstract: Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual primitives - blob video representation, a general representation for controllable video generation. Based on blob conditions, we develop a blob-grounded video diffusion model named BlobGEN-Vid that allows users to control object motions and fine-grained object appearance. In particular, we introduce a masked 3D attention module that effectively improves regional consistency across frames. In addition, we introduce a learnable module to interpolate text embeddings so that users can control semantics in specific frames and obtain smooth object transitions. We show that our framework is model-agnostic and build BlobGEN-Vid based on both U-Net and DiT-based video diffusion models. Extensive experimental results show that BlobGEN-Vid achieves superior zero-shot video generation ability and state-of-the-art layout controllability on multiple benchmarks. When combined with an LLM for layout planning, our framework even outperforms proprietary text-to-video generators in terms of compositional accuracy.
Authors: Jiahui Kang, Qing Cai, Runqing Tan, Yimei Liu, Zhi Liu
Abstract: Guided depth super-resolution (GDSR) has demonstrated impressive performance across a wide range of domains, with numerous methods being proposed. However, existing methods often treat depth maps as images, where shading values are computed discretely, making them struggle to effectively restore the continuity inherent in the depth map. In this paper, we propose a novel approach that maximizes the utilization of spatial characteristics in depth, coupled with human abstract perception of real-world substance, by transforming the GDSR issue into deformation of a roughcast with ideal plasticity, which can be deformed by force like a continuous object. Specifically, we firstly designed a cross-modal operation, Continuity-constrained Asymmetrical Pixelwise Operation (CAPO), which can mimic the process of deforming an isovolumetrically flexible object through external forces. Utilizing CAPO as the fundamental component, we develop the Pixelwise Cross Gradient Deformation (PCGD), which is capable of emulating operations on ideal plastic objects (without volume constraint). Notably, our approach demonstrates state-of-the-art performance across four widely adopted benchmarks for GDSR, with significant advantages in large-scale tasks and generalizability.
Authors: Jiajia Xie, Sheng Zhang, Beihao Xia, Zhu Xiao, Hongbo Jiang, Siwang Zhou, Zheng Qin, Hongyang Chen
Abstract: Pedestrian trajectory prediction is a critical technology in the evolution of self-driving cars toward complete artificial intelligence. Over recent years, focusing on the trajectories of pedestrians to model their social interactions has surged with great interest in more accurate trajectory predictions. However, existing methods for modeling pedestrian social interactions rely on pre-defined rules, struggling to capture non-explicit social interactions. In this work, we propose a novel framework named DTGAN, which extends the application of Generative Adversarial Networks (GANs) to graph sequence data, with the primary objective of automatically capturing implicit social interactions and achieving precise predictions of pedestrian trajectory. DTGAN innovatively incorporates random weights within each graph to eliminate the need for pre-defined interaction rules. We further enhance the performance of DTGAN by exploring diverse task loss functions during adversarial training, which yields improvements of 16.7\% and 39.3\% on metrics ADE and FDE, respectively. The effectiveness and accuracy of our framework are verified on two public datasets. The experimental results show that our proposed DTGAN achieves superior performance and is well able to understand pedestrians' intentions.
Authors: Reza Jalayer, Yuxin Chen, Masoud Jalayer, Carlotta Orsenigo, Masayoshi Tomizuka
Abstract: Reliable detection and segmentation of human hands are critical for enhancing safety and facilitating advanced interactions in human-robot collaboration. Current research predominantly evaluates hand segmentation under in-distribution (ID) data, which reflects the training data of deep learning (DL) models. However, this approach fails to address out-of-distribution (OOD) scenarios that often arise in real-world human-robot interactions. In this study, we present a novel approach by evaluating the performance of pre-trained DL models under both ID data and more challenging OOD scenarios. To mimic realistic industrial scenarios, we designed a diverse dataset featuring simple and cluttered backgrounds with industrial tools, varying numbers of hands (0 to 4), and hands with and without gloves. For OOD scenarios, we incorporated unique and rare conditions such as finger-crossing gestures and motion blur from fast-moving hands, addressing both epistemic and aleatoric uncertainties. To ensure multiple point of views (PoVs), we utilized both egocentric cameras, mounted on the operator's head, and static cameras to capture RGB images of human-robot interactions. This approach allowed us to account for multiple camera perspectives while also evaluating the performance of models trained on existing egocentric datasets as well as static-camera datasets. For segmentation, we used a deep ensemble model composed of UNet and RefineNet as base learners. Performance evaluation was conducted using segmentation metrics and uncertainty quantification via predictive entropy. Results revealed that models trained on industrial datasets outperformed those trained on non-industrial datasets, highlighting the importance of context-specific training. Although all models struggled with OOD scenarios, those trained on industrial datasets demonstrated significantly better generalization.
Authors: Dongwon Kim, Ju He, Qihang Yu, Chenglin Yang, Xiaohui Shen, Suha Kwak, Liang-Chieh Chen
Abstract: Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them challenging to replicate. In this work, we introduce Text-Aware Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful image tokenizer that can utilize either discrete or continuous 1-dimensional tokens. TA-TiTok uniquely integrates textual information during the tokenizer decoding stage (i.e., de-tokenization), accelerating convergence and enhancing performance. TA-TiTok also benefits from a simplified, yet effective, one-stage training process, eliminating the need for the complex two-stage distillation used in previous 1-dimensional tokenizers. This design allows for seamless scalability to large datasets. Building on this, we introduce a family of text-to-image Masked Generative Models (MaskGen), trained exclusively on open data while achieving comparable performance to models trained on private data. We aim to release both the efficient, strong TA-TiTok tokenizers and the open-data, open-weight MaskGen models to promote broader access and democratize the field of text-to-image masked generative models.
Authors: Yaqing Ding, V\'aclav V\'avra, Viktor Kocur, Jian Yang, Torsten Sattler, Zuzana Kukelova
Abstract: Recent advances in monocular depth prediction have led to significantly improved depth prediction accuracy. In turn, this enables various applications to use such depth predictions. In this paper, we propose a novel framework for estimating the relative pose between two cameras from point correspondences with associated monocular depths. Since depth predictions are typically defined up to an unknown scale and shift parameter, our solvers jointly estimate both scale and shift parameters together with the camera pose. We derive efficient solvers for three cases: (1) two calibrated cameras, (2) two uncalibrated cameras with an unknown but shared focal length, and (3) two uncalibrated cameras with unknown and different focal lengths. Experiments on synthetic and real data, including experiments with depth maps estimated by 11 different depth predictors, show the practical viability of our solvers. Compared to prior work, our solvers achieve state-of-the-art results on two large-scale, real-world datasets. The source code is available at https://github.com/yaqding/pose_monodepth
Authors: Guanjun Wang, Lu Wang, Ning Niu, Qiaoyi Yao, Yixuan Wang, Sufen Ren, Shengchao Chen
Abstract: Sclera segmentation is crucial for developing automatic eye-related medical computer-aided diagnostic systems, as well as for personal identification and verification, because the sclera contains distinct personal features. Deep learning-based sclera segmentation has achieved significant success compared to traditional methods that rely on hand-crafted features, primarily because it can autonomously extract critical output-related features without the need to consider potential physical constraints. However, achieving accurate sclera segmentation using these methods is challenging due to the scarcity of high-quality, fully labeled datasets, which depend on costly, labor-intensive medical acquisition and expertise. To address this challenge, this paper introduces a novel sclera segmentation framework that excels with limited labeled samples. Specifically, we employ a semi-supervised learning method that integrates domain-specific improvements and image-based spatial transformations to enhance segmentation performance. Additionally, we have developed a real-world eye diagnosis dataset to enrich the evaluation process. Extensive experiments on our dataset and two additional public datasets demonstrate the effectiveness and superiority of our proposed method, especially with significantly fewer labeled samples.
Authors: Xiaoshui Huang, Zhou Huang, Yifan Zuo, Yongshun Gong, Chengdong Zhang, Deyang Liu, Yuming Fang
Abstract: The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distinguishing the ambiguous structures in the overlapping regions. Therefore, the ambiguous features they extracted resulted in a significant number of outlier matches from overlapping regions. To solve this problem, we propose a prior-guided SMoE-based registration method to improve the feature distinctiveness by dispatching the potential correspondences to the same experts. Specifically, we propose a prior-guided SMoE module by fusing prior overlap and potential correspondence embeddings for routing, assigning tokens to the most suitable experts for processing. In addition, we propose a registration framework by a specific combination of Transformer layer and prior-guided SMoE module. The proposed method not only pays attention to the importance of locating the overlapping areas of point clouds, but also commits to finding more accurate correspondences in overlapping areas. Our extensive experiments demonstrate the effectiveness of our method, achieving state-of-the-art registration recall (95.7\%/79.3\%) on the 3DMatch/3DLoMatch benchmark. Moreover, we also test the performance on ModelNet40 and demonstrate excellent performance.
Authors: Zhaokai Wang, Xizhou Zhu, Xue Yang, Gen Luo, Hao Li, Changyao Tian, Wenhan Dou, Junqi Ge, Lewei Lu, Yu Qiao, Jifeng Dai
Abstract: Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of images, leading to significant computational cost. To address this challenge, we propose a novel network architecture, called Parameter-Inverted Image Pyramid Networks (PIIP). Specifically, PIIP uses pretrained models (ViTs or CNNs) as branches to process multi-scale images, where images of higher resolutions are processed by smaller network branches to balance computational cost and performance. To integrate information from different spatial scales, we further propose a novel cross-branch feature interaction mechanism. To validate PIIP, we apply it to various perception models and a representative multimodal large language model called LLaVA, and conduct extensive experiments on various tasks such as object detection, segmentation, image classification and multimodal understanding. PIIP achieves superior performance compared to single-branch and existing multi-resolution approaches with lower computational cost. When applied to InternViT-6B, a large-scale vision foundation model, PIIP can improve its performance by 1%-2% on detection and segmentation with only 40%-60% of the original computation, finally achieving 60.0 box AP on MS COCO and 59.7 mIoU on ADE20K. For multimodal understanding, our PIIP-LLaVA achieves 73.0% accuracy on TextVQA and 74.5% on MMBench with only 2.8M training data. Our code is released at https://github.com/OpenGVLab/PIIP.
Authors: Farnoosh Koleini, Muhammad Usama Saleem, Pu Wang, Hongfei Xue, Ahmed Helmy, Abbey Fenwick
Abstract: Recent advancements in 3D human pose estimation from single-camera images and videos have relied on parametric models, like SMPL. However, these models oversimplify anatomical structures, limiting their accuracy in capturing true joint locations and movements, which reduces their applicability in biomechanics, healthcare, and robotics. Biomechanically accurate pose estimation, on the other hand, typically requires costly marker-based motion capture systems and optimization techniques in specialized labs. To bridge this gap, we propose BioPose, a novel learning-based framework for predicting biomechanically accurate 3D human pose directly from monocular videos. BioPose includes three key components: a Multi-Query Human Mesh Recovery model (MQ-HMR), a Neural Inverse Kinematics (NeurIK) model, and a 2D-informed pose refinement technique. MQ-HMR leverages a multi-query deformable transformer to extract multi-scale fine-grained image features, enabling precise human mesh recovery. NeurIK treats the mesh vertices as virtual markers, applying a spatial-temporal network to regress biomechanically accurate 3D poses under anatomical constraints. To further improve 3D pose estimations, a 2D-informed refinement step optimizes the query tokens during inference by aligning the 3D structure with 2D pose observations. Experiments on benchmark datasets demonstrate that BioPose significantly outperforms state-of-the-art methods. Project website: \url{https://m-usamasaleem.github.io/publication/BioPose/BioPose.html}.
URLs: https://m-usamasaleem.github.io/publication/BioPose/BioPose.html
Authors: Yafei Qi, Chen Wang, Zhaoning Zhang, Yaping Liu, Yongmin Zhang
Abstract: Knowledge distillation has been widely adopted in computer vision task processing, since it can effectively enhance the performance of lightweight student networks by leveraging the knowledge transferred from cumbersome teacher networks. Most existing knowledge distillation methods utilize Kullback-Leibler divergence to mimic the logit output probabilities between the teacher network and the student network. Nonetheless, these methods may neglect the negative parts of the teacher's ''dark knowledge'' because the divergence calculations may ignore the effect of the minute probabilities from the teacher's logit output. This deficiency may lead to suboptimal performance in logit mimicry during the distillation process and result in an imbalance of information acquired by the student network. In this paper, we investigate the impact of this imbalance and propose a novel method, named Balance Divergence Distillation. By introducing a compensatory operation using reverse Kullback-Leibler divergence, our method can improve the modeling of the extremely small values in the negative from the teacher and preserve the learning capacity for the positive. Furthermore, we test the impact of different temperature coefficients adjustments, which may conducted to further balance for knowledge transferring. We evaluate the proposed method on several computer vision tasks, including image classification and semantic segmentation. The evaluation results show that our method achieves an accuracy improvement of 1%~3% for lightweight students on both CIFAR-100 and ImageNet dataset, and a 4.55% improvement in mIoU for PSP-ResNet18 on the Cityscapes dataset. The experiments show that our method is a simple yet highly effective solution that can be smoothly applied to different knowledge distillation methods.
Authors: Yunzhi Zhuge, Hongyu Gu, Lu Zhang, Jinqing Qi, Huchuan Lu
Abstract: In this paper, we address the challenges in unsupervised video object segmentation (UVOS) by proposing an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues. Unlike previous methods that focus solely on integrating appearance with motion or on modeling temporal relations, our method combines both aspects by integrating them within a unified framework. MTNet is devised by effectively merging appearance and motion features during the feature extraction process within encoders, promoting a more complementary representation. To capture the intricate long-range contextual dynamics and information embedded within videos, a temporal transformer module is introduced, facilitating efficacious inter-frame interactions throughout a video clip. Furthermore, we employ a cascade of decoders all feature levels across all feature levels to optimally exploit the derived features, aiming to generate increasingly precise segmentation masks. As a result, MTNet provides a strong and compact framework that explores both temporal and cross-modality knowledge to robustly localize and track the primary object accurately in various challenging scenarios efficiently. Extensive experiments across diverse benchmarks conclusively show that our method not only attains state-of-the-art performance in unsupervised video object segmentation but also delivers competitive results in video salient object detection. These findings highlight the method's robust versatility and its adeptness in adapting to a range of segmentation tasks. Source code is available on https://github.com/hy0523/MTNet.
Authors: Sitong Gong, Yunzhi Zhuge, Lu Zhang, Yifan Wang, Pingping Zhang, Lijun Wang, Huchuan Lu
Abstract: The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to quadratic computational costs, presenting a bottleneck in complex scenarios. To overcome this limitation and facilitate complex multi-modal comprehension with linear complexity, we introduce AVS-Mamba, a selective state space model to address the AVS task. Our framework incorporates two key components for video understanding and cross-modal learning: Temporal Mamba Block for sequential video processing and Vision-to-Audio Fusion Block for advanced audio-vision integration. Building on this, we develop the Multi-scale Temporal Encoder, aimed at enhancing the learning of visual features across scales, facilitating the perception of intra- and inter-frame information. To perform multi-modal fusion, we propose the Modality Aggregation Decoder, leveraging the Vision-to-Audio Fusion Block to integrate visual features into audio features across both frame and temporal levels. Further, we adopt the Contextual Integration Pyramid to perform audio-to-vision spatial-temporal context collaboration. Through these innovative contributions, our approach achieves new state-of-the-art results on the AVSBench-object and AVSBench-semantic datasets. Our source code and model weights are available at AVS-Mamba.
Authors: Haomiao Xiong, Yunzhi Zhuge, Jiawen Zhu, Lu Zhang, Huchuan Lu
Abstract: Multi-modal Large Language Models (MLLMs) exhibit impressive capabilities in 2D tasks, yet encounter challenges in discerning the spatial positions, interrelations, and causal logic in scenes when transitioning from 2D to 3D representations. We find that the limitations mainly lie in: i) the high annotation cost restricting the scale-up of volumes of 3D scene data, and ii) the lack of a straightforward and effective way to perceive 3D information which results in prolonged training durations and complicates the streamlined framework. To this end, we develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs and construct 3DS-160K , to enhance the pre-training process. Leveraging this high-quality pre-training data, we introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes, showcasing exceptional capability in navigating the complexities of the physical world. 3UR-LLM directly receives 3D point cloud as input and project 3D features fused with text instructions into a manageable set of tokens. Considering the computation burden derived from these hybrid tokens, we design a 3D compressor module to cohesively compress the 3D spatial cues and textual narrative. 3UR-LLM achieves promising performance with respect to the previous SOTAs, for instance, 3UR-LLM exceeds its counterparts by 7.1\% CIDEr on ScanQA, while utilizing fewer training resources. The code and model weights for 3UR-LLM and the 3DS-160K benchmark are available at 3UR-LLM.
Authors: Debasish Dutta, Deepjyoti Chetia, Neeharika Sonowal, Sanjib Kr Kalita
Abstract: Image Super-Resolution (SR) aims to recover a high-resolution image from its low-resolution counterpart, which has been affected by a specific degradation process. This is achieved by enhancing detail and visual quality. Recent advancements in transformer-based methods have remolded image super-resolution by enabling high-quality reconstructions surpassing previous deep-learning approaches like CNN and GAN-based. This effectively addresses the limitations of previous methods, such as limited receptive fields, poor global context capture, and challenges in high-frequency detail recovery. Additionally, the paper reviews recent trends and advancements in transformer-based SR models, exploring various innovative techniques and architectures that combine transformers with traditional networks to balance global and local contexts. These neoteric methods are critically analyzed, revealing promising yet unexplored gaps and potential directions for future research. Several visualizations of models and techniques are included to foster a holistic understanding of recent trends. This work seeks to offer a structured roadmap for researchers at the forefront of deep learning, specifically exploring the impact of transformers on super-resolution techniques.
Authors: Andrew Keith Wilkinson
Abstract: deepTerra is a comprehensive platform designed to facilitate the classification of land surface features using machine learning and satellite imagery. The platform includes modules for data collection, image augmentation, training, testing, and prediction, streamlining the entire workflow for image classification tasks. This paper presents a detailed overview of the capabilities of deepTerra, shows how it has been applied to various research areas, and discusses the future directions it might take.
Authors: Lin Liu, Yutong Wang, Jiahao Chen, Jianfang Li, Tangli Xue, Longlong Li, Jianqiang Ren, Liefeng Bo
Abstract: This report introduces Make-A-Character 2, an advanced system for generating high-quality 3D characters from single portrait photographs, ideal for game development and digital human applications. Make-A-Character 2 builds upon its predecessor by incorporating several significant improvements for image-based head generation. We utilize the IC-Light method to correct non-ideal illumination in input photos and apply neural network-based color correction to harmonize skin tones between the photos and game engine renders. We also employ the Hierarchical Representation Network to capture high-frequency facial structures and conduct adaptive skeleton calibration for accurate and expressive facial animations. The entire image-to-3D-character generation process takes less than 2 minutes. Furthermore, we leverage transformer architecture to generate co-speech facial and gesture actions, enabling real-time conversation with the generated character. These technologies have been integrated into our conversational AI avatar products.
Authors: Liping Yuan, Jiawei Wang, Haomiao Sun, Yuchen Zhang, Yuan Lin
Abstract: We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves significant advancements through three key upgrades: (1) Scaling pre-training data from 11M to 40M video-text pairs, enriching both volume and diversity; (2) Performing fine-grained temporal alignment during supervised fine-tuning; (3) Using model-based sampling to automatically construct preference data and applying DPO training for optimization. Extensive experiments show that Tarsier2-7B consistently outperforms leading proprietary models, including GPT-4o and Gemini 1.5 Pro, in detailed video description tasks. On the DREAM-1K benchmark, Tarsier2-7B improves F1 by 2.8\% over GPT-4o and 5.8\% over Gemini-1.5-Pro. In human side-by-side evaluations, Tarsier2-7B shows a +8.6\% performance advantage over GPT-4o and +24.9\% over Gemini-1.5-Pro. Tarsier2-7B also sets new state-of-the-art results across 15 public benchmarks, spanning tasks such as video question-answering, video grounding, hallucination test, and embodied question-answering, demonstrating its versatility as a robust generalist vision-language model.
Authors: Wassim Kabbani, Kiran Raja, Raghavendra Ramachandra, Christoph Busch
Abstract: Face image quality assessment (FIQA) algorithms are being integrated into online identity management applications. These applications allow users to upload a face image as part of their document issuance process, where the image is then run through a quality assessment process to make sure it meets the quality and compliance requirements. Concerns about demographic bias have been raised about biometric systems, given the societal implications this may cause. It is therefore important that demographic variability in FIQA algorithms is assessed such that mitigation measures can be created. In this work, we study the demographic variability of all face image quality measures included in the ISO/IEC 29794-5 international standard across three demographic variables: age, gender, and skin tone. The results are rather promising and show no clear bias toward any specific demographic group for most measures. Only two quality measures are found to have considerable variations in their outcomes for different groups on the skin tone variable.
Authors: Yuxi Wang, Wenjuan Zhang, Bing Zhang
Abstract: Optical remote sensing images play a crucial role in the observation of the Earth's surface. However, obtaining complete optical remote sensing images is challenging due to cloud cover. Reconstructing cloud-free optical images has become a major task in recent years. This paper presents a two-flow Polarimetric Synthetic Aperture Radar (PolSAR)-Optical data fusion cloud removal algorithm (PODF-CR), which achieves the reconstruction of missing optical images. PODF-CR consists of an encoding module and a decoding module. The encoding module includes two parallel branches that extract PolSAR image features and optical image features. To address speckle noise in PolSAR images, we introduce dynamic filters in the PolSAR branch for image denoising. To better facilitate the fusion between multimodal optical images and PolSAR images, we propose fusion blocks based on cross-skip connections to enable interaction of multimodal data information. The obtained fusion features are refined through an attention mechanism to provide better conditions for the subsequent decoding of the fused images. In the decoding module, multi-scale convolution is introduced to obtain multi-scale information. Additionally, to better utilize comprehensive scattering information and polarization characteristics to assist in the restoration of optical images, we use a dataset for cloud restoration called OPT-BCFSAR-PFSAR, which includes backscatter coefficient feature images and polarization feature images obtained from PoLSAR data and optical images. Experimental results demonstrate that this method outperforms existing methods in both qualitative and quantitative evaluations.
Authors: Hui Kuurila-Zhang, Haoyu Chen, Guoying Zhao
Abstract: Adversarial attacks have proven effective in deceiving machine learning models by subtly altering input images, motivating extensive research in recent years. Traditional methods constrain perturbations within $l_p$-norm bounds, but advancements in Unrestricted Adversarial Examples (UAEs) allow for more complex, generative-model-based manipulations. Diffusion models now lead UAE generation due to superior stability and image quality over GANs. However, existing diffusion-based UAE methods are limited to using reference images and face challenges in generating Natural Adversarial Examples (NAEs) directly from random noise, often producing uncontrolled or distorted outputs. In this work, we introduce VENOM, the first text-driven framework for high-quality unrestricted adversarial examples generation through diffusion models. VENOM unifies image content generation and adversarial synthesis into a single reverse diffusion process, enabling high-fidelity adversarial examples without sacrificing attack success rate (ASR). To stabilize this process, we incorporate an adaptive adversarial guidance strategy with momentum, ensuring that the generated adversarial examples $x^*$ align with the distribution $p(x)$ of natural images. Extensive experiments demonstrate that VENOM achieves superior ASR and image quality compared to prior methods, marking a significant advancement in adversarial example generation and providing insights into model vulnerabilities for improved defense development.
Authors: Chia-Ming Lee, Yu-Fan Lin, Li-Wei Kang, Chih-Chung Hsu
Abstract: High-resolution hyperspectral imaging plays a crucial role in various remote sensing applications, yet its acquisition often faces fundamental limitations due to hardware constraints. This paper introduces S$^{3}$RNet, a novel framework for hyperspectral image pansharpening that effectively combines low-resolution hyperspectral images (LRHSI) with high-resolution multispectral images (HRMSI) through sparse spatial-spectral representation. The core of S$^{3}$RNet is the Multi-Branch Fusion Network (MBFN), which employs parallel branches to capture complementary features at different spatial and spectral scales. Unlike traditional approaches that treat all features equally, our Spatial-Spectral Attention Weight Block (SSAWB) dynamically adjusts feature weights to maintain sparse representation while suppressing noise and redundancy. To enhance feature propagation, we incorporate the Dense Feature Aggregation Block (DFAB), which efficiently aggregates inputted features through dense connectivity patterns. This integrated design enables S$^{3}$RNet to selectively emphasize the most informative features from differnt scale while maintaining computational efficiency. Comprehensive experiments demonstrate that S$^{3}$RNet achieves state-of-the-art performance across multiple evaluation metrics, showing particular strength in maintaining high reconstruction quality even under challenging noise conditions. The code will be made publicly available.
Authors: Robin Sch\"on, Julian Lorenz, Daniel Kienzle, Rainer Lienhart
Abstract: In this paper, we present a novel architecture for interactive segmentation in winter sports contexts. The field of interactive segmentation deals with the prediction of high-quality segmentation masks by informing the network about the objects position with the help of user guidance. In our case the guidance consists of click prompts. For this task, we first present a baseline architecture which is specifically geared towards quickly responding after each click. Afterwards, we motivate and describe a number of architectural modifications which improve the performance when tasked with segmenting winter sports equipment on the WSESeg dataset. With regards to the average NoC@85 metric on the WSESeg classes, we outperform SAM and HQ-SAM by 2.336 and 7.946 clicks, respectively. When applied to the HQSeg-44k dataset, our system delivers state-of-the-art results with a NoC@90 of 6.00 and NoC@95 of 9.89. In addition to that, we test our model on a novel dataset containing masks for humans during skiing.
Authors: Jiaxing Zhao, Boyuan Sun, Xiang Chen, Xihan Wei
Abstract: Facial expression captioning has found widespread application across various domains. Recently, the emergence of video Multimodal Large Language Models (MLLMs) has shown promise in general video understanding tasks. However, describing facial expressions within videos poses two major challenges for these models: (1) the lack of adequate datasets and benchmarks, and (2) the limited visual token capacity of video MLLMs. To address these issues, this paper introduces a new instruction-following dataset tailored for dynamic facial expression caption. The dataset comprises 5,033 high-quality video clips annotated manually, containing over 700,000 tokens. Its purpose is to improve the capability of video MLLMs to discern subtle facial nuances. Furthermore, we propose FaceTrack-MM, which leverages a limited number of tokens to encode the main character's face. This model demonstrates superior performance in tracking faces and focusing on the facial expressions of the main characters, even in intricate multi-person scenarios. Additionally, we introduce a novel evaluation metric combining event extraction, relation classification, and the longest common subsequence (LCS) algorithm to assess the content consistency and temporal sequence consistency of generated text. Moreover, we present FEC-Bench, a benchmark designed to assess the performance of existing video MLLMs in this specific task. All data and source code will be made publicly available.
Authors: Pooja Guhan, Tsung-Wei Huang, Guan-Ming Su, Subhadra Gopalakrishnan, Dinesh Manocha
Abstract: We introduce V-Trans4Style, an innovative algorithm tailored for dynamic video content editing needs. It is designed to adapt videos to different production styles like documentaries, dramas, feature films, or a specific YouTube channel's video-making technique. Our algorithm recommends optimal visual transitions to help achieve this flexibility using a more bottom-up approach. We first employ a transformer-based encoder-decoder network to learn recommending temporally consistent and visually seamless sequences of visual transitions using only the input videos. We then introduce a style conditioning module that leverages this model to iteratively adjust the visual transitions obtained from the decoder through activation maximization. We demonstrate the efficacy of our method through experiments conducted on our newly introduced AutoTransition++ dataset. It is a 6k video version of AutoTransition Dataset that additionally categorizes its videos into different production style categories. Our encoder-decoder model outperforms the state-of-the-art transition recommendation method, achieving improvements of 10% to 80% in Recall@K and mean rank values over baseline. Our style conditioning module results in visual transitions that improve the capture of the desired video production style characteristics by an average of around 12% in comparison to other methods when measured with similarity metrics. We hope that our work serves as a foundation for exploring and understanding video production styles further.
Authors: Wei Long, Yongjun Zhang, Zhongwei Cui, Yujie Xu, Xuexue Zhang
Abstract: Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an effective approach for designing segmentation networks that can capture long-range pixel dependencies. SA enables the network to model the global dependencies between the input features, resulting in improved segmentation outcomes. However, the high density of attentional feature maps used in this mechanism causes exponential increases in computational complexity. Additionally, it introduces redundant information that negatively impacts the feature representation. Inspired by traditional threshold segmentation algorithms, we propose a novel threshold attention mechanism (TAM). This mechanism significantly reduces computational effort while also better modeling the correlation between different regions of the feature map. Based on TAM, we present a threshold attention network (TANet) for semantic segmentation. TANet consists of an attentional feature enhancement module (AFEM) for global feature enhancement of shallow features and a threshold attention pyramid pooling module (TAPP) for acquiring feature information at different scales for deep features. We have conducted extensive experiments on the ISPRS Vaihingen and Potsdam datasets. The results demonstrate the validity and superiority of our proposed TANet compared to the most state-of-the-art models.
Authors: Kuang Zhu, Xingli Gan, Min Sun
Abstract: Depth completion is a key task in autonomous driving, aiming to complete sparse LiDAR depth measurements into high-quality dense depth maps through image guidance. However, existing methods usually treat depth maps as an additional channel of color images, or directly perform convolution on sparse data, failing to fully exploit the 3D geometric information in depth maps, especially with limited performance in complex boundaries and sparse areas. To address these issues, this paper proposes a depth completion network combining channel attention mechanism and 3D global feature perception (CGA-Net). The main innovations include: 1) Utilizing PointNet++ to extract global 3D geometric features from sparse depth maps, enhancing the scene perception ability of low-line LiDAR data; 2) Designing a channel-attention-based multimodal feature fusion module to efficiently integrate sparse depth, RGB images, and 3D geometric features; 3) Combining residual learning with CSPN++ to optimize the depth refinement stage, further improving the completion quality in edge areas and complex scenes. Experiments on the KITTI depth completion dataset show that CGA-Net can significantly improve the prediction accuracy of dense depth maps, achieving a new state-of-the-art (SOTA), and demonstrating strong robustness to sparse and complex scenes.
Authors: Nairouz Shehata, Carolina Pi\c{c}arra, Ben Glocker
Abstract: We investigate combining imaging and shape features extracted from MRI for the clinically relevant tasks of brain age prediction and Alzheimer's disease classification. Our proposed model fuses ResNet-extracted image embeddings with shape embeddings from a bespoke graph neural network. The shape embeddings are derived from surface meshes of 15 brain structures, capturing detailed geometric information. Combined with the appearance features from T1-weighted images, we observe improvements in the prediction performance on both tasks, with substantial gains for classification. We evaluate the model using public datasets, including CamCAN, IXI, and OASIS3, demonstrating the effectiveness of fusing imaging and shape features for brain analysis.
Authors: Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondrag\'on, Peter H. N. de With, Fons van der Sommen
Abstract: Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code will be made publicly available
Authors: Feng Zhang, Ze Li, Xiatian Zhu, Lei Chen
Abstract: As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.
Authors: Alvaro Pastor-Naranjo, Pablo Meseguer, Roc\'io del Amor, Jose Antonio Lopez-Guerrero, Samuel Navarro, Katia Scotlandi, Antonio Llombart-Bosch, Isidro Machado, Valery Naranjo
Abstract: Ewing's sarcoma (ES), characterized by a high density of small round blue cells without structural organization, presents a significant health concern, particularly among adolescents aged 10 to 19. Artificial intelligence-based systems for automated analysis of histopathological images are promising to contribute to an accurate diagnosis of ES. In this context, this study explores the feature extraction ability of different pre-training strategies for distinguishing ES from other soft tissue or bone sarcomas with similar morphology in digitized tissue microarrays for the first time, as far as we know. Vision-language supervision (VLS) is compared to fully-supervised ImageNet pre-training within a multiple instance learning paradigm. Our findings indicate a substantial improvement in diagnostic accuracy with the adaption of VLS using an in-domain dataset. Notably, these models not only enhance the accuracy of predicted classes but also drastically reduce the number of trainable parameters and computational costs.
Authors: Mobai Xue, Jun Du, Zhenrong Zhang, Jiefeng Ma, Qikai Chang, Pengfei Hu, Jianshu Zhang, Yu Hu
Abstract: Automatic font generation remains a challenging research issue, primarily due to the vast number of Chinese characters, each with unique and intricate structures. Our investigation of previous studies reveals inherent bias capable of causing structural changes in characters. Specifically, when generating a Chinese character similar to, but different from, those in the training samples, the bias is prone to either correcting or ignoring these subtle variations. To address this concern, we propose a novel Skeleton and Font Generation Network (SFGN) to achieve a more robust Chinese character font generation. Our approach includes a skeleton builder and font generator. The skeleton builder synthesizes content features using low-resource text input, enabling our technique to realize font generation independently of content image inputs. Unlike previous font generation methods that treat font style as a global embedding, we introduce a font generator to align content and style features on the radical level, which is a brand-new perspective for font generation. Except for common characters, we also conduct experiments on misspelled characters, a substantial portion of which slightly differs from the common ones. Our approach visually demonstrates the efficacy of generated images and outperforms current state-of-the-art font generation methods. Moreover, we believe that misspelled character generation have significant pedagogical implications and verify such supposition through experiments. We used generated misspelled characters as data augmentation in Chinese character error correction tasks, simulating the scenario where students learn handwritten Chinese characters with the help of misspelled characters. The significantly improved performance of error correction tasks demonstrates the effectiveness of our proposed approach and the value of misspelled character generation.
Authors: Yuhang Zhang, Joshua Maraval, Zhengyu Zhang, Nicolas Ramin, Shishun Tian, Lu Zhang
Abstract: Gaussian Splatting (GS) and Neural Radiance Fields (NeRF) are two groundbreaking technologies that have revolutionized the field of Novel View Synthesis (NVS), enabling immersive photorealistic rendering and user experiences by synthesizing multiple viewpoints from a set of images of sparse views. The potential applications of NVS, such as high-quality virtual and augmented reality, detailed 3D modeling, and realistic medical organ imaging, underscore the importance of quality assessment of NVS methods from the perspective of human perception. Although some previous studies have explored subjective quality assessments for NVS technology, they still face several challenges, especially in NVS methods selection, scenario coverage, and evaluation methodology. To address these challenges, we conducted two subjective experiments for the quality assessment of NVS technologies containing both GS-based and NeRF-based methods, focusing on dynamic and real-world scenes. This study covers 360{\deg}, front-facing, and single-viewpoint videos while providing a richer and greater number of real scenes. Meanwhile, it's the first time to explore the impact of NVS methods in dynamic scenes with moving objects. The two types of subjective experiments help to fully comprehend the influences of different viewing paths from a human perception perspective and pave the way for future development of full-reference and no-reference quality metrics. In addition, we established a comprehensive benchmark of various state-of-the-art objective metrics on the proposed database, highlighting that existing methods still struggle to accurately capture subjective quality. The results give us some insights into the limitations of existing NVS methods and may promote the development of new NVS methods.
Authors: Nert Keser, Halil Ibrahim Orhan, Niki Amini-Naieni, Gesina Schwalbe, Alois Knoll, Matthias Rottmann
Abstract: Deep neural networks (DNNs) remain challenged by distribution shifts in complex open-world domains like automated driving (AD): Absolute robustness against yet unknown novel objects (semantic shift) or styles like lighting conditions (covariate shift) cannot be guaranteed. Hence, reliable operation-time monitors for identification of out-of-training-data-distribution (OOD) scenarios are imperative. Current approaches for OOD classification are untested for complex domains like AD, are limited in the kinds of shifts they detect, or even require supervision with OOD samples. To prepare for unanticipated shifts, we instead establish a framework around a principled, unsupervised, and model-agnostic method that unifies detection of all kinds of shifts: Find a full model of the training data's feature distribution, to then use its density at new points as in-distribution (ID) score. To implement this, we propose to combine the newly available Vision Foundation Models (VFM) as feature extractors with one of four alternative density modeling techniques. In an extensive benchmark of 4 VFMs against 20 baselines, we show the superior performance of VFM feature encodings compared to shift-specific OOD monitors. Additionally, we find that sophisticated architectures outperform larger latent space dimensionality; and our method identifies samples with higher risk of errors on downstream tasks, despite being model-agnostic. This suggests that VFMs are promising to realize model-agnostic, unsupervised, reliable safety monitors in complex vision tasks.
Authors: Feng Zhang, Jinwei Liu, Xiatian Zhu, Lei Chen
Abstract: Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.
Authors: E. Sarfati, A. B\^one, M-M. Roh\'e, C. Aub\'e, M. Ronot, P. Gori, I. Bloch
Abstract: Hepatocellular carcinoma is the most spread primary liver cancer across the world ($\sim$80\% of the liver tumors). The gold standard for HCC diagnosis is liver biopsy. However, in the clinical routine, expert radiologists provide a visual diagnosis by interpreting hepatic CT-scans according to a standardized protocol, the LI-RADS, which uses five radiological criteria with an associated decision tree. In this paper, we propose an automatic approach to predict histology-proven HCC from CT images in order to reduce radiologists' inter-variability. We first show that standard deep learning methods fail to accurately predict HCC from CT-scans on a challenging database, and propose a two-step approach inspired by the LI-RADS system to improve the performance. We achieve improvements from 6 to 18 points of AUC with respect to deep learning baselines trained with different architectures. We also provide clinical validation of our method, achieving results that outperform non-expert radiologists and are on par with expert ones.
Authors: Diego Velazquez, Pau Rodriguez L\'opez, Sergio Alonso, Josep M. Gonfaus, Jordi Gonzalez, Gerardo Richarte, Javier Marin, Yoshua Bengio, Alexandre Lacoste
Abstract: This paper presents EarthView, a comprehensive dataset specifically designed for self-supervision on remote sensing data, intended to enhance deep learning applications on Earth monitoring tasks. The dataset spans 15 tera pixels of global remote-sensing data, combining imagery from a diverse range of sources, including NEON, Sentinel, and a novel release of 1m spatial resolution data from Satellogic. Our dataset provides a wide spectrum of image data with varying resolutions, harnessed from different sensors and organized coherently into an accessible HuggingFace dataset in parquet format. This data spans five years, from 2017 to 2022. Accompanying the dataset, we introduce EarthMAE, a tailored Masked Autoencoder, developed to tackle the distinct challenges of remote sensing data. Trained in a self-supervised fashion, EarthMAE effectively processes different data modalities such as hyperspectral, multispectral, topographical data, segmentation maps, and temporal structure. This model helps us show that pre-training on Satellogic data improves performance on downstream tasks. While there is still a gap to fill in MAE for heterogeneous data, we regard this innovative combination of an expansive, diverse dataset and a versatile model adapted for self-supervised learning as a stride forward in deep learning for Earth monitoring.
Authors: Yuduo Wang, Weikang Yu, Pedram Ghamisi
Abstract: Change captioning has become essential for accurately describing changes in multi-temporal remote sensing data, providing an intuitive way to monitor Earth's dynamics through natural language. However, existing change captioning methods face two key challenges: high computational demands due to multistage fusion strategy, and insufficient detail in object descriptions due to limited semantic extraction from individual images. To solve these challenges, we propose SAT-Cap based on the transformers model with a single-stage feature fusion for remote sensing change captioning. In particular, SAT-Cap integrates a Spatial-Channel Attention Encoder, a Difference-Guided Fusion module, and a Caption Decoder. Compared to typical models that require multi-stage fusion in transformer encoder and fusion module, SAT-Cap uses only a simple cosine similarity-based fusion module for information integration, reducing the complexity of the model architecture. By jointly modeling spatial and channel information in Spatial-Channel Attention Encoder, our approach significantly enhances the model's ability to extract semantic information from objects in multi-temporal remote sensing images. Extensive experiments validate the effectiveness of SAT-Cap, achieving CIDEr scores of 140.23% on the LEVIR-CC dataset and 97.74% on the DUBAI-CC dataset, surpassing current state-of-the-art methods. The code and pre-trained models will be available online.
Authors: Roi Papo, Sapir Gershov, Tom Friedman, Itay Or, Gil Bolotin, Shlomi Laufer
Abstract: Hand-specific localization has garnered significant interest within the computer vision community. Although there are numerous datasets with hand annotations from various angles and settings, domain transfer techniques frequently struggle in surgical environments. This is mainly due to the limited availability of gloved hand instances and the unique challenges of operating rooms (ORs). Thus, hand-detection models tailored to OR settings require extensive training and expensive annotation processes. To overcome these challenges, we present "RoHan" - a novel approach for robust hand detection in the OR, leveraging advanced semi-supervised domain adaptation techniques to tackle the challenges of varying recording conditions, diverse glove colors, and occlusions common in surgical settings. Our methodology encompasses two main stages: (1) data augmentation strategy that utilizes "Artificial Gloves," a method for augmenting publicly available hand datasets with synthetic images of hands-wearing gloves; (2) semi-supervised domain adaptation pipeline that improves detection performance in real-world OR settings through iterative prediction refinement and efficient frame filtering. We evaluate our method using two datasets: simulated enterotomy repair and saphenous vein graft harvesting. "RoHan" substantially reduces the need for extensive labeling and model training, paving the way for the practical implementation of hand detection technologies in medical settings.
Authors: Seamie Hayes, Ganesh Sistu, Ciar\'an Eising
Abstract: Birds Eye View perception models require extensive data to perform and generalize effectively. While traditional datasets often provide abundant driving scenes from diverse locations, this is not always the case. It is crucial to maximize the utility of the available training data. With the advent of large foundation models such as DINOv2 and Metric3Dv2, a pertinent question arises: can these models be integrated into existing model architectures to not only reduce the required training data but surpass the performance of current models? We choose two model architectures in the vehicle segmentation domain to alter: Lift-Splat-Shoot, and Simple-BEV. For Lift-Splat-Shoot, we explore the implementation of frozen DINOv2 for feature extraction and Metric3Dv2 for depth estimation, where we greatly exceed the baseline results by 7.4 IoU while utilizing only half the training data and iterations. Furthermore, we introduce an innovative application of Metric3Dv2's depth information as a PseudoLiDAR point cloud incorporated into the Simple-BEV architecture, replacing traditional LiDAR. This integration results in a +3 IoU improvement compared to the Camera-only model.
Authors: Lucrezia Tosato, Flora Weissgerber, Laurent Wendling, Sylvain Lobry
Abstract: Remote sensing visual question answering (RSVQA) is a task that automatically extracts information from satellite images and processes a question to predict the answer from the images in textual form, helping with the interpretation of the image. While different methods have been proposed to extract information from optical images with different spectral bands and resolutions, no method has been proposed to answer questions from Synthetic Aperture Radar (SAR) images. SAR images capture electromagnetic information from the scene, and are less affected by atmospheric conditions, such as clouds. In this work, our objective is to introduce SAR in the RSVQA task, finding the best way to use this modality. In our research, we carry out a study on different pipelines for the task of RSVQA taking into account information from both SAR and optical data. To this purpose, we also present a dataset that allows for the introduction of SAR images in the RSVQA framework. We propose two different models to include the SAR modality. The first one is an end-to-end method in which we add an additional encoder for the SAR modality. In the second approach, we build on a two-stage framework. First, relevant information is extracted from SAR and, optionally, optical data. This information is then translated into natural language to be used in the second step which only relies on a language model to provide the answer. We find that the second pipeline allows us to obtain good results with SAR images alone. We then try various types of fusion methods to use SAR and optical images together, finding that a fusion at the decision level achieves the best results on the proposed dataset. We show that SAR data offers additional information when fused with the optical modality, particularly for questions related to specific land cover classes, such as water areas.
Authors: Marcella Astrid, Enjie Ghorbel, Djamila Aouada
Abstract: This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets, demonstrating its effectiveness in detecting audio-visual deepfakes.
Authors: Jonathan Lyhs, Lars Hinneburg, Michael Fischer, Florian \"Olsner, Stefan Milz, Jeremy Tschirner, Patrick M\"ader
Abstract: Modern machine learning techniques have shown tremendous potential, especially for object detection on camera images. For this reason, they are also used to enable safety-critical automated processes such as autonomous drone flights. We present a study on object detection for Detect and Avoid, a safety critical function for drones that detects air traffic during automated flights for safety reasons. An ill-posed problem is the generation of good and especially large data sets, since detection itself is the corner case. Most models suffer from limited ground truth in raw data, \eg recorded air traffic or frontal flight with a small aircraft. It often leads to poor and critical detection rates. We overcome this problem by using inpainting methods to bootstrap the dataset such that it explicitly contains the corner cases of the raw data. We provide an overview of inpainting methods and generative models and present an example pipeline given a small annotated dataset. We validate our method by generating a high-resolution dataset, which we make publicly available and present it to an independent object detector that was fully trained on real data.
Authors: Hanene F. Z. Brachemi Meftah, Wassim Hamidouche, Sid Ahmed Fezza, Olivier D\'eforges, Kassem Kallas
Abstract: The rise of deep learning (DL) has increased computing complexity and energy use, prompting the adoption of application specific integrated circuits (ASICs) for energy-efficient edge and mobile deployment. However, recent studies have demonstrated the vulnerability of these accelerators to energy attacks. Despite the development of various inference time energy attacks in prior research, backdoor energy attacks remain unexplored. In this paper, we design an innovative energy backdoor attack against deep neural networks (DNNs) operating on sparsity-based accelerators. Our attack is carried out in two distinct phases: backdoor injection and backdoor stealthiness. Experimental results using ResNet-18 and MobileNet-V2 models trained on CIFAR-10 and Tiny ImageNet datasets show the effectiveness of our proposed attack in increasing energy consumption on trigger samples while preserving the model's performance for clean/regular inputs. This demonstrates the vulnerability of DNNs to energy backdoor attacks. The source code of our attack is available at: https://github.com/hbrachemi/energy_backdoor.
Authors: Mazen Balat, Rewaa Awaad, Ahmed B. Zaky, Salah A. Aly
Abstract: This study introduces an integrated approach to recognizing Arabic Sign Language (ArSL) using state-of-the-art deep learning models such as MobileNetV3, ResNet50, and EfficientNet-B2. These models are further enhanced by explainable AI (XAI) techniques to boost interpretability. The ArSL2018 and RGB Arabic Alphabets Sign Language (AASL) datasets are employed, with EfficientNet-B2 achieving peak accuracies of 99.48\% and 98.99\%, respectively. Key innovations include sophisticated data augmentation methods to mitigate class imbalance, implementation of stratified 5-fold cross-validation for better generalization, and the use of Grad-CAM for clear model decision transparency. The proposed system not only sets new benchmarks in recognition accuracy but also emphasizes interpretability, making it suitable for applications in healthcare, education, and inclusive communication technologies.
Authors: Evgenii Evstafev
Abstract: This article introduces a benchmark designed to evaluate the capabilities of multimodal models in analyzing and interpreting images. The benchmark focuses on seven key visual aspects: main object, additional objects, background, detail, dominant colors, style, and viewpoint. A dataset of 14,580 images, generated from diverse text prompts, was used to assess the performance of seven leading multimodal models. These models were evaluated on their ability to accurately identify and describe each visual aspect, providing insights into their strengths and weaknesses for comprehensive image understanding. The findings of this benchmark have significant implications for the development and selection of multimodal models for various image analysis tasks.
Authors: Marcel Rogge, Didier Stricker
Abstract: Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96\% smaller and up to 71\% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.
Authors: Qian Zeng, Jie Song, Han Zheng, Hao Jiang, Mingli Song
Abstract: Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and accelerates diffusion models without retraining, but it inevitably introduces additional quantization noise, resulting in mean and variance deviations. In this work, we propose D2-DPM, a dual denoising mechanism aimed at precisely mitigating the adverse effects of quantization noise on the noise estimation network. Specifically, we first unravel the impact of quantization noise on the sampling equation into two components: the mean deviation and the variance deviation. The mean deviation alters the drift coefficient of the sampling equation, influencing the trajectory trend, while the variance deviation magnifies the diffusion coefficient, impacting the convergence of the sampling trajectory. The proposed D2-DPM is thus devised to denoise the quantization noise at each time step, and then denoise the noisy sample through the inverse diffusion iterations. Experimental results demonstrate that D2-DPM achieves superior generation quality, yielding a 1.42 lower FID than the full-precision model while achieving 3.99x compression and 11.67x bit-operation acceleration.
Authors: Steven Landgraf, Rongjun Qin, Markus Ulrich
Abstract: While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting absolute distances, poses particular challenges, as even the most advanced foundation models remain prone to critical errors. Since quantifying the uncertainty has emerged as a promising endeavor to address these limitations and enable trustworthy deployment, we fuse five different uncertainty quantification methods with the current state-of-the-art DepthAnythingV2 foundation model. To cover a wide range of metric depth domains, we evaluate their performance on four diverse datasets. Our findings identify fine-tuning with the Gaussian Negative Log-Likelihood Loss (GNLL) as a particularly promising approach, offering reliable uncertainty estimates while maintaining predictive performance and computational efficiency on par with the baseline, encompassing both training and inference time. By fusing uncertainty quantification and foundation models within the context of monocular depth estimation, this paper lays a critical foundation for future research aimed at improving not only model performance but also its explainability. Extending this critical synthesis of uncertainty quantification and foundation models into other crucial tasks, such as semantic segmentation and pose estimation, presents exciting opportunities for safer and more reliable machine vision systems.
Authors: Shuo Li, Mehrdad Yaghoobi
Abstract: Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data loss, which can significantly degrade their quality and usefulness. This paper introduces a convergent guaranteed algorithm, LRS-PnP-DIP(1-Lip), which successfully addresses the instability issue of DHP that has been reported before. The proposed algorithm extends the successful joint low-rank and sparse model to further exploit the underlying data structures beyond the conventional and sometimes restrictive unions of subspace models. A stability analysis guarantees the convergence of the proposed algorithm under mild assumptions , which is crucial for its application in real-world scenarios. Extensive experiments demonstrate that the proposed solution consistently delivers visually and quantitatively superior inpainting results, establishing state-of-the-art performance.
Authors: Yassine El Boudouri, Amine Bohi
Abstract: Facial expressions play a crucial role in human communication serving as a powerful and impactful means to express a wide range of emotions. With advancements in artificial intelligence and computer vision, deep neural networks have emerged as effective tools for facial emotion recognition. In this paper, we propose EmoNeXt, a novel deep learning framework for facial expression recognition based on an adapted ConvNeXt architecture network. We integrate a Spatial Transformer Network (STN) to focus on feature-rich regions of the face and Squeeze-and-Excitation blocks to capture channel-wise dependencies. Moreover, we introduce a self-attention regularization term, encouraging the model to generate compact feature vectors. We demonstrate the superiority of our model over existing state-of-the-art deep learning models on the FER2013 dataset regarding emotion classification accuracy.
Authors: Yabo Zhang, Xinpeng Zhou, Yihan Zeng, Hang Xu, Hui Li, Wangmeng Zuo
Abstract: Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with various physical interactions. However, these models are usually built upon text-to-image diffusion models, so necessitate (i) massive training samples and (ii) an additional reference encoder to learn real-world dynamics and visual consistency. In this paper, we reformulate this task as an image-to-video generation problem, so that inherit powerful video diffusion priors to reduce training costs and ensure temporal consistency. Specifically, we introduce FramePainter as an efficient instantiation of this formulation. Initialized with Stable Video Diffusion, it only uses a lightweight sparse control encoder to inject editing signals. Considering the limitations of temporal attention in handling large motion between two frames, we further propose matching attention to enlarge the receptive field while encouraging dense correspondence between edited and source image tokens. We highlight the effectiveness and efficiency of FramePainter across various of editing signals: it domainantly outperforms previous state-of-the-art methods with far less training data, achieving highly seamless and coherent editing of images, \eg, automatically adjust the reflection of the cup. Moreover, FramePainter also exhibits exceptional generalization in scenarios not present in real-world videos, \eg, transform the clownfish into shark-like shape. Our code will be available at https://github.com/YBYBZhang/FramePainter.
Authors: Zeineb Haouari, Jonas Weidner, Ivan Ezhov, Aswathi Varma, Daniel Rueckert, Bjoern Menze, Benedikt Wiestler
Abstract: Glioblastoma, a highly aggressive brain tumor, poses major challenges due to its poor prognosis and high morbidity rates. Partial differential equation-based models offer promising potential to enhance therapeutic outcomes by simulating patient-specific tumor behavior for improved radiotherapy planning. However, model calibration remains a bottleneck due to the high computational demands of optimization methods like Monte Carlo sampling and evolutionary algorithms. To address this, we recently introduced an approach leveraging a neural forward solver with gradient-based optimization to significantly reduce calibration time. This approach requires a highly accurate and fully differentiable forward model. We investigate multiple architectures, including (i) an enhanced TumorSurrogate, (ii) a modified nnU-Net, and (iii) a 3D Vision Transformer (ViT). The optimized TumorSurrogate achieved the best overall results, excelling in both tumor outline matching and voxel-level prediction of tumor cell concentration. It halved the MSE relative to the baseline model and achieved the highest Dice score across all tumor cell concentration thresholds. Our study demonstrates significant enhancement in forward solver performance and outlines important future research directions.
Authors: Amir Reza Takhsha, Maryam Rastgarpour, Mozhgan Naderi
Abstract: The COVID-19 pandemic has profoundly impacted billions globally. It challenges public health and healthcare systems due to its rapid spread and severe respiratory effects. An effective strategy to mitigate the COVID-19 pandemic involves integrating testing to identify infected individuals. While RT-PCR is considered the gold standard for diagnosing COVID-19, it has some limitations such as the risk of false negatives. To address this problem, this paper introduces a novel Deep Learning Diagnosis System that integrates pre-trained Deep Convolutional Neural Networks (DCNNs) within an ensemble learning framework to achieve precise identification of COVID-19 cases from Chest X-ray (CXR) images. We combine feature vectors from the final hidden layers of pre-trained DCNNs using the Choquet integral to capture interactions between different DCNNs that a linear approach cannot. We employed Sugeno-$\lambda$ measure theory to derive fuzzy measures for subsets of networks to enable aggregation. We utilized Differential Evolution to estimate fuzzy densities. We developed a TensorFlow-based layer for Choquet operation to facilitate efficient aggregation, due to the intricacies involved in aggregating feature vectors. Experimental results on the COVIDx dataset show that our ensemble model achieved 98\% accuracy in three-class classification and 99.50\% in binary classification, outperforming its components-DenseNet-201 (97\% for three-class, 98.75\% for binary), Inception-v3 (96.25\% for three-class, 98.50\% for binary), and Xception (94.50\% for three-class, 98\% for binary)-and surpassing many previous methods.
Authors: Rui Daniel, M. Rita Verdelho, Catarina Barata, Carlos Santiago
Abstract: Deep Learning for medical imaging faces challenges in adapting and generalizing to new contexts. Additionally, it often lacks sufficient labeled data for specific tasks requiring significant annotation effort. Continual Learning (CL) tackles adaptability and generalizability by enabling lifelong learning from a data stream while mitigating forgetting of previously learned knowledge. Active Learning (AL) reduces the number of required annotations for effective training. This work explores both approaches (CAL) to develop a novel framework for robust medical image analysis. Based on the automatic recognition of shifts in image characteristics, Replay-Base Architecture for Context Adaptation (RBACA) employs a CL rehearsal method to continually learn from diverse contexts, and an AL component to select the most informative instances for annotation. A novel approach to evaluate CAL methods is established using a defined metric denominated IL-Score, which allows for the simultaneous assessment of transfer learning, forgetting, and final model performance. We show that RBACA works in domain and class-incremental learning scenarios, by assessing its IL-Score on the segmentation and diagnosis of cardiac images. The results show that RBACA outperforms a baseline framework without CAL, and a state-of-the-art CAL method across various memory sizes and annotation budgets. Our code is available in https://github.com/RuiDaniel/RBACA .
Authors: Dudi Biton, Jacob Shams, Koda Satoru, Asaf Shabtai, Yuval Elovici, Ben Nassi
Abstract: The traditional learning process of patch-based adversarial attacks, conducted in the digital domain and then applied in the physical domain (e.g., via printed stickers), may suffer from reduced performance due to adversarial patches' limited transferability from the digital domain to the physical domain. Given that previous studies have considered using projectors to apply adversarial attacks, we raise the following question: can adversarial learning (i.e., patch generation) be performed entirely in the physical domain with a projector? In this work, we propose the Physical-domain Adversarial Patch Learning Augmentation (PAPLA) framework, a novel end-to-end (E2E) framework that converts adversarial learning from the digital domain to the physical domain using a projector. We evaluate PAPLA across multiple scenarios, including controlled laboratory settings and realistic outdoor environments, demonstrating its ability to ensure attack success compared to conventional digital learning-physical application (DL-PA) methods. We also analyze the impact of environmental factors, such as projection surface color, projector strength, ambient light, distance, and angle of the target object relative to the camera, on the effectiveness of projected patches. Finally, we demonstrate the feasibility of the attack against a parked car and a stop sign in a real-world outdoor environment. Our results show that under specific conditions, E2E adversarial learning in the physical domain eliminates the transferability issue and ensures evasion by object detectors. Finally, we provide insights into the challenges and opportunities of applying adversarial learning in the physical domain and explain where such an approach is more effective than using a sticker.
Authors: Sanjida Afrin Mou (Department of Mechatronics & Industrial Engineering, Chittagong University of Engineering & Technology), Tasfia Noor Chowdhury (Department of Mechanical Engineering, Chittagong University of Engineering & Technology), Adib Ibn Mannan, Sadia Nourin Mim, Lubana Tarannum, Tasrin Noman, Jamal Uddin Ahamed
Abstract: Flooding is a major natural hazard causing significant fatalities and economic losses annually, with increasing frequency due to climate change. Rapid and accurate flood detection and monitoring are crucial for mitigating these impacts. This study compares the performance of three deep learning models UNet, ResNet, and DeepLabv3 for pixelwise water segmentation to aid in flood detection, utilizing images from drones, in field observations, and social media. This study involves creating a new dataset that augments wellknown benchmark datasets with flood-specific images, enhancing the robustness of the models. The UNet, ResNet, and DeepLab v3 architectures are tested to determine their effectiveness in various environmental conditions and geographical locations, and the strengths and limitations of each model are also discussed here, providing insights into their applicability in different scenarios by predicting image segmentation masks. This fully automated approach allows these models to isolate flooded areas in images, significantly reducing processing time compared to traditional semi-automated methods. The outcome of this study is to predict segmented masks for each image effected by a flood disaster and the validation accuracy of these models. This methodology facilitates timely and continuous flood monitoring, providing vital data for emergency response teams to reduce loss of life and economic damages. It offers a significant reduction in the time required to generate flood maps, cutting down the manual processing time. Additionally, we present avenues for future research, including the integration of multimodal data sources and the development of robust deep learning architectures tailored specifically for flood detection tasks. Overall, our work contributes to the advancement of flood management strategies through innovative use of deep learning technologies.
Authors: Longtao Jiang, Zhendong Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Lei Shi, Dong Chen, Houqiang Li
Abstract: Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint the missing region. However, this approach lacks contextual information for the masked area, often resulting in unstable performance. In this work, we introduce SmartEraser, built with a new removing paradigm called Masked-Region Guidance. This paradigm retains the masked region in the input, using it as guidance for the removal process. It offers several distinct advantages: (a) it guides the model to accurately identify the object to be removed, preventing its regeneration in the output; (b) since the user mask often extends beyond the object itself, it aids in preserving the surrounding context in the final result. Leveraging this new paradigm, we present Syn4Removal, a large-scale object removal dataset, where instance segmentation data is used to copy and paste objects onto images as removal targets, with the original images serving as ground truths. Experimental results demonstrate that SmartEraser significantly outperforms existing methods, achieving superior performance in object removal, especially in complex scenes with intricate compositions.
Authors: Hongyu Li, Jinyu Chen, Ziyu Wei, Shaofei Huang, Tianrui Hui, Jialin Gao, Xiaoming Wei, Si Liu
Abstract: Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the textual coordinate special token into the visual space, simplifying the alignment of fine-grained spatial-temporal correspondences. Additionally, we design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams. Furthermore, we propose ST-Align dataset with 4.3M training samples for fine-grained spatial-temporal multimodal understanding. With ST-align, we present a progressive training pipeline that aligns the visual and textual feature through sequential coarse-to-fine stages.Additionally, we introduce an ST-Align benchmark to evaluate spatial-temporal interleaved fine-grained understanding tasks, which include Spatial-Temporal Video Grounding (STVG) , Event Localization and Captioning (ELC) and Spatial Video Grounding (SVG). LLaVA-ST achieves outstanding performance on 11 benchmarks requiring fine-grained temporal, spatial, or spatial-temporal interleaving multimodal understanding. Our code, data and benchmark will be released at Our code, data and benchmark will be released at https://github.com/appletea233/LLaVA-ST .
Authors: Yuxue Yang, Lue Fan, Zuzen Lin, Feng Wang, Zhaoxiang Zhang
Abstract: Animated video separates foreground and background elements into layers, with distinct processes for sketching, refining, coloring, and in-betweening. Existing video generation methods typically treat animation as a monolithic data domain, lacking fine-grained control over individual layers. In this paper, we introduce LayerAnimate, a novel architectural approach that enhances fine-grained control over individual animation layers within a video diffusion model, allowing users to independently manipulate foreground and background elements in distinct layers. To address the challenge of limited layer-specific data, we propose a data curation pipeline that features automated element segmentation, motion-state hierarchical merging, and motion coherence refinement. Through quantitative and qualitative comparisons, and user study, we demonstrate that LayerAnimate outperforms current methods in terms of animation quality, control precision, and usability, making it an ideal tool for both professional animators and amateur enthusiasts. This framework opens up new possibilities for layer-specific animation applications and creative flexibility. Our code is available at https://layeranimate.github.io.
Authors: Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis
Abstract: Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction that uses a unified and efficient visual sequence transformer architecture. Our approach incorporates a multimodal masked visual modeling objective and a novel masking mechanism designed for multimodal training. This allows the model to effectively integrate visible information from various modalities, improving prediction accuracy. Additionally, we propose a VAE-free hierarchical tokenization process, which reduces computational complexity, streamlines the training pipeline, and enables end-to-end training with high-resolution, multimodal inputs. We validate FUTURIST on the Cityscapes dataset, demonstrating state-of-the-art performance in future semantic segmentation for both short- and mid-term forecasting. We provide the implementation code at https://github.com/Sta8is/FUTURIST .
Authors: Shanchuan Lin, Xin Xia, Yuxi Ren, Ceyuan Yang, Xuefeng Xiao, Lu Jiang
Abstract: The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demonstrated the potential for one-step generation in the image domain, they still suffer from significant quality degradation. In this work, we propose Adversarial Post-Training (APT) against real data following diffusion pre-training for one-step video generation. To improve the training stability and quality, we introduce several improvements to the model architecture and training procedures, along with an approximated R1 regularization objective. Empirically, our experiments show that our adversarial post-trained model, Seaweed-APT, can generate 2-second, 1280x720, 24fps videos in real time using a single forward evaluation step. Additionally, our model is capable of generating 1024px images in a single step, achieving quality comparable to state-of-the-art methods.
Authors: Jiwen Yu, Yiran Qin, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu
Abstract: Generative game engines have the potential to revolutionize game development by autonomously creating new content and reducing manual workload. However, existing video-based game generation methods fail to address the critical challenge of scene generalization, limiting their applicability to existing games with fixed styles and scenes. In this paper, we present GameFactory, a framework focused on exploring scene generalization in game video generation. To enable the creation of entirely new and diverse games, we leverage pre-trained video diffusion models trained on open-domain video data. To bridge the domain gap between open-domain priors and small-scale game dataset, we propose a multi-phase training strategy that decouples game style learning from action control, preserving open-domain generalization while achieving action controllability. Using Minecraft as our data source, we release GF-Minecraft, a high-quality and diversity action-annotated video dataset for research. Furthermore, we extend our framework to enable autoregressive action-controllable game video generation, allowing the production of unlimited-length interactive game videos. Experimental results demonstrate that GameFactory effectively generates open-domain, diverse, and action-controllable game videos, representing a significant step forward in AI-driven game generation. Our dataset and project page are publicly available at \url{https://vvictoryuki.github.io/gamefactory/}.
Authors: Miran Heo, Min-Hung Chen, De-An Huang, Sifei Liu, Subhashree Radhakrishnan, Seon Joo Kim, Yu-Chiang Frank Wang, Ryo Hachiuma
Abstract: We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.
Authors: Yufei Ye, Yao Feng, Omid Taheri, Haiwen Feng, Shubham Tulsiani, Michael J. Black
Abstract: We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space. Despite the additional temporal cues, they generally underperform compared to image-based methods due to the scarcity of annotated video data. To address these issues, we repurpose a state-of-the-art image-based transformer to take in multiple frames and directly predict a coherent trajectory. We introduce two types of lightweight attention layers: cross-view self-attention to fuse temporal information, and global cross-attention to bring in larger spatial context. Our method infers 4D hand trajectories similar to the ground truth while maintaining strong 2D reprojection alignment. We apply the method to both egocentric and allocentric videos. It significantly outperforms existing methods in global trajectory accuracy while being comparable to the state-of-the-art in single-image pose estimation. Project website: https://judyye.github.io/haptic-www
Authors: Ryan Burgert, Yuancheng Xu, Wenqi Xian, Oliver Pilarski, Pascal Clausen, Mingming He, Li Ma, Yitong Deng, Lingxiao Li, Mohsen Mousavi, Michael Ryoo, Paul Debevec, Ning Yu
Abstract: Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequently, our method is agnostic to diffusion model design, requiring no changes to model architectures or training pipelines. Specifically, we propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise derived from optical flow fields, while preserving the spatial Gaussianity. The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer. The harmonization between temporal coherence and spatial Gaussianity in our warped noise leads to effective motion control while maintaining per-frame pixel quality. Extensive experiments and user studies demonstrate the advantages of our method, making it a robust and scalable approach for controlling motion in video diffusion models. Video results are available on our webpage: https://vgenai-netflix-eyeline-research.github.io/Go-with-the-Flow/; source code and model checkpoints are available on GitHub: https://github.com/VGenAI-Netflix-Eyeline-Research/Go-with-the-Flow.
URLs: https://vgenai-netflix-eyeline-research.github.io/Go-with-the-Flow/;, https://github.com/VGenAI-Netflix-Eyeline-Research/Go-with-the-Flow.
Authors: Zhiheng Liu, Ka Leong Cheng, Xi Chen, Jie Xiao, Hao Ouyang, Kai Zhu, Yu Liu, Yujun Shen, Qifeng Chen, Ping Luo
Abstract: Derived from diffusion models, MangaNinjia specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases, cross-character colorization, multi-reference harmonization, beyond the reach of existing algorithms.
Authors: Hyeonwoo Kim, Sangwon Beak, Hanbyul Joo
Abstract: Understanding the ability of humans to use objects is crucial for AI to improve daily life. Existing studies for learning such ability focus on human-object patterns (e.g., contact, spatial relation, orientation) in static situations, and learning Human-Object Interaction (HOI) patterns over time (i.e., movement of human and object) is relatively less explored. In this paper, we introduce a novel type of affordance named Dynamic Affordance. For a given input 3D object mesh, we learn dynamic affordance which models the distribution of both (1) human motion and (2) human-guided object pose during interactions. As a core idea, we present a method to learn the 3D dynamic affordance from synthetically generated 2D videos, leveraging a pre-trained video diffusion model. Specifically, we propose a pipeline that first generates 2D HOI videos from the 3D object and then lifts them into 3D to generate 4D HOI samples. Once we generate diverse 4D HOI samples on various target objects, we train our DAViD, where we present a method based on the Low-Rank Adaptation (LoRA) module for pre-trained human motion diffusion model (MDM) and an object pose diffusion model with human pose guidance. Our motion diffusion model is extended for multi-object interactions, demonstrating the advantage of our pipeline with LoRA for combining the concepts of object usage. Through extensive experiments, we demonstrate our DAViD outperforms the baselines in generating human motion with HOIs.
Authors: Shinyoung Yi, Donggun Kim, Jiwoong Na, Xin Tong, Min H. Kim
Abstract: The objective of polarization rendering is to simulate the interaction of light with materials exhibiting polarization-dependent behavior. However, integrating polarization into rendering is challenging and increases computational costs significantly. The primary difficulty lies in efficiently modeling and computing the complex reflection phenomena associated with polarized light. Specifically, frequency-domain analysis, essential for efficient environment lighting and storage of complex light interactions, is lacking. To efficiently simulate and reproduce polarized light interactions using frequency-domain techniques, we address the challenge of maintaining continuity in polarized light transport represented by Stokes vectors within angular domains. The conventional spherical harmonics method cannot effectively handle continuity and rotation invariance for Stokes vectors. To overcome this, we develop a new method called polarized spherical harmonics (PSH) based on the spin-weighted spherical harmonics theory. Our method provides a rotation-invariant representation of Stokes vector fields. Furthermore, we introduce frequency domain formulations of polarized rendering equations and spherical convolution based on PSH. We first define spherical convolution on Stokes vector fields in the angular domain, and it also provides efficient computation of polarized light transport, nearly on an entry-wise product in the frequency domain. Our frequency domain formulation, including spherical convolution, led to the development of the first real-time polarization rendering technique under polarized environmental illumination, named precomputed polarized radiance transfer, using our polarized spherical harmonics. Results demonstrate that our method can effectively and accurately simulate and reproduce polarized light interactions in complex reflection phenomena.
Authors: Ahmed Anu Wahab, Daqing Hou, Nadia Cheng, Parker Huntley, Charles Devlen
Abstract: Deep learning models, such as the Siamese Neural Networks (SNN), have shown great potential in capturing the intricate patterns in behavioral data. However, the impacts of dataset breadth (i.e., the number of subjects) and depth (e.g., the amount of training samples per subject) on the performance of these models is often informally assumed, and remains under-explored. To this end, we have conducted extensive experiments using the concepts of "feature space" and "density" to guide and gain deeper understanding on the impact of dataset breadth and depth on three publicly available keystroke datasets (Aalto, CMU and Clarkson II). Through varying the number of training subjects, number of samples per subject, amount of data in each sample, and number of triplets used in training, we found that when feasible, increasing dataset breadth enables the training of a well-trained model that effectively captures more inter-subject variability. In contrast, we find that the extent of depth's impact from a dataset depends on the nature of the dataset. Free-text datasets are influenced by all three depth-wise factors; inadequate samples per subject, sequence length, training triplets and gallery sample size, which may all lead to an under-trained model. Fixed-text datasets are less affected by these factors, and as such make it easier to create a well-trained model. These findings shed light on the importance of dataset breadth and depth in training deep learning models for behavioral biometrics and provide valuable insights for designing more effective authentication systems.
Authors: Hong Ye Tan, Emma Slade
Abstract: Dataset distillation aims to find a synthetic training set such that training on the synthetic data achieves similar performance to training on real data, with orders of magnitude less computational requirements. Existing methods can be broadly categorized as either bi-level optimization problems that have neural network training heuristics as the lower level problem, or disentangled methods that bypass the bi-level optimization by matching distributions of data. The latter method has the major advantages of speed and scalability in terms of size of both training and distilled datasets. We demonstrate that when equipped with an encoder-decoder structure, the empirically successful disentangled methods can be reformulated as an optimal quantization problem, where a finite set of points is found to approximate the underlying probability measure by minimizing the expected projection distance. In particular, we link existing disentangled dataset distillation methods to the classical optimal quantization and Wasserstein barycenter problems, demonstrating consistency of distilled datasets for diffusion-based generative priors. We propose a simple extension of the state-of-the-art data distillation method D4M, achieving better performance on the ImageNet-1K dataset with trivial additional computation, and state-of-the-art performance in higher image-per-class settings.
Authors: Sree Bhattacharyya, Shuhua Yang, James Z. Wang
Abstract: The rapid expansion of social media platforms has provided unprecedented access to massive amounts of multimodal user-generated content. Comprehending user emotions can provide valuable insights for improving communication and understanding of human behaviors. Despite significant advancements in Affective Computing, the diverse factors influencing user emotions in social networks remain relatively understudied. Moreover, there is a notable lack of deep learning-based methods for predicting user emotions in social networks, which could be addressed by leveraging the extensive multimodal data available. This work presents a novel formulation of personalized emotion prediction in social networks based on heterogeneous graph learning. Building upon this formulation, we design HMG-Emo, a Heterogeneous Multimodal Graph Learning Framework that utilizes deep learning-based features for user emotion recognition. Additionally, we include a dynamic context fusion module in HMG-Emo that is capable of adaptively integrating the different modalities in social media data. Through extensive experiments, we demonstrate the effectiveness of HMG-Emo and verify the superiority of adopting a graph neural network-based approach, which outperforms existing baselines that use rich hand-crafted features. To the best of our knowledge, HMG-Emo is the first multimodal and deep-learning-based approach to predict personalized emotions within online social networks. Our work highlights the significance of exploiting advanced deep learning techniques for less-explored problems in Affective Computing.
Authors: Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III
Abstract: This work invokes the notion of $f$-divergence to introduce a novel upper bound on the Bayes error rate of a general classification task. We show that the proposed bound can be computed by sampling from the output of a parameterized model. Using this practical interpretation, we introduce the Bayes optimal learning threshold (BOLT) loss whose minimization enforces a classification model to achieve the Bayes error rate. We validate the proposed loss for image and text classification tasks, considering MNIST, Fashion-MNIST, CIFAR-10, and IMDb datasets. Numerical experiments demonstrate that models trained with BOLT achieve performance on par with or exceeding that of cross-entropy, particularly on challenging datasets. This highlights the potential of BOLT in improving generalization.
Authors: Song-Lin Lv, Yu-Yang Chen, Zhi Zhou, Ming Yang, Lan-Zhe Guo
Abstract: Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing studies mainly focus on single-modal prompts or uni-directional modality interaction, overlooking the powerful alignment effects resulting from the interaction between the vision and language modalities. To this end, we propose a novel prompt learning method called $\underline{\textbf{B}}i-directional \underline{\textbf{M}}odality \underline{\textbf{I}}nteraction \underline{\textbf{P}}rompt (BMIP)$, which dynamically weights bi-modal information through learning the information of the attention layer, enhancing trainability and inter-modal consistency compared to simple information aggregation methods. To evaluate the effectiveness of prompt learning methods, we propose a more realistic evaluation paradigm called open-world generalization complementing the widely adopted cross-dataset transfer and domain generalization tasks. Comprehensive experiments on various datasets reveal that BMIP not only outperforms current state-of-the-art methods across all three evaluation paradigms but is also flexible enough to be combined with other prompt-based methods for consistent performance enhancement.
Authors: Mingke Xiao, Yue Su, Liang Yu, Guanglong Qu, Yutong Jia, Yukuan Chang, Xu Zhang
Abstract: The deployment of neural networks in vehicle platforms and wearable Artificial Intelligence-of-Things (AIOT) scenarios has become a research area that has attracted much attention. With the continuous evolution of deep learning technology, many image classification models are committed to improving recognition accuracy, but this is often accompanied by problems such as large model resource usage, complex structure, and high power consumption, which makes it challenging to deploy on resource-constrained platforms. Herein, we propose an ultra-lightweight binary neural network (BNN) model designed for hardware deployment, and conduct image classification research based on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. In addition, we also verify it on the Chinese Traffic Sign (CTS) and Belgian Traffic Sign (BTS) datasets. The proposed model shows excellent recognition performance with an accuracy of up to 97.64%, making it one of the best performing BNN models in the GTSRB dataset. Compared with the full-precision model, the accuracy loss is controlled within 1%, and the parameter storage overhead of the model is only 10% of that of the full-precision model. More importantly, our network model only relies on logical operations and low-bit width fixed-point addition and subtraction operations during the inference phase, which greatly simplifies the design complexity of the processing element (PE). Our research shows the great potential of BNN in the hardware deployment of computer vision models, especially in the field of computer vision tasks related to autonomous driving.
Authors: Ziheng Zhang, Zihan Li, Dandan Shan, Yuehui Qiu, Qingqi Hong, Qingqiang Wu
Abstract: Enhancing the precision of segmenting coronary atherosclerotic plaques from CT Angiography (CTA) images is pivotal for advanced Coronary Atherosclerosis Analysis (CAA), which distinctively relies on the analysis of vessel cross-section images reconstructed via Curved Planar Reformation. This task presents significant challenges due to the indistinct boundaries and structures of plaques and blood vessels, leading to the inadequate performance of current deep learning models, compounded by the inherent difficulty in annotating such complex data. To address these issues, we propose a novel dual-consistency semi-supervised framework that integrates Intra-frame Topological Consistency (ITC) and Cross-frame Topological Consistency (CTC) to leverage labeled and unlabeled data. ITC employs a dual-task network for simultaneous segmentation mask and Skeleton-aware Distance Transform (SDT) prediction, achieving similar prediction of topology structure through consistency constraint without additional annotations. Meanwhile, CTC utilizes an unsupervised estimator for analyzing pixel flow between skeletons and boundaries of adjacent frames, ensuring spatial continuity. Experiments on two CTA datasets show that our method surpasses existing semi-supervised methods and approaches the performance of supervised methods on CAA. In addition, our method also performs better than other methods on the ACDC dataset, demonstrating its generalization.
Authors: Min Sik Byun, Wendy Wan Yee Hui, Wai Kwong Lau
Abstract: This study describes a procedure for applying causal modeling to detect and mitigate algorithmic bias in a multiclass classification problem. The dataset was derived from the FairFace dataset, supplemented with emotional labels generated by the DeepFace pre-trained model. A custom Convolutional Neural Network (CNN) was developed, consisting of four convolutional blocks, followed by fully connected layers and dropout layers to mitigate overfitting. Gender bias was identified in the CNN model's classifications: Females were more likely to be classified as "happy" or "sad," while males were more likely to be classified as "neutral." To address this, the one-vs-all (OvA) technique was applied. A causal model was constructed for each emotion class to adjust the CNN model's predicted class probabilities. The adjusted probabilities for the various classes were then aggregated by selecting the class with the highest probability. The resulting debiased classifications demonstrated enhanced gender fairness across all classes, with negligible impact--or even a slight improvement--on overall accuracy. This study highlights that algorithmic fairness and accuracy are not necessarily trade-offs. All data and code for this study are publicly available for download.
Authors: Yasmine Hachani (LACODAM), Patrick Bouthemy (SAIRPICO), Elisa Fromont (LACODAM), Sylvie Ruffini (UVSQ, INRAE), Ludivine Laffont (UVSQ, INRAE), Alline de Paula Reis (UVSQ, INRAE, ENVA)
Abstract: Videomicroscopy is a promising tool combined with machine learning for studying the early development of in vitro fertilized bovine embryos and assessing its transferability as soon as possible. We aim to predict the embryo transferability within four days at most, taking 2D time-lapse microscopy videos as input. We formulate this problem as a supervised binary classification problem for the classes transferable and not transferable. The challenges are three-fold: 1) poorly discriminating appearance and motion, 2) class ambiguity, 3) small amount of annotated data. We propose a 3D convolutional neural network involving three pathways, which makes it multi-scale in time and able to handle appearance and motion in different ways. For training, we retain the focal loss. Our model, named SFR, compares favorably to other methods. Experiments demonstrate its effectiveness and accuracy for our challenging biological task.
Authors: Aishwarya Jadhav, Jeffery Cao, Abhishree Shetty, Urvashi Priyam Kumar, Aditi Sharma, Ben Sukboontip, Jayant Sravan Tamarapalli, Jingyi Zhang, Anirudh Koul
Abstract: This paper introduces AI Guide Dog (AIGD), a lightweight egocentric navigation assistance system for visually impaired individuals, designed for real-time deployment on smartphones. AIGD addresses key challenges in blind navigation by employing a vision-only, multi-label classification approach to predict directional commands, ensuring safe traversal across diverse environments. We propose a novel technique to enable goal-based outdoor navigation by integrating GPS signals and high-level directions, while also addressing uncertain multi-path predictions for destination-free indoor navigation. Our generalized model is the first navigation assistance system to handle both goal-oriented and exploratory navigation scenarios across indoor and outdoor settings, establishing a new state-of-the-art in blind navigation. We present methods, datasets, evaluations, and deployment insights to encourage further innovations in assistive navigation systems.
Authors: Yifang Xu, Yunzhuo Sun, Benxiang Zhai, Ming Li, Wenxin Liang, Yang Li, Sidan Du
Abstract: The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive high-quality datasets and time-consuming fine-tuning. Although some recent studies introduce a zero-shot setting to avoid fine-tuning, they overlook inherent language bias in the query, leading to erroneous localization. To tackle the aforementioned challenges, this paper proposes Moment-GPT, a tuning-free pipeline for zero-shot VMR utilizing frozen MLLMs. Specifically, we first employ LLaMA-3 to correct and rephrase the query to mitigate language bias. Subsequently, we design a span generator combined with MiniGPT-v2 to produce candidate spans adaptively. Finally, to leverage the video comprehension capabilities of MLLMs, we apply VideoChatGPT and span scorer to select the most appropriate spans. Our proposed method substantially outperforms the state-ofthe-art MLLM-based and zero-shot models on several public datasets, including QVHighlights, ActivityNet-Captions, and Charades-STA.
Authors: Marios Aristodemou, Xiaolan Liu, Yuan Wang, Konstantinos G. Kyriakopoulos, Sangarapillai Lambotharan, Qingsong Wei
Abstract: As we transition from Narrow Artificial Intelligence towards Artificial Super Intelligence, users are increasingly concerned about their privacy and the trustworthiness of machine learning (ML) technology. A common denominator for the metrics of trustworthiness is the quantification of uncertainty inherent in DL algorithms, and specifically in the model parameters, input data, and model predictions. One of the common approaches to address privacy-related issues in DL is to adopt distributed learning such as federated learning (FL), where private raw data is not shared among users. Despite the privacy-preserving mechanisms in FL, it still faces challenges in trustworthiness. Specifically, the malicious users, during training, can systematically create malicious model parameters to compromise the models predictive and generative capabilities, resulting in high uncertainty about their reliability. To demonstrate malicious behaviour, we propose a novel model poisoning attack method named Delphi which aims to maximise the uncertainty of the global model output. We achieve this by taking advantage of the relationship between the uncertainty and the model parameters of the first hidden layer of the local model. Delphi employs two types of optimisation , Bayesian Optimisation and Least Squares Trust Region, to search for the optimal poisoned model parameters, named as Delphi-BO and Delphi-LSTR. We quantify the uncertainty using the KL Divergence to minimise the distance of the predictive probability distribution towards an uncertain distribution of model output. Furthermore, we establish a mathematical proof for the attack effectiveness demonstrated in FL. Numerical results demonstrate that Delphi-BO induces a higher amount of uncertainty than Delphi-LSTR highlighting vulnerability of FL systems to model poisoning attacks.
Authors: Di Hong, Yueming Wang
Abstract: Spiking Neural Networks (SNNs) are promising for low-power computation due to their event-driven mechanism but often suffer from lower accuracy compared to Artificial Neural Networks (ANNs). ANN-to-SNN knowledge distillation can improve SNN performance, but previous methods either focus solely on label information, missing valuable intermediate layer features, or use a layer-wise approach that neglects spatial and temporal semantic inconsistencies, leading to performance degradation.To address these limitations, we propose a novel method called self-attentive spatio-temporal calibration (SASTC). SASTC uses self-attention to identify semantically aligned layer pairs between ANN and SNN, both spatially and temporally. This enables the autonomous transfer of relevant semantic information. Extensive experiments show that SASTC outperforms existing methods, effectively solving the mismatching problem. Superior accuracy results include 95.12% on CIFAR-10, 79.40% on CIFAR-100 with 2 time steps, and 68.69% on ImageNet with 4 time steps for static datasets, and 97.92% on DVS-Gesture and 83.60% on DVS-CIFAR10 for neuromorphic datasets. This marks the first time SNNs have outperformed ANNs on both CIFAR-10 and CIFAR-100, shedding the new light on the potential applications of SNNs.
Authors: Arwa Al-Rubaian, Gozde N. Gunesli, Wajd A. Althakfi, Ayesha Azam, David Snead, Nasir M. Rajpoot, Shan E Ahmed Raza
Abstract: Lung adenocarcinoma (LUAD) is a morphologically heterogeneous disease, characterized by five primary histological growth patterns. The classification of such patterns is crucial due to their direct relation to prognosis but the high subjectivity and observer variability pose a major challenge. Although several studies have developed machine learning methods for growth pattern classification, they either only report the predominant pattern per slide or lack proper evaluation. We propose a generalizable machine learning pipeline capable of classifying lung tissue into one of the five patterns or as non-tumor. The proposed pipeline's strength lies in a novel compact Cell Organization Maps (cellOMaps) representation that captures the cellular spatial patterns from Hematoxylin and Eosin whole slide images (WSIs). The proposed pipeline provides state-of-the-art performance on LUAD growth pattern classification when evaluated on both internal unseen slides and external datasets, significantly outperforming the current approaches. In addition, our preliminary results show that the model's outputs can be used to predict patients Tumor Mutational Burden (TMB) levels.
Authors: Yucong Meng, Zhiwei Yang, Zhijian Song, Yonghong Shi
Abstract: The accelerated MRI reconstruction poses a challenging ill-posed inverse problem due to the significant undersampling in k-space. Deep neural networks, such as CNNs and ViT, have shown substantial performance improvements for this task while encountering the dilemma between global receptive fields and efficient computation. To this end, this paper pioneers exploring Mamba, a new paradigm for long-range dependency modeling with linear complexity, for efficient and effective MRI reconstruction. However, directly applying Mamba to MRI reconstruction faces three significant issues: (1) Mamba's row-wise and column-wise scanning disrupts k-space's unique spectrum, leaving its potential in k-space learning unexplored. (2) Existing Mamba methods unfold feature maps with multiple lengthy scanning paths, leading to long-range forgetting and high computational burden. (3) Mamba struggles with spatially-varying contents, resulting in limited diversity of local representations. To address these, we propose a dual-domain multi-scale Mamba for MRI reconstruction from the following perspectives: (1) We pioneer vision Mamba in k-space learning. A circular scanning is customized for spectrum unfolding, benefiting the global modeling of k-space. (2) We propose a multi-scale Mamba with an efficient scanning strategy in both image and k-space domains. It mitigates long-range forgetting and achieves a better trade-off between efficiency and performance. (3) We develop a local diversity enhancement module to improve the spatially-varying representation of Mamba. Extensive experiments are conducted on three public datasets for MRI reconstruction under various undersampling patterns. Comprehensive results demonstrate that our method significantly outperforms state-of-the-art methods with lower computational cost. Implementation code will be available at https://github.com/XiaoMengLiLiLi/DM-Mamba.
Authors: Nessrine Farhat, Amine Bohi, Leila Ben Letaifa, Rim Slama
Abstract: The field of affective computing has seen significant advancements in exploring the relationship between emotions and emerging technologies. This paper presents a novel and valuable contribution to this field with the introduction of a comprehensive French multimodal dataset designed specifically for emotion recognition. The dataset encompasses three primary modalities: facial expressions, speech, and gestures, providing a holistic perspective on emotions. Moreover, the dataset has the potential to incorporate additional modalities, such as Natural Language Processing (NLP) to expand the scope of emotion recognition research. The dataset was curated through engaging participants in card game sessions, where they were prompted to express a range of emotions while responding to diverse questions. The study included 10 sessions with 20 participants (9 females and 11 males). The dataset serves as a valuable resource for furthering research in emotion recognition and provides an avenue for exploring the intricate connections between human emotions and digital technologies.
Authors: Matias Valdenegro-Toro, Marco Zullich
Abstract: Inputs to machine learning models can have associated noise or uncertainties, but they are often ignored and not modelled. It is unknown if Bayesian Neural Networks and their approximations are able to consider uncertainty in their inputs. In this paper we build a two input Bayesian Neural Network (mean and standard deviation) and evaluate its capabilities for input uncertainty estimation across different methods like Ensembles, MC-Dropout, and Flipout. Our results indicate that only some uncertainty estimation methods for approximate Bayesian NNs can model input uncertainty, in particular Ensembles and Flipout.
Authors: Ke Wu, Zicheng Zhang, Muer Tie, Ziqing Ai, Zhongxue Gan, Wenchao Ding
Abstract: VINGS-Mono is a monocular (inertial) Gaussian Splatting (GS) SLAM framework designed for large scenes. The framework comprises four main components: VIO Front End, 2D Gaussian Map, NVS Loop Closure, and Dynamic Eraser. In the VIO Front End, RGB frames are processed through dense bundle adjustment and uncertainty estimation to extract scene geometry and poses. Based on this output, the mapping module incrementally constructs and maintains a 2D Gaussian map. Key components of the 2D Gaussian Map include a Sample-based Rasterizer, Score Manager, and Pose Refinement, which collectively improve mapping speed and localization accuracy. This enables the SLAM system to handle large-scale urban environments with up to 50 million Gaussian ellipsoids. To ensure global consistency in large-scale scenes, we design a Loop Closure module, which innovatively leverages the Novel View Synthesis (NVS) capabilities of Gaussian Splatting for loop closure detection and correction of the Gaussian map. Additionally, we propose a Dynamic Eraser to address the inevitable presence of dynamic objects in real-world outdoor scenes. Extensive evaluations in indoor and outdoor environments demonstrate that our approach achieves localization performance on par with Visual-Inertial Odometry while surpassing recent GS/NeRF SLAM methods. It also significantly outperforms all existing methods in terms of mapping and rendering quality. Furthermore, we developed a mobile app and verified that our framework can generate high-quality Gaussian maps in real time using only a smartphone camera and a low-frequency IMU sensor. To the best of our knowledge, VINGS-Mono is the first monocular Gaussian SLAM method capable of operating in outdoor environments and supporting kilometer-scale large scenes.
Authors: MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu
Abstract: We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient scaling. To maximize computational capacity, we integrate it with Mixture of Experts (MoE), creating a model with 32 experts and 456 billion total parameters, of which 45.9 billion are activated for each token. We develop an optimized parallel strategy and highly efficient computation-communication overlap techniques for MoE and lightning attention. This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens. The context window of MiniMax-Text-01 can reach up to 1 million tokens during training and extrapolate to 4 million tokens during inference at an affordable cost. Our vision-language model, MiniMax-VL-01 is built through continued training with 512 billion vision-language tokens. Experiments on both standard and in-house benchmarks show that our models match the performance of state-of-the-art models like GPT-4o and Claude-3.5-Sonnet while offering 20-32 times longer context window. We publicly release MiniMax-01 at https://github.com/MiniMax-AI.
Authors: Brandon Victor, Zhen He, Aiden Nibali
Abstract: Agricultural research is essential for increasing food production to meet the requirements of an increasing population in the coming decades. Recently, satellite technology has been improving rapidly and deep learning has seen much success in generic computer vision tasks and many application areas which presents an important opportunity to improve analysis of agricultural land. Here we present a systematic review of 150 studies to find the current uses of deep learning on satellite imagery for agricultural research. Although we identify 5 categories of agricultural monitoring tasks, the majority of the research interest is in crop segmentation and yield prediction. We found that, when used, modern deep learning methods consistently outperformed traditional machine learning across most tasks; the only exception was that Long Short-Term Memory (LSTM) Recurrent Neural Networks did not consistently outperform Random Forests (RF) for yield prediction. The reviewed studies have largely adopted methodologies from generic computer vision, except for one major omission: benchmark datasets are not utilised to evaluate models across studies, making it difficult to compare results. Additionally, some studies have specifically utilised the extra spectral resolution available in satellite imagery, but other divergent properties of satellite images - such as the hugely different scales of spatial patterns - are not being taken advantage of in the reviewed studies.
Authors: Chaewon Kim, Seung-Jun Moon, Gyeong-Moon Park
Abstract: Recent advanced GAN inversion models aim to convey high-fidelity information from original images to generators through methods using generator tuning or high-dimensional feature learning. Despite these efforts, accurately reconstructing image-specific details remains as a challenge due to the inherent limitations both in terms of training and structural aspects, leading to a bias towards low-frequency information. In this paper, we look into the widely used pixel loss in GAN inversion, revealing its predominant focus on the reconstruction of low-frequency features. We then propose WINE, a Wavelet-guided GAN Inversion aNd Editing model, which transfers the high-frequency information through wavelet coefficients via newly proposed wavelet loss and wavelet fusion scheme. Notably, WINE is the first attempt to interpret GAN inversion in the frequency domain. Our experimental results showcase the precision of WINE in preserving high-frequency details and enhancing image quality. Even in editing scenarios, WINE outperforms existing state-of-the-art GAN inversion models with a fine balance between editability and reconstruction quality.
Authors: Florian Merkle, David Weber, Pascal Sch\"ottle, Stephan Schl\"ogl, Martin Nocker
Abstract: Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the increased computational requirements hamper the deployment in resource-constrained environments, such as mobile or IoT devices, and (2) explaining the complex decisions of such networks to humans is challenging. Network pruning is a technical approach to reduce the complexity of models, where less important parameters are removed. The work presented in this paper investigates whether this reduction in technical complexity also helps with perceived explainability. To do so, we conducted a pre-study and two human-grounded experiments, assessing the effects of different pruning ratios on explainability. Overall, we evaluate four different compression rates (i.e., 2, 4, 8, and 32) with 37 500 tasks on Mechanical Turk. Results indicate that lower compression rates have a positive influence on explainability, while higher compression rates show negative effects. Furthermore, we were able to identify sweet spots that increase both the perceived explainability and the model's performance.
Authors: Hao Wu, Fan Xu, Chong Chen, Xian-Sheng Hua, Xiao Luo, Haixin Wang
Abstract: In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams. Existing approaches typically utilize external information such as semantic maps to improve video prediction accuracy, which often neglect the inherent physical knowledge embedded within videos. Worse still, their high computational costs could impede their applications for high-resolution videos. To address these constraints, we introduce a novel framework called \underline{P}hysics-\underline{a}ssisted \underline{S}patio-\underline{t}emporal \underline{Net}work (PastNet) for high-quality video prediction. The core of PastNet lies in incorporating a spectral convolution operator in the Fourier domain, which efficiently introduces inductive biases from the underlying physical laws. Additionally, we employ a memory bank with the estimated intrinsic dimensionality to discretize local features during the processing of complex spatio-temporal signals, thereby reducing computational costs and facilitating efficient high-resolution video prediction. Extensive experiments on various widely-used spatio-temporal video benchmarks demonstrate the effectiveness and efficiency of the proposed PastNet compared with a range of state-of-the-art methods, particularly in high-resolution scenarios.
Authors: Huan Ma, Yan Zhu, Changqing Zhang, Peilin Zhao, Baoyuan Wu, Long-Kai Huang, Qinghua Hu, Bingzhe Wu
Abstract: Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of ``decision shortcuts'' that hinder their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, we propose a simple yet effective method, Spurious Feature Eraser (SEraser), to alleviate the decision shortcuts by erasing the spurious features. Specifically, we introduce a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading spurious information. We conduct comparative analysis of the proposed method against various approaches which validates the significant superiority.
Authors: Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang, Xiu Li
Abstract: Gesture synthesis is a vital realm of human-computer interaction, with wide-ranging applications across various fields like film, robotics, and virtual reality. Recent advancements have utilized the diffusion model and attention mechanisms to improve gesture synthesis. However, due to the high computational complexity of these techniques, generating long and diverse sequences with low latency remains a challenge. We explore the potential of state space models (SSMs) to address the challenge, implementing a two-stage modeling strategy with discrete motion priors to enhance the quality of gestures. Leveraging the foundational Mamba block, we introduce MambaTalk, enhancing gesture diversity and rhythm through multimodal integration. Extensive experiments demonstrate that our method matches or exceeds the performance of state-of-the-art models.
Authors: Patrick Guidotti
Abstract: A kernel based method is proposed for the construction of signature (defining) functions of subsets of $\mathbb{R}^d$. The subsets can range from full dimensional manifolds (open subsets) to point clouds (a finite number of points) and include bounded smooth manifolds of any codimension. The interpolation and analysis of point clouds are the main application. Two extreme cases in terms of regularity are considered, where the data set is interpolated by an analytic surface, at the one extreme, and by a H\"older continuous surface, at the other. The signature function can be computed as a linear combination of translated kernels, the coefficients of which are the solution of a finite dimensional linear problem. Once it is obtained, it can be used to estimate the dimension as well as the normal and the curvatures of the interpolated surface. The method is global and does not require explicit knowledge of local neighborhoods or any other structure present in the data set. It admits a variational formulation with a natural ``regularized'' counterpart, that proves to be useful in dealing with data sets corrupted by numerical error or noise. The underlying analytical structure of the approach is presented in general before it is applied to the case of point clouds.
Authors: Yuan Zang, Tian Yun, Hao Tan, Trung Bui, Chen Sun
Abstract: Do vision-language models (VLMs) pre-trained to caption an image of a "durian" learn visual concepts such as "brown" (color) and "spiky" (texture) at the same time? We aim to answer this question as visual concepts learned "for free" would enable wide applications such as neuro-symbolic reasoning or human-interpretable object classification. We assume that the visual concepts, if captured by pre-trained VLMs, can be extracted by their vision-language interface with text-based concept prompts. We observe that recent works prompting VLMs with concepts often differ in their strategies to define and evaluate the visual concepts, leading to conflicting conclusions. We propose a new concept definition strategy based on two observations: First, certain concept prompts include shortcuts that recognize correct concepts for wrong reasons; Second, multimodal information (e.g. visual discriminativeness, and textual knowledge) should be leveraged when selecting the concepts. Our proposed concept discovery and learning (CDL) framework is thus designed to identify a diverse list of generic visual concepts (e.g. "spiky" as opposed to "spiky durian"), which are ranked and selected based on visual and language mutual information. We carefully design quantitative and human evaluations of the discovered concepts on six diverse visual recognition datasets, which confirm that pre-trained VLMs do learn visual concepts that provide accurate and thorough descriptions for the recognized objects. All code and models are publicly released.
Authors: Xu Pan, Aaron Philip, Ziqian Xie, Odelia Schwartz
Abstract: Self-attention in vision transformers is often thought to perform perceptual grouping where tokens attend to other tokens with similar embeddings, which could correspond to semantically similar features of an object. However, attending to dissimilar tokens can be beneficial by providing contextual information. We propose to analyze the query-key interaction by the singular value decomposition of the interaction matrix (i.e. ${\textbf{W}_q}^\top\textbf{W}_k$). We find that in many ViTs, especially those with classification training objectives, early layers attend more to similar tokens, while late layers show increased attention to dissimilar tokens, providing evidence corresponding to perceptual grouping and contextualization, respectively. Many of these interactions between features represented by singular vectors are interpretable and semantic, such as attention between relevant objects, between parts of an object, or between the foreground and background. This offers a novel perspective on interpreting the attention mechanism, which contributes to understanding how transformer models utilize context and salient features when processing images.
Authors: Jinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma, Yaodong Yu, Cihang Xie
Abstract: CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite extensive investigations into the scaling behaviors of language and vision transformers, the scalability of CRATE remains an open question which this paper aims to address. Specifically, we propose CRATE-$\alpha$, featuring strategic yet minimal modifications to the sparse coding block in the CRATE architecture design, and a light training recipe designed to improve the scalability of CRATE. Through extensive experiments, we demonstrate that CRATE-$\alpha$ can effectively scale with larger model sizes and datasets. For example, our CRATE-$\alpha$-B substantially outperforms the prior best CRATE-B model accuracy on ImageNet classification by 3.7%, achieving an accuracy of 83.2%. Meanwhile, when scaling further, our CRATE-$\alpha$-L obtains an ImageNet classification accuracy of 85.1%. More notably, these model performance improvements are achieved while preserving, and potentially even enhancing the interpretability of learned CRATE models, as we demonstrate through showing that the learned token representations of increasingly larger trained CRATE-$\alpha$ models yield increasingly higher-quality unsupervised object segmentation of images. The project page is https://rayjryang.github.io/CRATE-alpha/.
Authors: Junbao Zhou, Ziqi Pang, Yu-Xiong Wang
Abstract: With recent video object segmentation (VOS) benchmarks evolving to challenging scenarios, we revisit a simple but overlooked strategy: restricting the size of memory banks. This diverges from the prevalent practice of expanding memory banks to accommodate extensive historical information. Our specially designed "memory deciphering" study offers a pivotal insight underpinning such a strategy: expanding memory banks, while seemingly beneficial, actually increases the difficulty for VOS modules to decode relevant features due to the confusion from redundant information. By restricting memory banks to a limited number of essential frames, we achieve a notable improvement in VOS accuracy. This process balances the importance and freshness of frames to maintain an informative memory bank within a bounded capacity. Additionally, restricted memory banks reduce the training-inference discrepancy in memory lengths compared with continuous expansion. This fosters new opportunities in temporal reasoning and enables us to introduce the previously overlooked "temporal positional embedding." Finally, our insights are embodied in "RMem" ("R" for restricted), a simple yet effective VOS modification that excels at challenging VOS scenarios and establishes new state of the art for object state changes (on the VOST dataset) and long videos (on the Long Videos dataset). Our code and demo are available at https://restricted-memory.github.io/.
Authors: Wojciech Zielonka, Timo Bolkart, Thabo Beeler, Justus Thies
Abstract: Current personalized neural head avatars face a trade-off: lightweight models lack detail and realism, while high-quality, animatable avatars require significant computational resources, making them unsuitable for commodity devices. To address this gap, we introduce Gaussian Eigen Models (GEM), which provide high-quality, lightweight, and easily controllable head avatars. GEM utilizes 3D Gaussian primitives for representing the appearance combined with Gaussian splatting for rendering. Building on the success of mesh-based 3D morphable face models (3DMM), we define GEM as an ensemble of linear eigenbases for representing the head appearance of a specific subject. In particular, we construct linear bases to represent the position, scale, rotation, and opacity of the 3D Gaussians. This allows us to efficiently generate Gaussian primitives of a specific head shape by a linear combination of the basis vectors, only requiring a low-dimensional parameter vector that contains the respective coefficients. We propose to construct these linear bases (GEM) by distilling high-quality compute-intense CNN-based Gaussian avatar models that can generate expression-dependent appearance changes like wrinkles. These high-quality models are trained on multi-view videos of a subject and are distilled using a series of principal component analyses. Once we have obtained the bases that represent the animatable appearance space of a specific human, we learn a regressor that takes a single RGB image as input and predicts the low-dimensional parameter vector that corresponds to the shown facial expression. In a series of experiments, we compare GEM's self-reenactment and cross-person reenactment results to state-of-the-art 3D avatar methods, demonstrating GEM's higher visual quality and better generalization to new expressions.
Authors: Shivansh Sharma, Mathew Huang, Sanat Nair, Alan Wen, Christina Petlowany, Juston Moore, Selma Wanna, Mitch Pryor
Abstract: Industry 4.0 introduced AI as a transformative solution for modernizing manufacturing processes. Its successor, Industry 5.0, envisions humans as collaborators and experts guiding these AI-driven manufacturing solutions. Developing these techniques necessitates algorithms capable of safe, real-time identification of human positions in a scene, particularly their hands, during collaborative assembly. Although substantial efforts have curated datasets for hand segmentation, most focus on residential or commercial domains. Existing datasets targeting industrial settings predominantly rely on synthetic data, which we demonstrate does not effectively transfer to real-world operations. Moreover, these datasets lack uncertainty estimations critical for safe collaboration. Addressing these gaps, we present HAGS: Hand and Glove Segmentation Dataset. This dataset provides challenging examples to build applications toward hand and glove segmentation in industrial human-robot collaboration scenarios as well as assess out-of-distribution images, constructed via green screen augmentations, to determine ML-classifier robustness. We study state-of-the-art, real-time segmentation models to evaluate existing methods. Our dataset and baselines are publicly available.
Authors: Despina Konstantinidou, Christos Koutlis, Symeon Papadopoulos
Abstract: Generative AI technologies produce increasingly realistic imagery, which, despite its potential for creative applications, can also be misused to produce misleading and harmful content. This renders Synthetic Image Detection (SID) methods essential for identifying AI-generated content online. State-of-the-art SID methods typically resize or center-crop input images due to architectural or computational constraints, which hampers the detection of artifacts that appear in high-resolution images. To address this limitation, we propose TextureCrop, an image pre-processing component that can be plugged in any pre-trained SID model to improve its performance. By focusing on high-frequency image parts where generative artifacts are prevalent, TextureCrop enhances SID performance with manageable memory requirements. Experimental results demonstrate a consistent improvement in AUC across various detectors by 6.1% compared to center cropping and by 15% compared to resizing, across high-resolution images from the Forensynths, Synthbuster and TWIGMA datasets. Code available at https : //github.com/mever-team/texture-crop.
Authors: Delyan Boychev, Radostin Cholakov
Abstract: Recent generative models produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. Potential harmful use cases of these models, necessitate the creation of robust synthetic image detectors. However, current datasets in the field contain generated images with questionable quality or have examples from one predominant content type which leads to poor generalizability of the underlying detectors. We find that the curation of a balanced amount of high-resolution generated images across various content types is crucial for the generalizability of detectors, and introduce ImagiNet, a dataset of 200K examples, spanning four categories: photos, paintings, faces, and miscellaneous. Synthetic images in ImagiNet are produced with both open-source and proprietary generators, whereas real counterparts for each content type are collected from public datasets. The structure of ImagiNet allows for a two-track evaluation system: i) classification as real or synthetic and ii) identification of the generative model. To establish a strong baseline, we train a ResNet-50 model using a self-supervised contrastive objective (SelfCon) for each track which achieves evaluation AUC of up to 0.99 and balanced accuracy ranging from 86% to 95%, even under conditions that involve compression and resizing. The provided model is generalizable enough to achieve zero-shot state-of-the-art performance on previous synthetic detection benchmarks. We provide ablations to demonstrate the importance of content types and publish code and data.
Authors: Zhiqiang Wu, Yingjie Liu, Licheng Sun, Jian Yang, Hanlin Dong, Shing-Ho J. Lin, Xuan Tang, Jinpeng Mi, Bo Jin, Xian Wei
Abstract: Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets.
Authors: Nishan Gunawardena, Gough Yumu Lui, Jeewani Anupama Ginige, Bahman Javadi
Abstract: A significant limitation of current smartphone-based eye-tracking algorithms is their low accuracy when applied to video-type visual stimuli, as they are typically trained on static images. Also, the increasing demand for real-time interactive applications like games, VR, and AR on smartphones requires overcoming the limitations posed by resource constraints such as limited computational power, battery life, and network bandwidth. Therefore, we developed two new smartphone eye-tracking techniques for video-type visuals by combining Convolutional Neural Networks (CNN) with two different Recurrent Neural Networks (RNN), namely Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). Our CNN+LSTM and CNN+GRU models achieved an average Root Mean Square Error of 0.955 cm and 1.091 cm, respectively. To address the computational constraints of smartphones, we developed an edge intelligence architecture to enhance the performance of smartphone-based eye tracking. We applied various optimisation methods like quantisation and pruning to deep learning models for better energy, CPU, and memory usage on edge devices, focusing on real-time processing. Using model quantisation, the model inference time in the CNN+LSTM and CNN+GRU models was reduced by 21.72% and 19.50%, respectively, on edge devices.
Authors: Vincenzo Polizzi, Marco Cannici, Davide Scaramuzza, Jonathan Kelly
Abstract: Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. Among these, sparse feature matching stands out as an efficient, versatile, and generally lightweight approach with numerous applications. However, feature-based methods often struggle with significant viewpoint and appearance changes, leading to matching failures and inaccurate pose estimates. To overcome this limitation, we propose a novel approach that leverages a globally sparse yet locally dense 3D representation of 2D features. By tracking and triangulating landmarks over a sequence of frames, we construct a sparse voxel map optimized to render image patch descriptors observed during tracking. Given an initial pose estimate, we first synthesize descriptors from the voxels using volumetric rendering and then perform feature matching to estimate the camera pose. This methodology enables the generation of descriptors for unseen views, enhancing robustness to view changes. We extensively evaluate our method on the 7-Scenes and Cambridge Landmarks datasets. Our results show that our method significantly outperforms existing state-of-the-art feature representation techniques in indoor environments, achieving up to a 39% improvement in median translation error. Additionally, our approach yields comparable results to other methods for outdoor scenarios while maintaining lower memory and computational costs.
Authors: Ali Mehrabian, Parsa Mojarad Adi, Moein Heidari, Ilker Hacihaliloglu
Abstract: Implicit neural representations (INRs) use neural networks to provide continuous and resolution-independent representations of complex signals with a small number of parameters. However, existing INR models often fail to capture important frequency components specific to each task. To address this issue, in this paper, we propose a Fourier Kolmogorov Arnold network (FKAN) for INRs. The proposed FKAN utilizes learnable activation functions modeled as Fourier series in the first layer to effectively control and learn the task-specific frequency components. In addition, the activation functions with learnable Fourier coefficients improve the ability of the network to capture complex patterns and details, which is beneficial for high-resolution and high-dimensional data. Experimental results show that our proposed FKAN model outperforms three state-of-the-art baseline schemes, and improves the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) for the image representation task and intersection over union (IoU) for the 3D occupancy volume representation task, respectively. The code is available at github.com/Ali-Meh619/FKAN.
Authors: Zihan Su, Junhao Zhuang, Chun Yuan
Abstract: Recently, text-guided image editing has achieved significant success. However, existing methods can only apply simple textures like wood or gold when changing the texture of an object. Complex textures such as cloud or fire pose a challenge. This limitation stems from that the target prompt needs to contain both the input image content and
Authors: Jiacheng Zhang, Yang Jiao, Shaoxiang Chen, Na Zhao, Jingjing Chen
Abstract: Recently, Multimodal Large Language Models (MLLMs) have made significant progress in the video comprehension field. Despite remarkable content reasoning and instruction following capabilities they demonstrated, the hallucination problem of these VideoLLMs is less explored compared with its counterpart in the image domain. To mitigate this gap, we propose EventHallusion, a novel benchmark that focuses on assessing the VideoLLMs' hallucination toward event, the crux of video analysis. From a hallucination attribution perspective, our EventHallusion benchmark is curated to assess a VideoLLM's susceptibility toward language priors and vision-language biases. On the other hand, we also propose a simple yet effective method, called Temporal Contrastive Decoding (TCD), to tackle the hallucination problems of VideoLLMs. The proposed TCD method rectifies the model's bias toward its priors during the decoding stage by comparing the original video with a modified version, in which temporal cues are disrupted. Through comprehensive evaluation of eight open-source and two closed-source VideoLLMs on the proposed EventHallusion benchmark, we observe that the open-source models suffer significantly from hallucination problems, whereas the closed-source ones perform markedly better. By further equipping open-source VideoLLMs with the proposed TCD approach, evident performance improvements are achieved across most metrics in the EventHallusion benchmark. Our codes and benchmark data are available at https://github.com/Stevetich/EventHallusion.
Authors: Lukas Heine, Fabian H\"orst, Jana Fragemann, Gijs Luijten, Jan Egger, Fin Bahnsen, M. Saquib Sarfraz, Jens Kleesiek, Constantin Seibold
Abstract: In industries such as healthcare, finance, and manufacturing, analysis of unstructured textual data presents significant challenges for analysis and decision making. Uncovering patterns within large-scale corpora and understanding their semantic impact is critical, but depends on domain experts or resource-intensive manual reviews. In response, we introduce Spacewalker in this system demonstration paper, an interactive tool designed to analyze, explore, and annotate data across multiple modalities. It allows users to extract data representations, visualize them in low-dimensional spaces and traverse large datasets either exploratory or by querying regions of interest. We evaluated Spacewalker through extensive experiments and annotation studies, assessing its efficacy in improving data integrity verification and annotation. We show that Spacewalker reduces time and effort compared to traditional methods. The code of this work is open-source and can be found at: https://github.com/code-lukas/Spacewalker
Authors: Junyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao Lu, Song Han
Abstract: We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at https://github.com/mit-han-lab/efficientvit.
Authors: Tianhao Zhang, Zhixiang Chen, Lyudmila S. Mihaylova
Abstract: Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for image Out-of-Distribution (OOD) detection, we introduce a novel and generic framework named Prior-augmented Vision Transformer (PViT). Taking as input the prior class logits from a pretrained model, we train PViT to predict the class logits. During inference, PViT identifies OOD samples by quantifying the divergence between the predicted class logits and the prior logits obtained from pre-trained models. Unlike existing state-of-the-art(SOTA) OOD detection methods, PViT shapes the decision boundary between ID and OOD by utilizing the proposed prior guided confidence, without requiring additional data modeling, generation methods, or structural modifications. Extensive experiments on the large-scale ImageNet benchmark, evaluated against over seven OOD datasets, demonstrate that PViT significantly outperforms existing SOTA OOD detection methods in terms of FPR95 and AUROC. The codebase is publicly available at https://github.com/RanchoGoose/PViT.
Authors: Ariel Larey, Eyal Rond, Omer Achrack
Abstract: Face recognition technologies are increasingly used in various applications, yet they are vulnerable to face spoofing attacks. These spoofing attacks often involve unique 3D structures, such as printed papers or mobile device screens. Although stereo-depth cameras can detect such attacks effectively, their high-cost limits their widespread adoption. Conversely, two-sensor systems without extrinsic calibration offer a cost-effective alternative but are unable to calculate depth using stereo techniques. In this work, we propose a method to overcome this challenge by leveraging facial attributes to derive disparity information and estimate relative depth for anti-spoofing purposes, using non-calibrated systems. We introduce a multi-modal anti-spoofing model, coined Disparity Model, that incorporates created disparity maps as a third modality alongside the two original sensor modalities. We demonstrate the effectiveness of the Disparity Model in countering various spoof attacks using a comprehensive dataset collected from the Intel RealSense ID Solution F455. Our method outperformed existing methods in the literature, achieving an Equal Error Rate (EER) of 1.71% and a False Negative Rate (FNR) of 2.77% at a False Positive Rate (FPR) of 1%. These errors are lower by 2.45% and 7.94% than the errors of the best comparison method, respectively. Additionally, we introduce a model ensemble that addresses 3D spoof attacks as well, achieving an EER of 2.04% and an FNR of 3.83% at an FPR of 1%. Overall, our work provides a state-of-the-art solution for the challenging task of anti-spoofing in non-calibrated systems that lack depth information.
Authors: Anjith George, Sebastien Marcel
Abstract: The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale datasets are often collected without explicit consent, raising ethical and privacy concerns. To address this, there have been proposals to use synthetic datasets for training face recognition models. Yet, such models still rely on real data to train the generative models and generally exhibit inferior performance compared to those trained on real datasets. One of these datasets, DigiFace, uses a graphics pipeline to generate different identities and intra-class variations without using real data in model training. However, the performance of this approach is poor on face recognition benchmarks, possibly due to the lack of realism in the images generated by the graphics pipeline. In this work, we introduce a novel framework for realism transfer aimed at enhancing the realism of synthetically generated face images. Our method leverages the large-scale face foundation model, and we adapt the pipeline for realism enhancement. By integrating the controllable aspects of the graphics pipeline with our realism enhancement technique, we generate a large amount of realistic variations, combining the advantages of both approaches. Our empirical evaluations demonstrate that models trained using our enhanced dataset significantly improve the performance of face recognition systems over the baseline. The source code and dataset will be publicly accessible at the following link: https://www.idiap.ch/paper/digi2real
Authors: Qishuai Wen, Chun-Guang Li
Abstract: State-of-the-art methods for Transformer-based semantic segmentation typically adopt Transformer decoders that are used to extract additional embeddings from image embeddings via cross-attention, refine either or both types of embeddings via self-attention, and project image embeddings onto the additional embeddings via dot-product. Despite their remarkable success, these empirical designs still lack theoretical justifications or interpretations, thus hindering potentially principled improvements. In this paper, we argue that there are fundamental connections between semantic segmentation and compression, especially between the Transformer decoders and Principal Component Analysis (PCA). From such a perspective, we derive a white-box, fully attentional DEcoder for PrIncipled semantiC segemenTation (DEPICT), with the interpretations as follows: 1) the self-attention operator refines image embeddings to construct an ideal principal subspace that aligns with the supervision and retains most information; 2) the cross-attention operator seeks to find a low-rank approximation of the refined image embeddings, which is expected to be a set of orthonormal bases of the principal subspace and corresponds to the predefined classes; 3) the dot-product operation yields compact representation for image embeddings as segmentation masks. Experiments conducted on dataset ADE20K find that DEPICT consistently outperforms its black-box counterpart, Segmenter, and it is light weight and more robust.
Authors: Chunhui Zhang, Li Liu, Hao Wen, Xi Zhou, Yanfeng Wang
Abstract: Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this end, we propose an efficient mamba-based tracker, leveraging dual enhancement techniques to boost night UAV tracking. The mamba-based low-light enhancer, equipped with an illumination estimator and a damage restorer, achieves global image enhancement while preserving the details and structure of low-light images. Additionally, we advance a cross-modal mamba network to achieve efficient interactive learning between vision and language modalities. Extensive experiments showcase that our method achieves advanced performance and exhibits significantly improved computation and memory efficiency. For instance, our method is 2.8$\times$ faster than CiteTracker and reduces 50.2$\%$ GPU memory. Our codes are available at \url{https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.
URLs: https://github.com/983632847/Awesome-Multimodal-Object-Tracking
Authors: S\"onke Tenckhoff, Mario Koddenbrock, Erik Rodner
Abstract: Automated object detection has become increasingly valuable across diverse applications, yet efficient, high-quality annotation remains a persistent challenge. In this paper, we present the development and evaluation of a platform designed to interactively improve object detection models. The platform allows uploading and annotating images as well as fine-tuning object detection models. Users can then manually review and refine annotations, further creating improved snapshots that are used for automatic object detection on subsequent image uploads - a process we refer to as semi-automatic annotation resulting in a significant gain in annotation efficiency. Whereas iterative refinement of model results to speed up annotation has become common practice, we are the first to quantitatively evaluate its benefits with respect to time, effort, and interaction savings. Our experimental results show clear evidence for a significant time reduction of up to 53% for semi-automatic compared to manual annotation. Importantly, these efficiency gains did not compromise annotation quality, while matching or occasionally even exceeding the accuracy of manual annotations. These findings demonstrate the potential of our lightweight annotation platform for creating high-quality object detection datasets and provide best practices to guide future development of annotation platforms. The platform is open-source, with the frontend and backend repositories available on GitHub (https://github.com/ml-lab-htw/iterative-annotate). To support the understanding of our labeling process, we have created an explanatory video demonstrating the methodology using microscopy images of E. coli bacteria as an example. The video is available on YouTube (https://www.youtube.com/watch?v=CM9uhE8NN5E).
URLs: https://github.com/ml-lab-htw/iterative-annotate)., https://www.youtube.com/watch?v=CM9uhE8NN5E).
Authors: Chancharik Mitra, Brandon Huang, Tianning Chai, Zhiqiu Lin, Assaf Arbelle, Rogerio Feris, Leonid Karlinsky, Trevor Darrell, Deva Ramanan, Roei Herzig
Abstract: Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks such as image captioning or visual question answering. Despite strong performance, LMMs are not directly suited for foundational discriminative vision-language tasks (i.e., tasks requiring discrete label predictions) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for discriminative tasks is the extraction of useful features from generative models. To overcome this issue, we propose an approach for finding features in the model's latent space to more effectively leverage LMMs for discriminative tasks. Toward this end, we present Sparse Attention Vectors (SAVs) -- a finetuning-free method that leverages sparse attention head activations (fewer than 1\% of the heads) in LMMs as strong features for VL tasks. With only few-shot examples, SAVs demonstrate state-of-the-art performance compared to a variety of few-shot and finetuned baselines on a collection of discriminative tasks. Our experiments also imply that SAVs can scale in performance with additional examples and generalize to similar tasks, establishing SAVs as both effective and robust multimodal feature representations.
Authors: Yizhou Jin, Jiahui Zhu, Guodong Wang, Shiwei Li, Jinjin Zhang, Qingjie Liu, Xinyue Liu, Yunhong Wang
Abstract: Incremental anomaly detection sequentially recognizes abnormal regions in novel categories for dynamic industrial scenarios. This remains highly challenging due to knowledge overwriting and feature conflicts, leading to catastrophic forgetting. In this work, we propose ONER, an end-to-end ONline Experience Replay method, which efficiently mitigates catastrophic forgetting while adapting to new tasks with minimal cost. Specifically, our framework utilizes two types of experiences from past tasks: decomposed prompts and semantic prototypes, addressing both model parameter updates and feature optimization. The decomposed prompts consist of learnable components that assemble to produce attention-conditioned prompts. These prompts reuse previously learned knowledge, enabling model to learn novel tasks effectively. The semantic prototypes operate at both pixel and image levels, performing regularization in the latent feature space to prevent forgetting across various tasks. Extensive experiments demonstrate that our method achieves state-of-the-art performance in incremental anomaly detection with significantly reduced forgetting, as well as efficiently adapting to new categories with minimal costs. These results confirm the efficiency and stability of ONER, making it a powerful solution for real-world applications.
Authors: Shun Zhang, Xuechao Zou, Kai Li, Congyan Lang, Shiying Wang, Pin Tao, Tengfei Cao
Abstract: Fine-grained remote sensing image segmentation is essential for accurately identifying detailed objects in remote sensing images. Recently, vision transformer models (VTMs) pre-trained on large-scale datasets have demonstrated strong zero-shot generalization. However, directly applying them to specific tasks may lead to domain shift. We introduce a novel end-to-end learning paradigm combining knowledge guidance with domain refinement to enhance performance. We present two key components: the Feature Alignment Module (FAM) and the Feature Modulation Module (FMM). FAM aligns features from a CNN-based backbone with those from the pretrained VTM's encoder using channel transformation and spatial interpolation, and transfers knowledge via KL divergence and L2 normalization constraint. FMM further adapts the knowledge to the specific domain to address domain shift. We also introduce a fine-grained grass segmentation dataset and demonstrate, through experiments on two datasets, that our method achieves a significant improvement of 2.57 mIoU on the grass dataset and 3.73 mIoU on the cloud dataset. The results highlight the potential of combining knowledge transfer and domain adaptation to overcome domain-related challenges and data limitations. The project page is available at https://xavierjiezou.github.io/KTDA/.
Authors: Jui-Che Chiang, Hou-Ning Hu, Bo-Syuan Hou, Chia-Yu Tseng, Yu-Lun Liu, Min-Hung Chen, Yen-Yu Lin
Abstract: Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from visible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, ORFormer compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By integrating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLW and COFW.
Authors: Qingyan Bai, Hao Ouyang, Yinghao Xu, Qiuyu Wang, Ceyuan Yang, Ka Leong Cheng, Yujun Shen, Qifeng Chen
Abstract: As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.
Authors: Hao Wang, Cheng Deng, Zhidong Zhao
Abstract: Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works mostly focus on mining discriminative artifacts from vast amount of visual data. However, they usually lack the exploration of prior knowledge and rarely pay attention to the domain shift between training categories (e.g., natural and indoor objects) and testing ones (e.g., fine-grained human facial images), resulting in unsatisfactory detection performance. To address these issues, we propose a novel knowledge-guided prompt learning method for deepfake facial image detection. Specifically, we retrieve forgery-related prompts from large language models as expert knowledge to guide the optimization of learnable prompts. Besides, we elaborate test-time prompt tuning to alleviate the domain shift, achieving significant performance improvement and boosting the application in real-world scenarios. Extensive experiments on DeepFakeFaceForensics dataset show that our proposed approach notably outperforms state-of-the-art methods.
Authors: Gur Elkin, Ofir Itzhak Shahar, Yaniv Ohayon, Nadav Alali, Ohad Ben-Shahar
Abstract: Ancient artworks obtained in archaeological excavations usually suffer from a certain degree of fragmentation and physical degradation. Often, fragments of multiple artifacts from different periods or artistic styles could be found on the same site. With each fragment containing only partial information about its source, and pieces from different objects being mixed, categorizing broken artifacts based on their visual cues could be a challenging task, even for professionals. As classification is a common function of many machine learning models, the power of modern architectures can be harnessed for efficient and accurate fragment classification. In this work, we present a generalized deep-learning framework for predicting the artistic style of image fragments, achieving state-of-the-art results for pieces with varying styles and geometries.
Authors: Jinze Yu, Yiqun Wang, Zhengda Lu, Jianwei Guo, Yong Li, Hongxing Qin, Xiaopeng Zhang
Abstract: Current novel view synthesis tasks primarily rely on high-quality and clear images. However, in foggy scenes, scattering and attenuation can significantly degrade the reconstruction and rendering quality. Although NeRF-based dehazing reconstruction algorithms have been developed, their use of deep fully connected neural networks and per-ray sampling strategies leads to high computational costs. Moreover, NeRF's implicit representation struggles to recover fine details from hazy scenes. In contrast, recent advancements in 3D Gaussian Splatting achieve high-quality 3D scene reconstruction by explicitly modeling point clouds into 3D Gaussians. In this paper, we propose leveraging the explicit Gaussian representation to explain the foggy image formation process through a physically accurate forward rendering process. We introduce DehazeGS, a method capable of decomposing and rendering a fog-free background from participating media using only muti-view foggy images as input. We model the transmission within each Gaussian distribution to simulate the formation of fog. During this process, we jointly learn the atmospheric light and scattering coefficient while optimizing the Gaussian representation of the hazy scene. In the inference stage, we eliminate the effects of scattering and attenuation on the Gaussians and directly project them onto a 2D plane to obtain a clear view. Experiments on both synthetic and real-world foggy datasets demonstrate that DehazeGS achieves state-of-the-art performance in terms of both rendering quality and computational efficiency.
Authors: Bowei Zhang, Yi Zhang
Abstract: Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real applications, the large-scale datasets are not always available, and ViT performs worse than Convolutional Neural Networks (CNNs) if it is only trained on small scale dataset (called tiny dataset), since it requires large amount of training data to ensure its representational capacity. In this paper, a small-size ViT architecture with multi-scale self-attention mechanism and convolution blocks is presented (dubbed MSCViT) to model different scales of attention at each layer. Firstly, we introduced wavelet convolution, which selectively combines the high-frequency components obtained by frequency division with our convolution channel to extract local features. Then, a lightweight multi-head attention module is developed to reduce the number of tokens and computational costs. Finally, the positional encoding (PE) in the backbone is replaced by a local feature extraction module. Compared with the original ViT, it is parameter-efficient and is particularly suitable for tiny datasets. Extensive experiments have been conducted on tiny datasets, in which our model achieves an accuracy of 84.68% on CIFAR-100 with 14.0M parameters and 2.5 GFLOPs, without pre-training on large datasets.
Authors: Zhendong Zhang
Abstract: To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly enhancing computational efficiency. To further optimize this process, one might consider replacing standard attention with flash attention, which has proven to be more efficient in language models. However, a direct substitution is ineffective. Flash attention is designed for long sequences, whereas window attention deals with shorter sequences but must handle numerous of them in parallel. In this report, we present an optimized solution called Flash Window Attention, tailored specifically for window attention. Flash Window Attention improves attention computation efficiency by up to 300% and enhances end-to-end runtime efficiency by up to 30%. Our code is available online.
Authors: Ziyang Xie, Zhizheng Liu, Zhenghao Peng, Wayne Wu, Bolei Zhou
Abstract: Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world. Previous work has primarily focused on domain randomization and system identification to mitigate this gap. However, these methods are often limited by the inherent constraints of the simulation and graphics engines. In this work, we propose Vid2Sim, a novel framework that effectively bridges the sim2real gap through a scalable and cost-efficient real2sim pipeline for neural 3D scene reconstruction and simulation. Given a monocular video as input, Vid2Sim can generate photorealistic and physically interactable 3D simulation environments to enable the reinforcement learning of visual navigation agents in complex urban environments. Extensive experiments demonstrate that Vid2Sim significantly improves the performance of urban navigation in the digital twins and real world by 31.2% and 68.3% in success rate compared with agents trained with prior simulation methods.
Authors: Junlong Ren, Gangjian Zhang, Haifeng Sun, Hao Wang
Abstract: Temporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments. Existing methods generate augmented videos, where target moments are forced to have varying temporal locations. However, since the video lengths of the given datasets have small variations, only changing the temporal locations results in poor generalization ability in videos with varying lengths. In this paper, we propose a novel training framework complemented by diversified data augmentation and a domain discriminator. The data augmentation generates videos with various lengths and target moment locations to diversify temporal distributions. However, augmented videos inevitably exhibit distinct feature distributions which may introduce noise. To address this, we design a domain adaptation auxiliary task to diminish feature discrepancies between original and augmented videos. We also encourage the model to produce distinct predictions for videos with the same text queries but different moment locations to promote debiased training. Experiments on Charades-CD and ActivityNet-CD datasets demonstrate the effectiveness and generalization abilities of our method in multiple grounding structures, achieving state-of-the-art results.
Authors: Alejandro Lozano, Min Woo Sun, James Burgess, Liangyu Chen, Jeffrey J Nirschl, Jeffrey Gu, Ivan Lopez, Josiah Aklilu, Austin Wolfgang Katzer, Collin Chiu, Anita Rau, Xiaohan Wang, Yuhui Zhang, Alfred Seunghoon Song, Robert Tibshirani, Serena Yeung-Levy
Abstract: The development of vision-language models (VLMs) is driven by large-scale and diverse multimodal datasets. However, progress toward generalist biomedical VLMs is limited by the lack of annotated, publicly accessible datasets across biology and medicine. Existing efforts are restricted to narrow domains, missing the full diversity of biomedical knowledge encoded in scientific literature. To address this gap, we introduce BIOMEDICA, a scalable, open-source framework to extract, annotate, and serialize the entirety of the PubMed Central Open Access subset into an easy-to-use, publicly accessible dataset. Our framework produces a comprehensive archive with over 24 million unique image-text pairs from over 6 million articles. Metadata and expert-guided annotations are also provided. We demonstrate the utility and accessibility of our resource by releasing BMCA-CLIP, a suite of CLIP-style models continuously pre-trained on the BIOMEDICA dataset via streaming, eliminating the need to download 27 TB of data locally. On average, our models achieve state-of-the-art performance across 40 tasks - spanning pathology, radiology, ophthalmology, dermatology, surgery, molecular biology, parasitology, and cell biology - excelling in zero-shot classification with a 6.56% average improvement (as high as 29.8% and 17.5% in dermatology and ophthalmology, respectively), and stronger image-text retrieval, all while using 10x less compute. To foster reproducibility and collaboration, we release our codebase and dataset for the broader research community.
Authors: Xinyu Cai, Wentao Jiang, Runsheng Xu, Wenquan Zhao, Jiaqi Ma, Si Liu, Yikang Li
Abstract: Recently, Vehicle-to-Everything(V2X) cooperative perception has attracted increasing attention. Infrastructure sensors play a critical role in this research field; however, how to find the optimal placement of infrastructure sensors is rarely studied. In this paper, we investigate the problem of infrastructure sensor placement and propose a pipeline that can efficiently and effectively find optimal installation positions for infrastructure sensors in a realistic simulated environment. To better simulate and evaluate LiDAR placement, we establish a Realistic LiDAR Simulation library that can simulate the unique characteristics of different popular LiDARs and produce high-fidelity LiDAR point clouds in the CARLA simulator. Through simulating point cloud data in different LiDAR placements, we can evaluate the perception accuracy of these placements using multiple detection models. Then, we analyze the correlation between the point cloud distribution and perception accuracy by calculating the density and uniformity of regions of interest. Experiments show that when using the same number and type of LiDAR, the placement scheme optimized by our proposed method improves the average precision by 15%, compared with the conventional placement scheme in the standard lane scene. We also analyze the correlation between perception performance in the region of interest and LiDAR point cloud distribution and validate that density and uniformity can be indicators of performance. Both the RLS Library and related code will be released at https://github.com/PJLab-ADG/PCSim.
Authors: Ella Eidlin, Assaf Hoogi, Hila Rozen, Mohammad Badarne, Nathan S. Netanyahu
Abstract: Chest X-rays remain the primary diagnostic tool in emergency medicine, yet their limited ability to capture fine anatomical details can result in missed or delayed diagnoses. To address this, we introduce XVertNet, a novel deep-learning framework designed to enhance vertebral structure visualization in X-ray images significantly. Our framework introduces two key innovations: (1) An unsupervised learning architecture that eliminates reliance on manually labeled training data a persistent bottleneck in medical imaging, and (2) a dynamic self-tuned internal guidance mechanism featuring an adaptive feedback loop for real-time image optimization. Extensive validation across four major public datasets revealed that XVertNet outperforms state-of-the-art enhancement methods, as demonstrated by improvements in entropy scores, Tenengrad criterion values, the local phase coherence sharpness index (LPC-SI), and thetone mapped image quality index (TMQI). Furthermore, clinical validation conducted with two board-certified radiologists confirmed that the enhanced images enabled more sensitive detection of subtle vertebral fractures and degenerative changes. The unsupervised nature of XVertNet facilitates immediate clinical deployment without requiring additional training overhead. This innovation represents a transformative advancement in emergency radiology, providing a scalable and time-efficient solution to enhance diagnostic accuracy in high-pressure clinical environments.
Authors: Delong Liu, Haiwen Li, Zhicheng Zhao, Yuan Dong, Nikolaos V. Boulgouris
Abstract: The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and textual modalities. The prevailing methods map texts and images into unified embedding space for matching, while the intricate semantic correspondences between texts and images are still not effectively constructed. To address this issue, we propose a novel TIPR framework to build fine-grained interactions and alignment between person images and the corresponding texts. Specifically, via fine-tuning the Contrastive Language-Image Pre-training (CLIP) model, a visual-textual dual encoder is firstly constructed, to preliminarily align the image and text features. Secondly, a Text-guided Image Restoration (TIR) auxiliary task is proposed to map abstract textual entities to specific image regions, improving the alignment between local textual and visual embeddings. Additionally, a cross-modal triplet loss is presented to handle hard samples, and further enhance the model's discriminability for minor differences. Moreover, a pruning-based text data augmentation approach is proposed to enhance focus on essential elements in descriptions, thereby avoiding excessive model attention to less significant information. The experimental results show our proposed method outperforms state-of-the-art methods on three popular benchmark datasets, and the code will be made publicly available at https://github.com/Delong-liu-bupt/SEN.
Authors: Yan Fan, Yu Wang, Pengfei Zhu, Qinghua Hu
Abstract: Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem severely impacts the performance of SSCL. To address the limitations, we propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning, which leverages both semantic and structural information to achieve more stable knowledge distillation on unlabeled data and exhibit robustness against distribution bias. Firstly, we formalize a general model of structural distillation and design a dynamic graph construction for the continual learning progress. Next, we define a structure distillation vector and design a dynamic sub-graph distillation algorithm, which enables end-to-end training and adaptability to scale up tasks. The entire proposed method is adaptable to various CL methods and supervision settings. Finally, experiments conducted on three datasets CIFAR10, CIFAR100, and ImageNet-100, with varying supervision ratios, demonstrate the effectiveness of our proposed approach in mitigating the catastrophic forgetting problem in semi-supervised continual learning scenarios.
Authors: Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers
Abstract: Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high spatial resolution. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We address these shortcomings by learning a consistency model (CM) that efficiently and accurately downscales arbitrary ESM simulations without retraining in a zero-shot manner. Our approach yields probabilistic downscaled fields at a resolution only limited by the observational reference data. We show that the CM outperforms state-of-the-art diffusion models at a fraction of computational cost while maintaining high controllability on the downscaling task. Further, our method generalizes to climate states unseen during training without explicitly formulated physical constraints.
Authors: Ruixiang Jiang, Lingbo Liu, Changwen Chen
Abstract: Despite the demonstrated parameter efficiency of prompt-based multimodal fusion methods, their limited adaptivity and expressiveness often result in suboptimal performance compared to other tuning approaches. In this paper, we introduce the Mixture of Prompt Experts (MoPE), the first technique designed to overcome these limitations by decomposing standard prompts to capture instance-level features adaptively. Building on this decomposition, MoPE enhances prompt fusion's expressiveness by leveraging multimodal pairing priors to route the most effective prompt for each instance dynamically. Compared to vanilla prompting, our MoPE-based fusion method exhibits greater expressiveness, scaling more effectively with the training data and the overall number of trainable parameters. We also investigate regularization terms for expert routing, which lead to emergent expert specialization with enhanced adaptiveness and interpretablity. Extensive experiments across six multimodal datasets spanning four modalities demonstrate state-of-the-art performance for prompt fusion, matching or even surpassing the performance of fine-tuning while requiring only 0.8% of the trainable parameters. Project homepage: https://github.com/songrise/MoPE
Authors: Wasif Khan, Seowung Leem, Kyle B. See, Joshua K. Wong, Shaoting Zhang, Ruogu Fang
Abstract: Foundation models (FMs) are large-scale deep learning models that are developed using large datasets and self-supervised learning methods. These models serve as a base for different downstream tasks, including healthcare. FMs have been adopted with great success across various domains within healthcare. Existing healthcare-based surveys have not yet included all of these domains. Therefore, we provide a detailed survey of FMs in healthcare. We focus on the history, learning strategies, flagship models, applications, and challenges of FMs. We explore how FMs such as the BERT and GPT families are reshaping various healthcare domains, including clinical large language models, medical image analysis, and omics. Furthermore, we provide a detailed taxonomy of healthcare applications facilitated by FMs, such as clinical NLP, medical computer vision, graph learning, and other biology-related tasks. Despite the promising opportunities FMs provide, they also have several associated challenges, which are explained in detail. We also outline open research issues and potential lessons learned to provide researchers and practitioners with insights into the capabilities of FMs in healthcare to advance their deployment and mitigate associated risks.
Authors: Zhiqi Bu, Shiyun Xu
Abstract: We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, our method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive experiments on language and vision tasks (e.g. GPT and ResNet) to showcase that GeN optimizers match the state-of-the-art performance, which was achieved with carefully tuned learning rate schedulers.
Authors: Linxuan Han, Sa Xiao, Zimeng Li, Haidong Li, Xiuchao Zhao, Yeqing Han, Fumin Guo, Xin Zhou
Abstract: Multi-modal magnetic resonance imaging (MRI) provides information of lesions for computer-aided diagnosis from different views. Deep learning algorithms are suitable for identifying specific anatomical structures, segmenting lesions, and classifying diseases. Manual labels are limited due to the high expense, which hinders further improvement of accuracy. Self-supervised learning, particularly masked image modeling (MIM), has shown promise in utilizing unlabeled data. However, we spot model collapse when applying MIM to multi-modal MRI datasets. The performance of downstream tasks does not see any improvement following the collapsed model. To solve model collapse, we analyze and address it in two types: complete collapse and dimensional collapse. We find complete collapse occurs because the collapsed loss value in multi-modal MRI datasets falls below the normally converged loss value. Based on this, the hybrid mask pattern (HMP) masking strategy is introduced to elevate the collapsed loss above the normally converged loss value and avoid complete collapse. Additionally, we reveal that dimensional collapse stems from insufficient feature uniformity in MIM. We mitigate dimensional collapse by introducing the pyramid barlow twins (PBT) module as an explicit regularization method. Overall, we construct the enhanced MIM (E-MIM) with HMP and PBT module to avoid model collapse multi-modal MRI. Experiments are conducted on three multi-modal MRI datasets to validate the effectiveness of our approach in preventing both types of model collapse. By preventing model collapse, the training of the model becomes more stable, resulting in a decent improvement in performance for segmentation and classification tasks. The code is available at https://github.com/LinxuanHan/E-MIM.
Authors: Sai Prasanna, Daniel Honerkamp, Kshitij Sirohi, Tim Welschehold, Wolfram Burgard, Abhinav Valada
Abstract: Embodied AI has made significant progress acting in unexplored environments. However, tasks such as object search have largely focused on efficient policy learning. In this work, we identify several gaps in current search methods: They largely focus on dated perception models, neglect temporal aggregation, and transfer from ground truth directly to noisy perception at test time, without accounting for the resulting overconfidence in the perceived state. We address the identified problems through calibrated perception probabilities and uncertainty across aggregation and found decisions, thereby adapting the models for sequential tasks. The resulting methods can be directly integrated with pretrained models across a wide family of existing search approaches at no additional training cost. We perform extensive evaluations of aggregation methods across both different semantic perception models and policies, confirming the importance of calibrated uncertainties in both the aggregation and found decisions. We make the code and trained models available at https://semantic-search.cs.uni-freiburg.de.
Authors: Yosuke Yamagishi, Shouhei Hanaoka, Tomohiro Kikuchi, Takahiro Nakao, Yuta Nakamura, Yukihiro Nomura, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe
Abstract: Objectives: To evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, and to investigate the effects of prompt settings on segmentation results. Materials and Methods: In this retrospective study, we used a subset of the TotalSegmentator CT dataset from eight institutions to assess SAM 2's ability to segment eight abdominal organs. Segmentation was initiated from three different z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the Dice similarity coefficient (DSC). We also analyzed the impact of "negative prompts," which explicitly exclude certain regions from the segmentation process, on accuracy. Results: 123 patients (mean age, 60.7 \pm 15.5 years; 63 men, 60 women) were evaluated. As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean DSCs as follows: liver 0.821 \pm 0.192, right kidney 0.862 \pm 0.212, left kidney 0.870 \pm 0.154, and spleen 0.891 \pm 0.131. Smaller organs showed lower performance: gallbladder 0.531 \pm 0.291, pancreas 0.361 \pm 0.197, and adrenal glands, right 0.203 \pm 0.222, left 0.308 \pm 0.234. The initial slice for segmentation and the use of negative prompts significantly influenced the results. By removing negative prompts from the input, the DSCs significantly decreased for six organs. Conclusion: SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs. Performance was significantly influenced by input negative prompts and initial slice selection, highlighting the importance of optimizing these factors.
Authors: Hamza Kheddar
Abstract: With significant advancements in Transformers LLMs, NLP has extended its reach into many research fields due to its enhanced capabilities in text generation and user interaction. One field benefiting greatly from these advancements is cybersecurity. In cybersecurity, many parameters that need to be protected and exchanged between senders and receivers are in the form of text and tabular data, making NLP a valuable tool in enhancing the security measures of communication protocols. This survey paper provides a comprehensive analysis of the utilization of Transformers and LLMs in cyber-threat detection systems. The methodology of paper selection and bibliometric analysis is outlined to establish a rigorous framework for evaluating existing research. The fundamentals of Transformers are discussed, including background information on various cyber-attacks and datasets commonly used in this field. The survey explores the application of Transformers in IDSs, focusing on different architectures such as Attention-based models, LLMs like BERT and GPT, CNN/LSTM-Transformer hybrids, emerging approaches like ViTs, among others. Furthermore, it explores the diverse environments and applications where Transformers and LLMs-based IDS have been implemented, including computer networks, IoT devices, critical infrastructure protection, cloud computing, SDN, as well as in autonomous vehicles. The paper also addresses research challenges and future directions in this area, identifying key issues such as interpretability, scalability, and adaptability to evolving threats, and more. Finally, the conclusion summarizes the findings and highlights the significance of Transformers and LLMs in enhancing cyber-threat detection capabilities, while also outlining potential avenues for further research and development.
Authors: Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu
Abstract: Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance, particularly in intricate web environments and long-horizon tasks. To address these limitations, we present ExACT, an approach to combine test-time search and self-learning to build o1-like models for agentic applications. We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore decision space on the fly. R-MCTS extends traditional MCTS by 1) incorporating contrastive reflection, allowing agents to learn from past interactions and dynamically improve their search efficiency; and 2) using multi-agent debate for reliable state evaluation. Next, we introduce Exploratory Learning, a novel learning strategy to teach agents to search at inference time without relying on any external search algorithms. On the challenging VisualWebArena benchmark, our GPT-4o based R-MCTS agent achieves a 6% to 30% relative improvement across various tasks compared to the previous state-of-the-art. Additionally, we show that the knowledge and experience gained from test-time search can be effectively transferred back to GPT-4o via fine-tuning. After Exploratory Learning, GPT-4o 1) demonstrates the ability to explore the environment, evaluate a state, and backtrack to viable ones when it detects that the current state cannot lead to success, and 2) matches 87% of R-MCTS's performance while using significantly less compute. Notably, our work demonstrates the compute scaling properties in both training - data collection with R-MCTS - and testing time. These results suggest a promising research direction to enhance VLMs' capabilities for agentic applications via test-time search and self-learning.
Authors: Zixuan Wang, Chi-Keung Tang, Yu-Wing Tai
Abstract: We introduce Audio-Agent, a multimodal framework for audio generation, editing and composition based on text or video inputs. Conventional approaches for text-to-audio (TTA) tasks often make single-pass inferences from text descriptions. While straightforward, this design struggles to produce high-quality audio when given complex text conditions. In our method, we utilize a pre-trained TTA diffusion network as the audio generation agent to work in tandem with GPT-4, which decomposes the text condition into atomic, specific instructions and calls the agent for audio generation. In doing so, Audio-Agent can generate high-quality audio that is closely aligned with the provided text or video exhibiting complex and multiple events, while supporting variable-length and variable-volume generation. For video-to-audio (VTA) tasks, most existing methods require training a timestamp detector to synchronize video events with the generated audio, a process that can be tedious and time-consuming. Instead, we propose a simpler approach by fine-tuning a pre-trained Large Language Model (LLM), e.g., Gemma2-2B-it, to obtain both semantic and temporal conditions that bridge the video and audio modality. Consequently, our framework contributes a comprehensive solution for both TTA and VTA tasks without substantial computational overhead in training.
Authors: Putri A. van der Linden, Alejandro Garc\'ia-Castellanos, Sharvaree Vadgama, Thijs P. Kuipers, Erik J. Bekkers
Abstract: Group equivariance has emerged as a valuable inductive bias in deep learning, enhancing generalization, data efficiency, and robustness. Classically, group equivariant methods require the groups of interest to be known beforehand, which may not be realistic for real-world data. Additionally, baking in fixed group equivariance may impose overly restrictive constraints on model architecture. This highlights the need for methods that can dynamically discover and apply symmetries as soft constraints. For neural network architectures, equivariance is commonly achieved through group transformations of a canonical weight tensor, resulting in weight sharing over a given group $G$. In this work, we propose to learn such a weight-sharing scheme by defining a collection of learnable doubly stochastic matrices that act as soft permutation matrices on canonical weight tensors, which can take regular group representations as a special case. This yields learnable kernel transformations that are jointly optimized with downstream tasks. We show that when the dataset exhibits strong symmetries, the permutation matrices will converge to regular group representations and our weight-sharing networks effectively become regular group convolutions. Additionally, the flexibility of the method enables it to effectively pick up on partial symmetries.
Authors: Tal Zeevi, Ravid Shwartz-Ziv, Yann LeCun, Lawrence H. Staib, John A. Onofrey
Abstract: Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forward passes with dropout during inference. However, using static dropout rates across all layers and inputs can lead to suboptimal uncertainty estimates, as it fails to adapt to the varying characteristics of individual inputs and network layers. Existing approaches optimize dropout rates during training using labeled data, resulting in fixed inference-time parameters that cannot adjust to new data distributions, compromising uncertainty estimates in Monte Carlo simulations. In this paper, we propose Rate-In, an algorithm that dynamically adjusts dropout rates during inference by quantifying the information loss induced by dropout in each layer's feature maps. By treating dropout as controlled noise injection and leveraging information-theoretic principles, Rate-In adapts dropout rates per layer and per input instance without requiring ground truth labels. By quantifying the functional information loss in feature maps, we adaptively tune dropout rates to maintain perceptual quality across diverse medical imaging tasks and architectural configurations. Our extensive empirical study on synthetic data and real-world medical imaging tasks demonstrates that Rate-In improves calibration and sharpens uncertainty estimates compared to fixed or heuristic dropout rates without compromising predictive performance. Rate-In offers a practical, unsupervised, inference-time approach to optimizing dropout for more reliable predictive uncertainty estimation in critical applications.
Authors: Ayush Deshmukh
Abstract: The global outbreak of the Mpox virus, classified as a Public Health Emergency of International Concern (PHEIC) by the World Health Organization, presents significant diagnostic challenges due to its visual similarity to other skin lesion diseases. Traditional diagnostic methods for Mpox, which rely on clinical symptoms and laboratory tests, are slow and labor intensive. Deep learning-based approaches for skin lesion classification offer a promising alternative. However, developing a model that balances efficiency with accuracy is crucial to ensure reliable and timely diagnosis without compromising performance. This study introduces the Cascaded Atrous Group Attention (CAGA) framework to address these challenges, combining the Cascaded Atrous Attention module and the Cascaded Group Attention mechanism. The Cascaded Atrous Attention module utilizes dilated convolutions and cascades the outputs to enhance multi-scale representation. This is integrated into the Cascaded Group Attention mechanism, which reduces redundancy in Multi-Head Self-Attention. By integrating the Cascaded Atrous Group Attention module with EfficientViT-L1 as the backbone architecture, this approach achieves state-of-the-art performance, reaching an accuracy of 98% on the Mpox Close Skin Image (MCSI) dataset while reducing model parameters by 37.5% compared to the original EfficientViT-L1. The model's robustness is demonstrated through extensive validation on two additional benchmark datasets, where it consistently outperforms existing approaches.
Authors: Chia-Ming Lee, Yu-Fan Lin, Yu-Hao Ho, Li-Wei Kang, Chih-Chung Hsu
Abstract: Hyperspectral image (HSI) fusion addresses the challenge of reconstructing High-Resolution HSIs (HR-HSIs) from High-Resolution Multispectral images (HR-MSIs) and Low-Resolution HSIs (LR-HSIs), a critical task given the high costs and hardware limitations associated with acquiring high-quality HSIs. While existing methods leverage spatial and spectral relationships, they often suffer from limited receptive fields and insufficient feature utilization, leading to suboptimal performance. Furthermore, the scarcity of high-quality HSI data highlights the importance of efficient data utilization to maximize reconstruction quality. To address these issues, we propose HyFusion, a novel Dual-Coupled Network (DCN) framework designed to enhance cross-domain feature extraction and enable effective feature map reusing. The framework first processes HR-MSI and LR-HSI inputs through specialized subnetworks that mutually enhance each other during feature extraction, preserving complementary spatial and spectral details. At its core, HyFusion utilizes an Enhanced Reception Field Block (ERFB), which combines shifting-window attention and dense connections to expand the receptive field, effectively capturing long-range dependencies while minimizing information loss. Extensive experiments demonstrate that HyFusion achieves state-of-the-art performance in HR-MSI/LR-HSI fusion, significantly improving reconstruction quality while maintaining a compact model size and computational efficiency. By integrating enhanced receptive fields and feature map reusing into a coupled network architecture, HyFusion provides a practical and effective solution for HSI fusion in resource-constrained scenarios, setting a new benchmark in hyperspectral imaging. Our code will be publicly available.
Authors: Du Chen, Liyi Chen, Zhengqiang Zhang, Lei Zhang
Abstract: Equipped with the continuous representation capability of Multi-Layer Perceptron (MLP), Implicit Neural Representation (INR) has been successfully employed for Arbitrary-scale Super-Resolution (ASR). However, the limited receptive field of the linear layers in MLP restricts the representation capability of INR, while it is computationally expensive to query the MLP numerous times to render each pixel. Recently, Gaussian Splatting (GS) has shown its advantages over INR in both visual quality and rendering speed in 3D tasks, which motivates us to explore whether GS can be employed for the ASR task. However, directly applying GS to ASR is exceptionally challenging because the original GS is an optimization-based method through overfitting each single scene, while in ASR we aim to learn a single model that can generalize to different images and scaling factors. We overcome these challenges by developing two novel techniques. Firstly, to generalize GS for ASR, we elaborately design an architecture to predict the corresponding image-conditioned Gaussians of the input low-resolution image in a feed-forward manner. Secondly, we implement an efficient differentiable 2D GPU/CUDA-based scale-aware rasterization to render super-resolved images by sampling discrete RGB values from the predicted contiguous Gaussians. Via end-to-end training, our optimized network, namely GSASR, can perform ASR for any image and unseen scaling factors. Extensive experiments validate the effectiveness of our proposed method. The project page can be found at \url{https://mt-cly.github.io/GSASR.github.io/}.