Authors: Han Sun, Rui Gong, Ismail Nejjar, Olga Fink
Abstract: Current unsupervised domain adaptation (UDA) methods for semantic segmentation typically assume identical class labels between the source and target domains. This assumption ignores the label-level domain gap, which is common in real-world scenarios, thus limiting their ability to identify finer-grained or novel categories without requiring extensive manual annotation. A promising direction to address this limitation lies in recent advancements in foundation models, which exhibit strong generalization abilities due to their rich prior knowledge. However, these models often struggle with domain-specific nuances and underrepresented fine-grained categories. To address these challenges, we introduce DynAlign, a framework that integrates UDA with foundation models to bridge both the image-level and label-level domain gaps. Our approach leverages prior semantic knowledge to align source categories with target categories that can be novel, more fine-grained, or named differently (e.g., vehicle to {car, truck, bus}). Foundation models are then employed for precise segmentation and category reassignment. To further enhance accuracy, we propose a knowledge fusion approach that dynamically adapts to varying scene contexts. DynAlign generates accurate predictions in a new target label space without requiring any manual annotations, allowing seamless adaptation to new taxonomies through either model retraining or direct inference. Experiments on the street scene semantic segmentation benchmarks GTA to Mapillary Vistas and GTA to IDD validate the effectiveness of our approach, achieving a significant improvement over existing methods. Our code will be publicly available.
Authors: Wei Chow, Jiageng Mao, Boyi Li, Daniel Seita, Vitor Guizilini, Yue Wang
Abstract: Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 100,000 entries of interleaved video-image-text data, categorized into four major domains: physical object properties, physical object relationships, physical scene understanding, and physics-based dynamics, further divided into 19 subclasses and 8 distinct capability dimensions. Our extensive experiments, conducted on 75 representative VLMs, reveal that while these models excel in common-sense reasoning, they struggle with understanding the physical world -- likely due to the absence of physical knowledge in their training data and the lack of embedded physical priors. To tackle the shortfall, we introduce PhysAgent, a novel framework that combines the generalization strengths of VLMs with the specialized expertise of vision models, significantly enhancing VLMs' physical understanding across a variety of tasks, including an 18.4\% improvement on GPT-4o. Furthermore, our results demonstrate that enhancing VLMs' physical world understanding capabilities can help embodied agents such as MOKA. We believe that PhysBench and PhysAgent offer valuable insights and contribute to bridging the gap between VLMs and physical world understanding.
Authors: Philip Hughes, Larry Burns, Luke Adams
Abstract: Semantic segmentation plays a crucial role in enabling machines to understand and interpret visual scenes at a pixel level. While traditional segmentation methods have achieved remarkable success, their generalization to diverse scenes and unseen object categories remains limited. Recent advancements in large language models (LLMs) offer a promising avenue for bridging visual and textual modalities, providing a deeper understanding of semantic relationships. In this paper, we propose LangSeg, a novel LLM-guided semantic segmentation method that leverages context-sensitive, fine-grained subclass descriptors generated by LLMs. Our framework integrates these descriptors with a pre-trained Vision Transformer (ViT) to achieve superior segmentation performance without extensive model retraining. We evaluate LangSeg on two challenging datasets, ADE20K and COCO-Stuff, where it outperforms state-of-the-art models, achieving up to a 6.1% improvement in mean Intersection over Union (mIoU). Additionally, we conduct a comprehensive ablation study and human evaluation to validate the effectiveness of our method in real-world scenarios. The results demonstrate that LangSeg not only excels in semantic understanding and contextual alignment but also provides a flexible and efficient framework for language-guided segmentation tasks. This approach opens up new possibilities for interactive and domain-specific segmentation applications.
Authors: Weijie He, Yuwei Zhang, Ting Xu, Tai An, Yingbin Liang, Bo Zhang
Abstract: Deep learning has emerged as a transformative approach for solving complex pattern recognition and object detection challenges. This paper focuses on the application of a novel detection framework based on the RT-DETR model for analyzing intricate image data, particularly in areas such as diabetic retinopathy detection. Diabetic retinopathy, a leading cause of vision loss globally, requires accurate and efficient image analysis to identify early-stage lesions. The proposed RT-DETR model, built on a Transformer-based architecture, excels at processing high-dimensional and complex visual data with enhanced robustness and accuracy. Comparative evaluations with models such as YOLOv5, YOLOv8, SSD, and DETR demonstrate that RT-DETR achieves superior performance across precision, recall, mAP50, and mAP50-95 metrics, particularly in detecting small-scale objects and densely packed targets. This study underscores the potential of Transformer-based models like RT-DETR for advancing object detection tasks, offering promising applications in medical imaging and beyond.
Authors: Payal Kamboj, Ayan Banerjee, Bin Xu, Sandeep Gupta
Abstract: Rare events, due to their infrequent occurrences, do not have much data, and hence deep learning techniques fail in estimating the distribution for such data. Open-vocabulary models represent an innovative approach to image classification. Unlike traditional models, these models classify images into any set of categories specified with natural language prompts during inference. These prompts usually comprise manually crafted templates (e.g., 'a photo of a {}') that are filled in with the names of each category. This paper introduces a simple yet effective method for generating highly accurate and contextually descriptive prompts containing discriminative characteristics. Rare event detection, especially in medicine, is more challenging due to low inter-class and high intra-class variability. To address these, we propose a novel approach that uses domain-specific expert knowledge on rare events to generate customized and contextually relevant prompts, which are then used by large language models for image classification. Our zero-shot, privacy-preserving method enhances rare event classification without additional training, outperforming state-of-the-art techniques.
Authors: Georgios Andreadis, Eduard Ruiz Munn\'e, Thomas H. W. B\"ack, Peter A. N. Bosman, Tanja Alderliesten
Abstract: When choosing a deformable image registration (DIR) approach for images with large deformations and content mismatch, the realism of found transformations often needs to be traded off against the required runtime. DIR approaches using deep learning (DL) techniques have shown remarkable promise in instantly predicting a transformation. However, on difficult registration problems, the realism of these transformations can fall short. DIR approaches using biomechanical, finite element modeling (FEM) techniques can find more realistic transformations, but tend to require much longer runtimes. This work proposes the first hybrid approach to combine them, with the aim of getting the best of both worlds. This hybrid approach, called DL-MOREA, combines a recently introduced multi-objective DL-based DIR approach which leverages the VoxelMorph framework, called DL-MODIR, with MOREA, an evolutionary algorithm-based, multi-objective DIR approach in which a FEM-like biomechanical mesh transformation model is used. In our proposed hybrid approach, the DL results are used to smartly initialize MOREA, with the aim of more efficiently optimizing its mesh transformation model. We empirically compare DL-MOREA against its components, DL-MODIR and MOREA, on CT scan pairs capturing large bladder filling differences of 15 cervical cancer patients. While MOREA requires a median runtime of 45 minutes, DL-MOREA can already find high-quality transformations after 5 minutes. Compared to the DL-MODIR transformations, the transformations found by DL-MOREA exhibit far less folding and improve or preserve the bladder contour distance error.
Authors: Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou, Cheng-Yen Yang, Hsiang-Wei Huang, Jenq-Neng Hwang
Abstract: Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models.
Authors: Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli
Abstract: The rising popularity of large foundation models has led to a heightened demand for parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), which offer performance comparable to full model fine-tuning while requiring only a few additional parameters tailored to the specific base model. When such base models are deprecated and replaced, all associated LoRA modules must be retrained, requiring access to either the original training data or a substantial amount of synthetic data that mirrors the original distribution. However, the original data is often inaccessible due to privacy or licensing issues, and generating synthetic data may be impractical and insufficiently representative. These factors complicate the fine-tuning process considerably. To address this challenge, we introduce a new adapter, Cross-Model Low-Rank Adaptation (LoRA-X), which enables the training-free transfer of LoRA parameters across source and target models, eliminating the need for original or synthetic training data. Our approach imposes the adapter to operate within the subspace of the source base model. This constraint is necessary because our prior knowledge of the target model is limited to its weights, and the criteria for ensuring the adapter's transferability are restricted to the target base model's weights and subspace. To facilitate the transfer of LoRA parameters of the source model to a target model, we employ the adapter only in the layers of the target model that exhibit an acceptable level of subspace similarity. Our extensive experiments demonstrate the effectiveness of LoRA-X for text-to-image generation, including Stable Diffusion v1.5 and Stable Diffusion XL.
Authors: Abi Aryaza, Novanto Yudistira, Tibyani
Abstract: Marine debris poses significant harm to marine life due to substances like microplastics, polychlorinated biphenyls, and pesticides, which damage habitats and poison organisms. Human-based solutions, such as diving, are increasingly ineffective in addressing this issue. Autonomous underwater vehicles (AUVs) are being developed for efficient sea garbage collection, with the choice of object detection architecture being critical. This research employs the YOLOv4 model for real-time detection of marine debris using the Trash-ICRA 19 dataset, consisting of 7683 images at 480x320 pixels. Various modifications-pretrained models, training from scratch, mosaic augmentation, layer freezing, YOLOv4-tiny, and channel pruning-are compared to enhance architecture efficiency. Channel pruning significantly improves detection speed, increasing the base YOLOv4 frame rate from 15.19 FPS to 19.4 FPS, with only a 1.2% drop in mean Average Precision, from 97.6% to 96.4%.
Authors: Long Peng, Xin Di, Zhanfeng Feng, Wenbo Li, Renjing Pei, Yang Wang, Xueyang Fu, Yang Cao, Zheng-Jun Zha
Abstract: Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (\textit{e.g.}, 4K and 8K), achieving a balance between restoration quality and computational efficiency has become increasingly critical. Existing methods, primarily based on CNNs, Transformers, or their hybrid approaches, apply uniform deep representation extraction across the image. However, these methods often struggle to effectively model long-range dependencies and largely overlook the spatial characteristics of image degradation (regions with richer textures tend to suffer more severe damage), making it hard to achieve the best trade-off between restoration quality and efficiency. To address these issues, we propose a novel texture-aware image restoration method, TAMambaIR, which simultaneously perceives image textures and achieves a trade-off between performance and efficiency. Specifically, we introduce a novel Texture-Aware State Space Model, which enhances texture awareness and improves efficiency by modulating the transition matrix of the state-space equation and focusing on regions with complex textures. Additionally, we design a {Multi-Directional Perception Block} to improve multi-directional receptive fields while maintaining low computational overhead. Extensive experiments on benchmarks for image super-resolution, deraining, and low-light image enhancement demonstrate that TAMambaIR achieves state-of-the-art performance with significantly improved efficiency, establishing it as a robust and efficient framework for image restoration.
Authors: Xiaolei Liu, Yan Sun, Mark Nixon
Abstract: Gait recognition is an emerging identification technology that distinguishes individuals at long distances by analyzing individual walking patterns. Traditional techniques rely heavily on large-scale labeled datasets, which incurs high costs and significant labeling challenges. Recently, researchers have explored unsupervised gait recognition with clustering-based unsupervised domain adaptation methods and achieved notable success. However, these methods directly use pseudo-label generated by clustering and neglect pseudolabel noise caused by domain differences, which affects the effect of the model training process. To mitigate these issues, we proposed a novel model called GaitDCCR, which aims to reduce the influence of noisy pseudo labels on clustering and model training. Our approach can be divided into two main stages: clustering and training stage. In the clustering stage, we propose Dynamic Cluster Parameters (DCP) and Dynamic Weight Centroids (DWC) to improve the efficiency of clustering and obtain reliable cluster centroids. In the training stage, we employ the classical teacher-student structure and propose Confidence-based Pseudo-label Refinement (CPR) and Contrastive Teacher Module (CTM) to encourage noisy samples to converge towards clusters containing their true identities. Extensive experiments on public gait datasets have demonstrated that our simple and effective method significantly enhances the performance of unsupervised gait recognition, laying the foundation for its application in the real-world.The code is available at https://github.com/YanSun-github/GaitDCCR
Authors: Wenfeng Lin, Jiangchuan Wei, Boyuan Liu, Yichen Zhang, Shiyue Yan, Mingyu Guo
Abstract: Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-video (T2V) applications. However, the computational demands of diffusion models pose significant challenges, particularly in generating high-resolution videos with high frame rates. In this paper, we propose CascadeV, a cascaded latent diffusion model (LDM), that is capable of producing state-of-the-art 2K resolution videos. Experiments demonstrate that our cascaded model achieves a higher compression ratio, substantially reducing the computational challenges associated with high-quality video generation. We also implement a spatiotemporal alternating grid 3D attention mechanism, which effectively integrates spatial and temporal information, ensuring superior consistency across the generated video frames. Furthermore, our model can be cascaded with existing T2V models, theoretically enabling a 4$\times$ increase in resolution or frames per second without any fine-tuning. Our code is available at https://github.com/bytedance/CascadeV.
Authors: Di Qi, Tong Yang, Beining Wang, Xiangyu Zhang, Wenqiang Zhang
Abstract: We present a novel framework for dynamic radiance field prediction given monocular video streams. Unlike previous methods that primarily focus on predicting future frames, our method goes a step further by generating explicit 3D representations of the dynamic scene. The framework builds on two core designs. First, we adopt an ego-centric unbounded triplane to explicitly represent the dynamic physical world. Second, we develop a 4D-aware transformer to aggregate features from monocular videos to update the triplane. Coupling these two designs enables us to train the proposed model with large-scale monocular videos in a self-supervised manner. Our model achieves top results in dynamic radiance field prediction on NVIDIA dynamic scenes, demonstrating its strong performance on 4D physical world modeling. Besides, our model shows a superior generalizability to unseen scenarios. Notably, we find that our approach emerges capabilities for geometry and semantic learning.
Authors: Anurag Vaidya, Andrew Zhang, Guillaume Jaume, Andrew H. Song, Tong Ding, Sophia J. Wagner, Ming Y. Lu, Paul Doucet, Harry Robertson, Cristina Almagro-Perez, Richard J. Chen, Dina ElHarouni, Georges Ayoub, Connor Bossi, Keith L. Ligon, Georg Gerber, Long Phi Le, Faisal Mahmood
Abstract: Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances, foundation models are still limited in their ability to encode the entire gigapixel whole-slide images without additional training and often lack complementary multimodal data. Here, we introduce Threads, a slide-level foundation model capable of generating universal representations of whole-slide images of any size. Threads was pre-trained using a multimodal learning approach on a diverse cohort of 47,171 hematoxylin and eosin (H&E)-stained tissue sections, paired with corresponding genomic and transcriptomic profiles - the largest such paired dataset to be used for foundation model development to date. This unique training paradigm enables Threads to capture the tissue's underlying molecular composition, yielding powerful representations applicable to a wide array of downstream tasks. In extensive benchmarking across 54 oncology tasks, including clinical subtyping, grading, mutation prediction, immunohistochemistry status determination, treatment response prediction, and survival prediction, Threads outperformed all baselines while demonstrating remarkable generalizability and label efficiency. It is particularly well suited for predicting rare events, further emphasizing its clinical utility. We intend to make the model publicly available for the broader community.
Authors: Seyyed Taghi Ataei, Parviz Mohammad Zadeh, Saeid Ataei
Abstract: This study addresses the urgent need for efficient and accurate damage detection in wind turbine structures, a crucial component of renewable energy infrastructure. Traditional inspection methods, such as manual assessments and non-destructive testing (NDT), are often costly, time-consuming, and prone to human error. To tackle these challenges, this research investigates advanced deep learning algorithms for vision-based structural health monitoring (SHM). A dataset of wind turbine surface images, featuring various damage types and pollution, was prepared and augmented for enhanced model training. Three algorithms-YOLOv7, its lightweight variant, and Faster R-CNN- were employed to detect and classify surface damage. The models were trained and evaluated on a dataset split into training, testing, and evaluation subsets (80%-10%-10%). Results indicate that YOLOv7 outperformed the others, achieving 82.4% mAP@50 and high processing speed, making it suitable for real-time inspections. By optimizing hyperparameters like learning rate and batch size, the models' accuracy and efficiency improved further. YOLOv7 demonstrated significant advancements in detection precision and execution speed, especially for real-time applications. However, challenges such as dataset limitations and environmental variability were noted, suggesting future work on segmentation methods and larger datasets. This research underscores the potential of vision-based deep learning techniques to transform SHM practices by reducing costs, enhancing safety, and improving reliability, thus contributing to the sustainable maintenance of critical infrastructure and supporting the longevity of wind energy systems.
Authors: Mingyuan Li, Tong Jia, Hui Lu, Bowen Ma, Hao Wang, Dongyue Chen
Abstract: Prohibited item detection based on X-ray images is one of the most effective security inspection methods. However, the foreground-background feature coupling caused by the overlapping phenomenon specific to X-ray images makes general detectors designed for natural images perform poorly. To address this issue, we propose a Category Semantic Prior Contrastive Learning (CSPCL) mechanism, which aligns the class prototypes perceived by the classifier with the content queries to correct and supplement the missing semantic information responsible for classification, thereby enhancing the model sensitivity to foreground features.To achieve this alignment, we design a specific contrastive loss, CSP loss, which includes Intra-Class Truncated Attraction (ITA) loss and Inter-Class Adaptive Repulsion (IAR) loss, and outperforms classic N-pair loss and InfoNCE loss. Specifically, ITA loss leverages class prototypes to attract intra-class category-specific content queries while preserving necessary distinctiveness. IAR loss utilizes class prototypes to adaptively repel inter-class category-specific content queries based on the similarity between class prototypes, helping disentangle features of similar categories.CSPCL is general and can be easily integrated into Deformable DETR-based models. Extensive experiments on the PIXray and OPIXray datasets demonstrate that CSPCL significantly enhances the performance of various state-of-the-art models without increasing complexity.The code will be open source once the paper is accepted.
Authors: Parth Padalkar, Jaeseong Lee, Shiyi Wei, Gopal Gupta
Abstract: There has been significant focus on creating neuro-symbolic models for interpretable image classification using Convolutional Neural Networks (CNNs). These methods aim to replace the CNN with a neuro-symbolic model consisting of the CNN, which is used as a feature extractor, and an interpretable rule-set extracted from the CNN itself. While these approaches provide interpretability through the extracted rule-set, they often compromise accuracy compared to the original CNN model. In this paper, we identify the root cause of this accuracy loss as the post-training binarization of filter activations to extract the rule-set. To address this, we propose a novel sparsity loss function that enables class-specific filter binarization during CNN training, thus minimizing information loss when extracting the rule-set. We evaluate several training strategies with our novel sparsity loss, analyzing their effectiveness and providing guidance on their appropriate use. Notably, we set a new benchmark, achieving a 9% improvement in accuracy and a 53% reduction in rule-set size on average, compared to the previous SOTA, while coming within 3% of the original CNN's accuracy. This highlights the significant potential of interpretable neuro-symbolic models as viable alternatives to black-box CNNs.
Authors: Shengyuan Liu, Zhen Chen, Qiushi Yang, Weihao Yu, Di Dong, Jiancong Hu, Yixuan Yuan
Abstract: Automated diagnostic systems (ADS) have shown significant potential in the early detection of polyps during endoscopic examinations, thereby reducing the incidence of colorectal cancer. However, due to high annotation costs and strict privacy concerns, acquiring high-quality endoscopic images poses a considerable challenge in the development of ADS. Despite recent advancements in generating synthetic images for dataset expansion, existing endoscopic image generation algorithms failed to accurately generate the details of polyp boundary regions and typically required medical priors to specify plausible locations and shapes of polyps, which limited the realism and diversity of the generated images. To address these limitations, we present Polyp-Gen, the first full-automatic diffusion-based endoscopic image generation framework. Specifically, we devise a spatial-aware diffusion training scheme with a lesion-guided loss to enhance the structural context of polyp boundary regions. Moreover, to capture medical priors for the localization of potential polyp areas, we introduce a hierarchical retrieval-based sampling strategy to match similar fine-grained spatial features. In this way, our Polyp-Gen can generate realistic and diverse endoscopic images for building reliable ADS. Extensive experiments demonstrate the state-of-the-art generation quality, and the synthetic images can improve the downstream polyp detection task. Additionally, our Polyp-Gen has shown remarkable zero-shot generalizability on other datasets. The source code is available at https://github.com/CUHK-AIM-Group/Polyp-Gen.
Authors: Jianing Li, Ming Lu, Hao Wang, Chenyang Gu, Wenzhao Zheng, Li Du, Shanghang Zhang
Abstract: 3D semantic occupancy prediction is a crucial task in visual perception, as it requires the simultaneous comprehension of both scene geometry and semantics. It plays a crucial role in understanding 3D scenes and has great potential for various applications, such as robotic vision perception and autonomous driving. Many existing works utilize planar-based representations such as Bird's Eye View (BEV) and Tri-Perspective View (TPV). These representations aim to simplify the complexity of 3D scenes while preserving essential object information, thereby facilitating efficient scene representation. However, in dense indoor environments with prevalent occlusions, directly applying these planar-based methods often leads to difficulties in capturing global semantic occupancy, ultimately degrading model performance. In this paper, we present a new vertical slice representation that divides the scene along the vertical axis and projects spatial point features onto the nearest pair of parallel planes. To utilize these slice features, we propose SliceOcc, an RGB camera-based model specifically tailored for indoor 3D semantic occupancy prediction. SliceOcc utilizes pairs of slice queries and cross-attention mechanisms to extract planar features from input images. These local planar features are then fused to form a global scene representation, which is employed for indoor occupancy prediction. Experimental results on the EmbodiedScan dataset demonstrate that SliceOcc achieves a mIoU of 15.45% across 81 indoor categories, setting a new state-of-the-art performance among RGB camera-based models for indoor 3D semantic occupancy prediction. Code is available at https://github.com/NorthSummer/SliceOcc.
Authors: Ali Zia, Jun Zhou, Muyiwa Olayemi
Abstract: Sugarcane mosaic disease poses a serious threat to the Australian sugarcane industry, leading to yield losses of up to 30% in susceptible varieties. Existing manual inspection methods for detecting mosaic resilience are inefficient and impractical for large-scale application. This study introduces a novel approach using hyperspectral imaging and machine learning to detect mosaic resilience by leveraging global feature representation from local spectral patches. Hyperspectral data were collected from eight sugarcane varieties under controlled and field conditions. Local spectral patches were analyzed to capture spatial and spectral variations, which were then aggregated into global feature representations using a ResNet18 deep learning architecture. While classical methods like Support Vector Machines struggled to utilize spatial-spectral relationships effectively, the deep learning model achieved high classification accuracy, demonstrating its capacity to identify mosaic resilience from fine-grained hyperspectral data. This approach enhances early detection capabilities, enabling more efficient management of susceptible strains and contributing to sustainable sugarcane production.
Authors: MD Sadik Hossain Shanto, Mahir Labib Dihan, Souvik Ghosh, Riad Ahmed Anonto, Hafijul Hoque Chowdhury, Abir Muhtasim, Rakib Ahsan, MD Tanvir Hassan, MD Roqunuzzaman Sojib, Sheikh Azizul Hakim, M. Saifur Rahman
Abstract: This report presents our approach for the IEEE SP Cup 2025: Deepfake Face Detection in the Wild (DFWild-Cup), focusing on detecting deepfakes across diverse datasets. Our methodology employs advanced backbone models, including MaxViT, CoAtNet, and EVA-02, fine-tuned using supervised contrastive loss to enhance feature separation. These models were specifically chosen for their complementary strengths. Integration of convolution layers and strided attention in MaxViT is well-suited for detecting local features. In contrast, hybrid use of convolution and attention mechanisms in CoAtNet effectively captures multi-scale features. Robust pretraining with masked image modeling of EVA-02 excels at capturing global features. After training, we freeze the parameters of these models and train the classification heads. Finally, a majority voting ensemble is employed to combine the predictions from these models, improving robustness and generalization to unseen scenarios. The proposed system addresses the challenges of detecting deepfakes in real-world conditions and achieves a commendable accuracy of 95.83% on the validation dataset.
Authors: Huijie Liu, Jingyun Wang, Shuai Ma, Jie Hu, Xiaoming Wei, Guoliang Kang
Abstract: Motion customization aims to adapt the diffusion model (DM) to generate videos with the motion specified by a set of video clips with the same motion concept. To realize this goal, the adaptation of DM should be possible to model the specified motion concept, without compromising the ability to generate diverse appearances. Thus, the key to solving this problem lies in how to separate the motion concept from the appearance in the adaptation process of DM. Typical previous works explore different ways to represent and insert a motion concept into large-scale pretrained text-to-video diffusion models, e.g., learning a motion LoRA, using latent noise residuals, etc. While those methods can encode the motion concept, they also inevitably encode the appearance in the reference videos, resulting in weakened appearance generation capability. In this paper, we follow the typical way to learn a motion LoRA to encode the motion concept, but propose two novel strategies to enhance motion-appearance separation, including temporal attention purification (TAP) and appearance highway (AH). Specifically, we assume that in the temporal attention module, the pretrained Value embeddings are sufficient to serve as basic components needed by producing a new motion. Thus, in TAP, we choose only to reshape the temporal attention with motion LoRAs so that Value embeddings can be reorganized to produce a new motion. Further, in AH, we alter the starting point of each skip connection in U-Net from the output of each temporal attention module to the output of each spatial attention module. Extensive experiments demonstrate that compared to previous works, our method can generate videos with appearance more aligned with the text descriptions and motion more consistent with the reference videos.
Authors: Tongxu Zhang, Bei Wang
Abstract: We propose a novel framework that integrates medical image segmentation and point cloud upsampling for accurate shape reconstruction of pelvic models. Using the SAM-Med3D model for segmentation and a point cloud upsampling network trained on the MedShapeNet dataset, our method transforms sparse medical imaging data into high-resolution 3D bone models. This framework leverages prior knowledge of anatomical shapes, achieving smoother and more complete reconstructions. Quantitative evaluations using metrics such as Chamfer Distance etc, demonstrate the effectiveness of the point cloud upsampling in pelvic model. Our approach offers potential applications in reconstructing other skeletal structures, providing a robust solution for medical image analysis and statistical shape modeling.
Authors: Chunpeng Zhou, Qianqian Shen, Zhi Yu, Jiajun Bu, Haishuai Wang
Abstract: Recent advancements in fine-tuning Vision-Language Foundation Models (VLMs) have garnered significant attention for their effectiveness in downstream few-shot learning tasks.While these recent approaches exhibits some performance improvements, they often suffer from excessive training parameters and high computational costs. To address these challenges, we propose a novel Block matrix-based low-rank adaptation framework, called Block-LoRA, for fine-tuning VLMs on downstream few-shot tasks. Inspired by recent work on Low-Rank Adaptation (LoRA), Block-LoRA partitions the original low-rank decomposition matrix of LoRA into a series of sub-matrices while sharing all down-projection sub-matrices. This structure not only reduces the number of training parameters, but also transforms certain complex matrix multiplication operations into simpler matrix addition, significantly lowering the computational cost of fine-tuning. Notably, Block-LoRA enables fine-tuning CLIP on the ImageNet few-shot benchmark using a single 24GB GPU. We also show that Block-LoRA has the more tighter bound of generalization error than vanilla LoRA. Without bells and whistles, extensive experiments demonstrate that Block-LoRA achieves competitive performance compared to state-of-the-art CLIP-based few-shot methods, while maintaining a low training parameters count and reduced computational overhead.
Authors: Yoojin Jang, Junsu Kim, Hayeon Kim, Eun-ki Lee, Eun-sol Kim, Seungryul Baek, Jaejun Yoo
Abstract: Human-object interaction (HOI) is an essential problem in artificial intelligence (AI) which aims to understand the visual world that involves complex relationships between humans and objects. However, current benchmarks such as HICO-DET face the following limitations: (1) severe class imbalance and (2) varying number of train and test sets for certain classes. These issues can potentially lead to either inflation or deflation of model performance during evaluation, ultimately undermining the reliability of evaluation scores. In this paper, we propose a systematic approach to develop a new class-balanced dataset, Benchmark Re-evaluation for Integrity in Generalized Human-object Interaction Testing (B-RIGHT), that addresses these imbalanced problems. B-RIGHT achieves class balance by leveraging balancing algorithm and automated generation-and-filtering processes, ensuring an equal number of instances for each HOI class. Furthermore, we design a balanced zero-shot test set to systematically evaluate models on unseen scenario. Re-evaluating existing models using B-RIGHT reveals substantial the reduction of score variance and changes in performance rankings compared to conventional HICO-DET. Our experiments demonstrate that evaluation under balanced conditions ensure more reliable and fair model comparisons.
Authors: Chenru Jiang, Chengrui Zhang, Xi Yang, Jie Sun, Kaizhu Huang
Abstract: This paper delves into the study of 3D point cloud reconstruction from a single image. Our objective is to develop the Consistency Diffusion Model, exploring synergistic 2D and 3D priors in the Bayesian framework to ensure superior consistency in the reconstruction process, a challenging yet critical requirement in this field. Specifically, we introduce a pioneering training framework under diffusion models that brings two key innovations. First, we convert 3D structural priors derived from the initial 3D point cloud as a bound term to increase evidence in the variational Bayesian framework, leveraging these robust intrinsic priors to tightly govern the diffusion training process and bolster consistency in reconstruction. Second, we extract and incorporate 2D priors from the single input image, projecting them onto the 3D point cloud to enrich the guidance for diffusion training. Our framework not only sidesteps potential model learning shifts that may arise from directly imposing additional constraints during training but also precisely transposes the 2D priors into the 3D domain. Extensive experimental evaluations reveal that our approach sets new benchmarks in both synthetic and real-world datasets. The code is included with the submission.
Authors: Muxi Chen, Chenchen Zhao, Qiang Xu
Abstract: Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices. Identifying and mitigating these error slices is crucial to enhancing model robustness and reliability in real-world scenarios. In this paper, we introduce DebugAgent, an automated framework for error slice discovery and model repair. DebugAgent first generates task-specific visual attributes to highlight instances prone to errors through an interpretable and structured process. It then employs an efficient slice enumeration algorithm to systematically identify error slices, overcoming the combinatorial challenges that arise during slice exploration. Additionally, DebugAgent extends its capabilities by predicting error slices beyond the validation set, addressing a key limitation of prior approaches. Extensive experiments across multiple domains, including image classification, pose estimation, and object detection - show that DebugAgent not only improves the coherence and precision of identified error slices but also significantly enhances the model repair capabilities.
Authors: Hy Nguyen, Srikanth Thudumu, Hung Du, Rajesh Vasa, Kon Mouzakis
Abstract: Next-frame prediction in videos is crucial for applications such as autonomous driving, object tracking, and motion prediction. The primary challenge in next-frame prediction lies in effectively capturing and processing both spatial and temporal information from previous video sequences. The transformer architecture, known for its prowess in handling sequence data, has made remarkable progress in this domain. However, transformer-based next-frame prediction models face notable issues: (a) The multi-head self-attention (MHSA) mechanism requires the input embedding to be split into $N$ chunks, where $N$ is the number of heads. Each segment captures only a fraction of the original embeddings information, which distorts the representation of the embedding in the latent space, resulting in a semantic dilution problem; (b) These models predict the embeddings of the next frames rather than the frames themselves, but the loss function based on the errors of the reconstructed frames, not the predicted embeddings -- this creates a discrepancy between the training objective and the model output. We propose a Semantic Concentration Multi-Head Self-Attention (SCMHSA) architecture, which effectively mitigates semantic dilution in transformer-based next-frame prediction. Additionally, we introduce a loss function that optimizes SCMHSA in the latent space, aligning the training objective more closely with the model output. Our method demonstrates superior performance compared to the original transformer-based predictors.
Authors: Haifeng Ni
Abstract: Recent advancements in virtual fitting for characters and clothing have leveraged diffusion models to improve the realism of garment fitting. However, challenges remain in handling complex scenes and poses, which can result in unnatural garment fitting and poorly rendered intricate patterns. In this work, we introduce ITVTON, a novel method that enhances clothing-character interactions by combining clothing and character images along spatial channels as inputs, thereby improving fitting accuracy for the inpainting model. Additionally, we incorporate integrated textual descriptions from multiple images to boost the realism of the generated visual effects. To optimize computational efficiency, we limit training to the attention parameters within a single diffusion transformer (Single-DiT) block. To more rigorously address the complexities of real-world scenarios, we curated training samples from the IGPair dataset, thereby enhancing ITVTON's performance across diverse environments. Extensive experiments demonstrate that ITVTON outperforms baseline methods both qualitatively and quantitatively, setting a new standard for virtual fitting tasks.
Authors: Surojit Saha, Ross Whitaker
Abstract: Automated interpretation of seismic images using deep learning methods is challenging because of the limited availability of training data. Few-shot learning is a suitable learning paradigm in such scenarios due to its ability to adapt to a new task with limited supervision (small training budget). Existing few-shot semantic segmentation (FSSS) methods fix the number of target classes. Therefore, they do not support joint training on multiple datasets varying in the number of classes. In the context of the interpretation of seismic facies, fixing the number of target classes inhibits the generalization capability of a model trained on one facies dataset to another, which is likely to have a different number of facies. To address this shortcoming, we propose a few-shot semantic segmentation method for interpreting seismic facies that can adapt to the varying number of facies across the dataset, dubbed the AdaSemSeg. In general, the backbone network of FSSS methods is initialized with the statistics learned from the ImageNet dataset for better performance. The lack of such a huge annotated dataset for seismic images motivates using a self-supervised algorithm on seismic datasets to initialize the backbone network. We have trained the AdaSemSeg on three public seismic facies datasets with different numbers of facies and evaluated the proposed method on multiple metrics. The performance of the AdaSemSeg on unseen datasets (not used in training) is better than the prototype-based few-shot method and baselines.
Authors: Chenguo Lin, Panwang Pan, Bangbang Yang, Zeming Li, Yadong Mu
Abstract: Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively generates 3D Gaussian splats by taming large-scale text-to-image diffusion models. It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model. To bootstrap the training, a lightweight reconstruction model is proposed to instantly produce multi-view Gaussian splat grids for scalable dataset curation. In conjunction with the regular diffusion loss on these grids, a 3D rendering loss is introduced to facilitate 3D coherence across arbitrary views. The compatibility with image diffusion models enables seamless adaptions of numerous techniques for image generation to the 3D realm. Extensive experiments reveal the superiority of DiffSplat in text- and image-conditioned generation tasks and downstream applications. Thorough ablation studies validate the efficacy of each critical design choice and provide insights into the underlying mechanism.
Authors: Pengfei Zhu, Peng Shu, Mengshi Qi, Liang Liu, Huadong Ma
Abstract: Accurate prediction of future trajectories of traffic agents is essential for ensuring safe autonomous driving. However, partially observed trajectories can significantly degrade the performance of even state-of-the-art models. Previous approaches often rely on knowledge distillation to transfer features from fully observed trajectories to partially observed ones. This involves firstly training a fully observed model and then using a distillation process to create the final model. While effective, they require multi-stage training, making the training process very expensive. Moreover, knowledge distillation can lead to a performance degradation of the model. In this paper, we introduce a Target-driven Self-Distillation method (TSD) for motion forecasting. Our method leverages predicted accurate targets to guide the model in making predictions under partial observation conditions. By employing self-distillation, the model learns from the feature distributions of both fully observed and partially observed trajectories during a single end-to-end training process. This enhances the model's ability to predict motion accurately in both fully observed and partially observed scenarios. We evaluate our method on multiple datasets and state-of-the-art motion forecasting models. Extensive experimental results demonstrate that our approach achieves significant performance improvements in both settings. To facilitate further research, we will release our code and model checkpoints.
Authors: Muhammad Atta ur Rahman
Abstract: Self-supervised learning can resolve numerous image or linguistic processing problems when effectively trained. This study investigated simple yet efficient methods for adaping previously learned foundation models for open-vocabulary semantic segmentation tasks. Our research proposed "Beyond-Labels," a lightweight transformer-based fusion module that uses a handful of image segmentation data to fuse frozen image representations with language concepts. Furthermore, we efficiently captured positional information in images using Fourier embeddings, thus improving the generalization across various image sizes. Extensive ablation tests were performed to investigate the important components of our proposed method; when tested against the common benchmark PASCAL-5i, it demonstrated superior performance despite being trained on frozen image and language characteristics.
Authors: Arvin Tashakori, Arash Tashakori, Gongbo Yang, Z. Jane Wang, Peyman Servati
Abstract: Lightweight, controllable, and physically plausible human motion synthesis is crucial for animation, virtual reality, robotics, and human-computer interaction applications. Existing methods often compromise between computational efficiency, physical realism, or spatial controllability. We propose FlexMotion, a novel framework that leverages a computationally lightweight diffusion model operating in the latent space, eliminating the need for physics simulators and enabling fast and efficient training. FlexMotion employs a multimodal pre-trained Transformer encoder-decoder, integrating joint locations, contact forces, joint actuations and muscle activations to ensure the physical plausibility of the generated motions. FlexMotion also introduces a plug-and-play module, which adds spatial controllability over a range of motion parameters (e.g., joint locations, joint actuations, contact forces, and muscle activations). Our framework achieves realistic motion generation with improved efficiency and control, setting a new benchmark for human motion synthesis. We evaluate FlexMotion on extended datasets and demonstrate its superior performance in terms of realism, physical plausibility, and controllability.
Authors: Yun Li, Zhe Liu, Yajing Kong, Guangrui Li, Jiyuan Zhang, Chao Bian, Feng Liu, Lina Yao, Zhenbang Sun
Abstract: Applying Multimodal Large Language Models (MLLMs) to video understanding presents significant challenges due to the need to model temporal relations across frames. Existing approaches adopt either implicit temporal modeling, relying solely on the LLM decoder, or explicit temporal modeling, employing auxiliary temporal encoders. To investigate this debate between the two paradigms, we propose the Stackable Temporal Encoder (STE). STE enables flexible explicit temporal modeling with adjustable temporal receptive fields and token compression ratios. Using STE, we systematically compare implicit and explicit temporal modeling across dimensions such as overall performance, token compression effectiveness, and temporal-specific understanding. We also explore STE's design considerations and broader impacts as a plug-in module and in image modalities. Our findings emphasize the critical role of explicit temporal modeling, providing actionable insights to advance video MLLMs.
Authors: Yuxuan Chen, Jiawen Li, Huijuan Shi, Yang Xu, Tian Guan, Lianghui Zhu, Yonghong He, Anjia Han
Abstract: Bone metastasis analysis is a significant challenge in pathology and plays a critical role in determining patient quality of life and treatment strategies. The microenvironment and specific tissue structures are essential for pathologists to predict the primary bone cancer origins and primary bone cancer subtyping. By digitizing bone tissue sections into whole slide images (WSIs) and leveraging deep learning to model slide embeddings, this analysis can be enhanced. However, tumor metastasis involves complex multivariate interactions with diverse bone tissue structures, which traditional WSI analysis methods such as multiple instance learning (MIL) fail to capture. Moreover, graph neural networks (GNNs), limited to modeling pairwise relationships, are hard to represent high-order biological associations. To address these challenges, we propose a dynamic hypergraph neural network (DyHG) that overcomes the edge construction limitations of traditional graph representations by connecting multiple nodes via hyperedges. A low-rank strategy is used to reduce the complexity of parameters in learning hypergraph structures, while a Gumbel-Softmax-based sampling strategy optimizes the patch distribution across hyperedges. An MIL aggregator is then used to derive a graph-level embedding for comprehensive WSI analysis. To evaluate the effectiveness of DyHG, we construct two large-scale datasets for primary bone cancer origins and subtyping classification based on real-world bone metastasis scenarios. Extensive experiments demonstrate that DyHG significantly outperforms state-of-the-art (SOTA) baselines, showcasing its ability to model complex biological interactions and improve the accuracy of bone metastasis analysis.
Authors: Lanyun Zhu, Tianrun Chen, Deyi Ji, Jieping Ye, Jun Liu
Abstract: This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or transformer backbones to extract deep features for every position in every sampled video frame. Here, we argue that this exhaustive feature extraction could be unnecessary, since we find that different frames in a ReID video often exhibit small differences and contain many similar regions due to the relatively slight movements of human beings. Inspired by this, a more selective, efficient paradigm is explored in this paper. Specifically, we introduce a patch selection mechanism to reduce computational cost by choosing only the crucial and non-repetitive patches for feature extraction. Additionally, we present a novel network structure that generates and utilizes pseudo frame global context to address the issue of incomplete views resulting from sparse inputs. By incorporating these new designs, our backbone can achieve both high performance and low computational cost. Extensive experiments on multiple datasets show that our approach reduces the computational cost by 74\% compared to ViT-B and 28\% compared to ResNet50, while the accuracy is on par with ViT-B and outperforms ResNet50 significantly.
Authors: Josep Lopez Camunas, Cristina Bustos, Yanjun Zhu, Raquel Ros, Agata Lapedriza
Abstract: Understanding emotional signals in older adults is crucial for designing virtual assistants that support their well-being. However, existing affective computing models often face significant limitations: (1) limited availability of datasets representing older adults, especially in non-English-speaking populations, and (2) poor generalization of models trained on younger or homogeneous demographics. To address these gaps, this study evaluates state-of-the-art affective computing models -- including facial expression recognition, text sentiment analysis, and smile detection -- using videos of older adults interacting with either a person or a virtual avatar. As part of this effort, we introduce a novel dataset featuring Spanish-speaking older adults engaged in human-to-human video interviews. Through three comprehensive analyses, we investigate (1) the alignment between human-annotated labels and automatic model outputs, (2) the relationships between model outputs across different modalities, and (3) individual variations in emotional signals. Using both the Wizard of Oz (WoZ) dataset and our newly collected dataset, we uncover limited agreement between human annotations and model predictions, weak consistency across modalities, and significant variability among individuals. These findings highlight the shortcomings of generalized emotion perception models and emphasize the need of incorporating personal variability and cultural nuances into future systems.
Authors: Veronika Solopova, Lucas Schmidt, Dorothea Kolossa
Abstract: We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA framework addresses the need for explainability in temporal models used for video analysis. To demonstrate its effectiveness, we apply VIBA to video deepfake detection, testing it on two architectures: the Xception model for spatial features and a VGG11-based model for capturing motion dynamics through optical flow. Using a custom dataset that reflects recent deepfake generation techniques, we adapt IBA to create relevance and optical flow maps, visually highlighting manipulated regions and motion inconsistencies. Our results show that VIBA generates temporally and spatially consistent explanations, which align closely with human annotations, thus providing interpretability for video classification and particularly for deepfake detection.
Authors: Marco Huber, Fadi Boutros, Naser Damer
Abstract: Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face recognition models. Several works aimed at exploring possible roots of gender and ethnicity bias, identifying semantic reasons such as hairstyle, make-up, or facial hair as possible sources. Motivated by recent discoveries of the importance of frequency patterns in convolutional neural networks, we explain bias in face recognition using state-of-the-art frequency-based explanations. Our extensive results show that different frequencies are important to FR models depending on the ethnicity of the samples.
Authors: Yuan-Chih Chen, Chun-Shien Lu
Abstract: The study of adversarial defense still struggles to combat with advanced adversarial attacks. In contrast to most prior studies that rely on the diffusion model for test-time defense to remarkably increase the inference time, we propose Masked AutoEncoder Purifier (MAEP), which integrates Masked AutoEncoder (MAE) into an adversarial purifier framework for test-time purification. While MAEP achieves promising adversarial robustness, it particularly features model defense transferability and attack generalization without relying on using additional data that is different from the training dataset. To our knowledge, MAEP is the first study of adversarial purifier based on MAE. Extensive experimental results demonstrate that our method can not only maintain clear accuracy with only a slight drop but also exhibit a close gap between the clean and robust accuracy. Notably, MAEP trained on CIFAR10 achieves state-of-the-art performance even when tested directly on ImageNet, outperforming existing diffusion-based models trained specifically on ImageNet.
Authors: Nikolaos Kaparinos, Vasileios Mezaris
Abstract: Face detection is a computer vision application that increasingly demands lightweight models to facilitate deployment on devices with limited computational resources. Neural network pruning is a promising technique that can effectively reduce network size without significantly affecting performance. In this work, we propose a novel face detection pruning pipeline that leverages Filter Pruning via Geometric Median (FPGM) pruning, Soft Filter Pruning (SFP) and Bayesian optimization in order to achieve a superior trade-off between size and performance compared to existing approaches. FPGM pruning is a structured pruning technique that allows pruning the least significant filters in each layer, while SFP iteratively prunes the filters and allows them to be updated in any subsequent training step. Bayesian optimization is employed in order to optimize the pruning rates of each layer, rather than relying on engineering expertise to determine the optimal pruning rates for each layer. In our experiments across all three subsets of the WIDER FACE dataset, our proposed approach B-FPGM consistently outperforms existing ones in balancing model size and performance. All our experiments were applied to EResFD, the currently smallest (in number of parameters) well-performing face detector of the literature; a small ablation study with a second small face detector, EXTD, is also reported. The source code and trained pruned face detection models can be found at: https://github.com/IDTITI/B-FPGM.
Authors: Sania Waheed, Bruno Ferrarini, Michael Milford, Sarvapali D. Ramchurn, Shoaib Ehsan
Abstract: The advances in Vision-Language models (VLMs) offer exciting opportunities for robotic applications involving image geo-localization, the problem of identifying the geo-coordinates of a place based on visual data only. Recent research works have focused on using a VLM as embeddings extractor for geo-localization, however, the most sophisticated VLMs may only be available as black boxes that are accessible through an API, and come with a number of limitations: there is no access to training data, model features and gradients; retraining is not possible; the number of predictions may be limited by the API; training on model outputs is often prohibited; and queries are open-ended. The utilization of a VLM as a stand-alone, zero-shot geo-localization system using a single text-based prompt is largely unexplored. To bridge this gap, this paper undertakes the first systematic study, to the best of our knowledge, to investigate the potential of some of the state-of-the-art VLMs as stand-alone, zero-shot geo-localization systems in a black-box setting with realistic constraints. We consider three main scenarios for this thorough investigation: a) fixed text-based prompt; b) semantically-equivalent text-based prompts; and c) semantically-equivalent query images. We also take into account the auto-regressive and probabilistic generation process of the VLMs when investigating their utility for geo-localization task by using model consistency as a metric in addition to traditional accuracy. Our work provides new insights in the capabilities of different VLMs for the above-mentioned scenarios.
Authors: Shujuan Huang, Chunyu Lin, Yao Zhao
Abstract: Calibration is an essential prerequisite for the accurate data fusion of LiDAR and camera sensors. Traditional calibration techniques often require specific targets or suitable scenes to obtain reliable 2D-3D correspondences. To tackle the challenge of target-less and online calibration, deep neural networks have been introduced to solve the problem in a data-driven manner. While previous learning-based methods have achieved impressive performance on specific datasets, they still struggle in complex real-world scenarios. Most existing works focus on improving calibration accuracy but overlook the underlying mechanisms. In this paper, we revisit the development of learning-based LiDAR-Camera calibration and encourage the community to pay more attention to the underlying principles to advance practical applications. We systematically analyze the paradigm of mainstream learning-based methods, and identify the critical limitations of regression-based methods with the widely used data generation pipeline. Our findings reveal that most learning-based methods inadvertently operate as retrieval networks, focusing more on single-modality distributions rather than cross-modality correspondences. We also investigate how the input data format and preprocessing operations impact network performance and summarize the regression clues to inform further improvements.
Authors: Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi, Ali Ansari, Sepehr Ghobadi, Masoud Hadi, Arshia Soltani Moakhar, Mohammad Azizmalayeri, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Abstract: In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far behind that in standard settings. This is due to the lack of effective exposure to adversarial scenarios during training, especially on unseen outliers, leading to detection models failing to learn robust features. To bridge this gap, we introduce RODEO, a data-centric approach that generates effective outliers for robust outlier detection. More specifically, we show that incorporating outlier exposure (OE) and adversarial training can be an effective strategy for this purpose, as long as the exposed training outliers meet certain characteristics, including diversity, and both conceptual differentiability and analogy to the inlier samples. We leverage a text-to-image model to achieve this goal. We demonstrate both quantitatively and qualitatively that our adaptive OE method effectively generates ``diverse'' and ``near-distribution'' outliers, leveraging information from both text and image domains. Moreover, our experimental results show that utilizing our synthesized outliers significantly enhances the performance of the outlier detector, particularly in adversarial settings.
Authors: Xiangyu Gao, Yu Dai, Benliu Qiu, Hongliang Li
Abstract: Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocabulary object detectors attempt to utilize the pre-trained VLM to attain generative representation. F-ViT uses the pre-trained visual encoder as the backbone network and freezes it during training. However, the frozen backbone doesn't benefit from the labeled data to strengthen the representation. Therefore, we propose a novel two-branch backbone network design, named as ViT-Feature-Modulated Multi-Scale Convolutional network (VMCNet). VMCNet consists of a trainable convolutional branch, a frozen pre-trained ViT branch and a feature modulation module. The trainable CNN branch could be optimized with labeled data while the frozen pre-trained ViT branch could keep the representation ability derived from large-scale pre-training. Then, the proposed feature modulation module could modulate the multi-scale CNN features with the representations from ViT branch. With the proposed mixed structure, detector is more likely to discover novel categories. Evaluated on two popular benchmarks, our method boosts the detection performance on novel category and outperforms the baseline. On OV-COCO, the proposed method achieves 44.3 AP$_{50}^{\mathrm{novel}}$ with ViT-B/16 and 48.5 AP$_{50}^{\mathrm{novel}}$ with ViT-L/14. On OV-LVIS, VMCNet with ViT-B/16 and ViT-L/14 reaches 27.8 and 38.4 mAP$_{r}$.
Authors: Tuong Do, Nghia Vu, Tudor Jianu, Baoru Huang, Minh Vu, Jionglong Su, Erman Tjiputra, Quang D. Tran, Te-Chuan Chiu, Anh Nguyen
Abstract: In endovascular surgery, the precise identification of catheters and guidewires in X-ray images is essential for reducing intervention risks. However, accurately segmenting catheter and guidewire structures is challenging due to the limited availability of labeled data. Foundation models offer a promising solution by enabling the collection of similar domain data to train models whose weights can be fine-tuned for downstream tasks. Nonetheless, large-scale data collection for training is constrained by the necessity of maintaining patient privacy. This paper proposes a new method to train a foundation model in a decentralized federated learning setting for endovascular intervention. To ensure the feasibility of the training, we tackle the unseen data issue using differentiable Earth Mover's Distance within a knowledge distillation framework. Once trained, our foundation model's weights provide valuable initialization for downstream tasks, thereby enhancing task-specific performance. Intensive experiments show that our approach achieves new state-of-the-art results, contributing to advancements in endovascular intervention and robotic-assisted endovascular surgery, while addressing the critical issue of data sharing in the medical domain.
Authors: Shreyam Gupta (Indian Institute of Technology), P. Agrawal (University of Colorado, Boulder, USA), Priyam Gupta (Intelligent Field Robotic Systems)
Abstract: Temporal sequence modeling stands as the fundamental foundation for video prediction systems and real-time forecasting operations as well as anomaly detection applications. The achievement of accurate predictions through efficient resource consumption remains an ongoing issue in contemporary temporal sequence modeling. We introduce the Multi-Attention Unit (MAUCell) which combines Generative Adversarial Networks (GANs) and spatio-temporal attention mechanisms to improve video frame prediction capabilities. Our approach implements three types of attention models to capture intricate motion sequences. A dynamic combination of these attention outputs allows the model to reach both advanced decision accuracy along with superior quality while remaining computationally efficient. The integration of GAN elements makes generated frames appear more true to life therefore the framework creates output sequences which mimic real-world footage. The new design system maintains equilibrium between temporal continuity and spatial accuracy to deliver reliable video prediction. Through a comprehensive evaluation methodology which merged the perceptual LPIPS measurement together with classic tests MSE, MAE, SSIM and PSNR exhibited enhancing capabilities than contemporary approaches based on direct benchmark tests of Moving MNIST, KTH Action, and CASIA-B (Preprocessed) datasets. Our examination indicates that MAUCell shows promise for operational time requirements. The research findings demonstrate how GANs work best with attention mechanisms to create better applications for predicting video sequences.
Authors: Max Dax, Jordi Berbel, Jan Stria, Leonidas Guibas, Urs Bergmann
Abstract: We generate abstractions of buildings, reflecting the essential aspects of their geometry and structure, by learning to invert procedural models. We first build a dataset of abstract procedural building models paired with simulated point clouds and then learn the inverse mapping through a transformer. Given a point cloud, the trained transformer then infers the corresponding abstracted building in terms of a programmatic language description. This approach leverages expressive procedural models developed for gaming and animation, and thereby retains desirable properties such as efficient rendering of the inferred abstractions and strong priors for regularity and symmetry. Our approach achieves good reconstruction accuracy in terms of geometry and structure, as well as structurally consistent inpainting.
Authors: Akash Kumar, Zsolt Kira, Yogesh Singh Rawat
Abstract: In this work, we focus on Weakly Supervised Spatio-Temporal Video Grounding (WSTVG). It is a multimodal task aimed at localizing specific subjects spatio-temporally based on textual queries without bounding box supervision. Motivated by recent advancements in multi-modal foundation models for grounding tasks, we first explore the potential of state-of-the-art object detection models for WSTVG. Despite their robust zero-shot capabilities, our adaptation reveals significant limitations, including inconsistent temporal predictions, inadequate understanding of complex queries, and challenges in adapting to difficult scenarios. We propose CoSPaL (Contextual Self-Paced Learning), a novel approach which is designed to overcome these limitations. CoSPaL integrates three core components: (1) Tubelet Phrase Grounding (TPG), which introduces spatio-temporal prediction by linking textual queries to tubelets; (2) Contextual Referral Grounding (CRG), which improves comprehension of complex queries by extracting contextual information to refine object identification over time; and (3) Self-Paced Scene Understanding (SPS), a training paradigm that progressively increases task difficulty, enabling the model to adapt to complex scenarios by transitioning from coarse to fine-grained understanding.
Authors: Muhammad Shahbaz, Shaurya Agarwal
Abstract: Recent advancements in deep-learning methods for object detection in point-cloud data have enabled numerous roadside applications, fostering improvements in transportation safety and management. However, the intricate nature of point-cloud data poses significant challenges for human-supervised labeling, resulting in substantial expenditures of time and capital. This paper addresses the issue by developing an end-to-end, scalable, and self-supervised framework for training deep object detectors tailored for roadside point-cloud data. The proposed framework leverages self-supervised, statistically modeled teachers to train off-the-shelf deep object detectors, thus circumventing the need for human supervision. The teacher models follow fine-tuned set standard practices of background filtering, object clustering, bounding-box fitting, and classification to generate noisy labels. It is presented that by training the student model over the combined noisy annotations from multitude of teachers enhances its capacity to discern background/foreground more effectively and forces it to learn diverse point-cloud-representations for object categories of interest. The evaluations, involving publicly available roadside datasets and state-of-art deep object detectors, demonstrate that the proposed framework achieves comparable performance to deep object detectors trained on human-annotated labels, despite not utilizing such human-annotations in its training process.
Authors: Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan
Abstract: Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.
Authors: Rivera Esteban, L\"ubberstedt Jannik, Nico Uhlemann, Markus Lienkamp
Abstract: Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions, making an effective scene-based categorization of samples necessary to improve their reliability across diverse domains. Manual captioning, though valuable, is both labor-intensive and time-consuming, creating a bottleneck in the data annotation process. Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and categorization through contextual queries, often without requiring retraining for new categories. In this study, we evaluate the capabilities of LVLMs, including GPT-4 and LLaVA, to understand and classify urban traffic scenes on both an in-house dataset and the BDD100K. We propose a scalable captioning pipeline that integrates state-of-the-art models, enabling a flexible deployment on new datasets. Our analysis, combining quantitative metrics with qualitative insights, demonstrates the effectiveness of LVLMs to understand urban traffic scenarios and highlights their potential as an efficient tool for data-driven advancements in autonomous driving.
Authors: Han Yang, Enis Simsar, Sotiris Anagnostidi, Yanlong Zang, Thomas Hofmann, Ziwei Liu
Abstract: Existing diffusion models show great potential for identity-preserving generation. However, personalized portrait generation remains challenging due to the diversity in user profiles, including variations in appearance and lighting conditions. To address these challenges, we propose IC-Portrait, a novel framework designed to accurately encode individual identities for personalized portrait generation. Our key insight is that pre-trained diffusion models are fast learners (e.g.,100 ~ 200 steps) for in-context dense correspondence matching, which motivates the two major designs of our IC-Portrait framework. Specifically, we reformulate portrait generation into two sub-tasks: 1) Lighting-Aware Stitching: we find that masking a high proportion of the input image, e.g., 80%, yields a highly effective self-supervisory representation learning of reference image lighting. 2) View-Consistent Adaptation: we leverage a synthetic view-consistent profile dataset to learn the in-context correspondence. The reference profile can then be warped into arbitrary poses for strong spatial-aligned view conditioning. Coupling these two designs by simply concatenating latents to form ControlNet-like supervision and modeling, enables us to significantly enhance the identity preservation fidelity and stability. Extensive evaluations demonstrate that IC-Portrait consistently outperforms existing state-of-the-art methods both quantitatively and qualitatively, with particularly notable improvements in visual qualities. Furthermore, IC-Portrait even demonstrates 3D-aware relighting capabilities.
Authors: Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Philipp Henzler, Konrad Schindler, Federico Tombari
Abstract: We introduce a novel method for generating 360{\deg} panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively. Project page: https://cubediff.github.io/
Authors: Qing Li, Jiahui Geng, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray
Abstract: Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an \textbf{internal activation revision} approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94\%, 34.34\%, 43.92\%, and 52.98\% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.
Authors: Samuel Biruduganti, Yash Yardi, Lars Ankile
Abstract: Simulation offers a scalable and efficient alternative to real-world data collection for learning visuomotor robotic policies. However, the simulation-to-reality, or "Sim2Real" distribution shift -- introduced by employing simulation-trained policies in real-world environments -- frequently prevents successful policy transfer. This study explores the potential of using large-scale pre-training of vision encoders to address the Sim2Real gap. We examine a diverse collection of encoders, evaluating their ability to (1) extract features necessary for robot control while (2) remaining invariant to task-irrelevant environmental variations. We quantitatively measure the encoder's feature extraction capabilities through linear probing and its domain invariance by computing distances between simulation and real-world embedding centroids. Additional qualitative insights are provided through t-SNE plots and GradCAM saliency maps. Findings suggest that encoders pre-trained on manipulation-specific datasets generally outperform those trained on generic datasets in bridging the Sim2Real gap. https://github.com/yyardi/Bridging-the-Sim2Real-Gap
Authors: Oriol Barbany, Adri\`a Colom\'e, Carme Torras
Abstract: Cloth folding is a complex task due to the inevitable self-occlusions of clothes, their complicated dynamics, and the disparate materials, geometries, and textures that garments can have. In this work, we learn folding actions conditioned on text commands. Translating high-level, abstract instructions into precise robotic actions requires sophisticated language understanding and manipulation capabilities. To do that, we leverage a pre-trained vision-language model and repurpose it to predict manipulation actions. Our model, BiFold, can take context into account and achieves state-of-the-art performance on an existing language-conditioned folding benchmark. Given the lack of annotated bimanual folding data, we devise a procedure to automatically parse actions of a simulated dataset and tag them with aligned text instructions. BiFold attains the best performance on our dataset and can transfer to new instructions, garments, and environments.
Authors: Tianyi Xie, Yiwei Zhao, Ying Jiang, Chenfanfu Jiang
Abstract: Creating hand-drawn animation sequences is labor-intensive and demands professional expertise. We introduce PhysAnimator, a novel approach for generating physically plausible meanwhile anime-stylized animation from static anime illustrations. Our method seamlessly integrates physics-based simulations with data-driven generative models to produce dynamic and visually compelling animations. To capture the fluidity and exaggeration characteristic of anime, we perform image-space deformable body simulations on extracted mesh geometries. We enhance artistic control by introducing customizable energy strokes and incorporating rigging point support, enabling the creation of tailored animation effects such as wind interactions. Finally, we extract and warp sketches from the simulation sequence, generating a texture-agnostic representation, and employ a sketch-guided video diffusion model to synthesize high-quality animation frames. The resulting animations exhibit temporal consistency and visual plausibility, demonstrating the effectiveness of our method in creating dynamic anime-style animations.
Authors: Jinlan Fu, Shenzhen Huangfu, Hao Fei, Xiaoyu Shen, Bryan Hooi, Xipeng Qiu, See-Kiong Ng
Abstract: Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using preference pairs from text-based responses. However, our analysis of representation distributions reveals that multimodal DPO struggles to align image and text representations and to distinguish between hallucinated and non-hallucinated descriptions. To address these challenges, in this work, we propose a Cross-modal Hierarchical Direct Preference Optimization (CHiP) to address these limitations. We introduce a visual preference optimization module within the DPO framework, enabling MLLMs to learn from both textual and visual preferences simultaneously. Furthermore, we propose a hierarchical textual preference optimization module that allows the model to capture preferences at multiple granular levels, including response, segment, and token levels. We evaluate CHiP through both quantitative and qualitative analyses, with results across multiple benchmarks demonstrating its effectiveness in reducing hallucinations. On the Object HalBench dataset, CHiP outperforms DPO in hallucination reduction, achieving improvements of 52.7% and 55.5% relative points based on the base model Muffin and LLaVA models, respectively. We make all our datasets and code publicly available: https://github.com/LVUGAI/CHiP.
Authors: Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, Jianyu Chen
Abstract: Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models are powerful, how to improve these large models during interaction with environments remains an open question. In this paper, we explore how to further improve these VLA models via Reinforcement Learning (RL), a commonly used fine-tuning technique for large models. However, we find that directly applying online RL to large VLA models presents significant challenges, including training instability that severely impacts the performance of large models, and computing burdens that exceed the capabilities of most local machines. To address these challenges, we propose iRe-VLA framework, which iterates between Reinforcement Learning and Supervised Learning to effectively improve VLA models, leveraging the exploratory benefits of RL while maintaining the stability of supervised learning. Experiments in two simulated benchmarks and a real-world manipulation suite validate the effectiveness of our method.
Authors: Yueen Ma, Yuzheng Zhuang, Jianye Hao, Irwin King
Abstract: 3D vision and spatial reasoning have long been recognized as preferable for accurately perceiving our three-dimensional world, especially when compared with traditional visual reasoning based on 2D images. Due to the difficulties in collecting high-quality 3D data, research in this area has only recently gained momentum. With the advent of powerful large language models (LLMs), multi-modal LLMs for 3D vision have been developed over the past few years. However, most of these models focus primarily on the vision encoder for 3D data. In this paper, we propose converting existing densely activated LLMs into mixture-of-experts (MoE) models, which have proven effective for multi-modal data processing. In addition to leveraging these models' instruction-following capabilities, we further enable embodied task planning by attaching a diffusion head, Pose-DiT, that employs a novel rectified flow diffusion scheduler. Experimental results on 3D question answering and task-planning tasks demonstrate that our 3D-MoE framework achieves improved performance with fewer activated parameters.
Authors: Yinfeng Gao, Qichao Zhang, Da-wei Ding, Dongbin Zhao
Abstract: It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency.
Authors: Kunal Dasharath Patil, Gowthamaan Palani, Ganapathy Krishnamurthi
Abstract: The Segment Anything Model (SAM) has set a new standard in interactive image segmentation, offering robust performance across various tasks. However, its significant computational requirements limit its deployment in real-time or resource-constrained environments. To address these challenges, we propose a novel knowledge distillation approach, KD SAM, which incorporates both encoder and decoder optimization through a combination of Mean Squared Error (MSE) and Perceptual Loss. This dual-loss framework captures structural and semantic features, enabling the student model to maintain high segmentation accuracy while reducing computational complexity. Based on the model evaluation on datasets, including Kvasir-SEG, ISIC 2017, Fetal Head Ultrasound, and Breast Ultrasound, we demonstrate that KD SAM achieves comparable or superior performance to the baseline models, with significantly fewer parameters. KD SAM effectively balances segmentation accuracy and computational efficiency, making it well-suited for real-time medical image segmentation applications in resource-constrained environments.
Authors: Lantao Li, Kang Yang, Wenqi Zhang, Xiaoxue Wang, Chen Sun
Abstract: Cooperative perception offers an optimal solution to overcome the perception limitations of single-agent systems by leveraging Vehicle-to-Everything (V2X) communication for data sharing and fusion across multiple agents. However, most existing approaches focus on single-modality data exchange, limiting the potential of both homogeneous and heterogeneous fusion across agents. This overlooks the opportunity to utilize multi-modality data per agent, restricting the system's performance. In the automotive industry, manufacturers adopt diverse sensor configurations, resulting in heterogeneous combinations of sensor modalities across agents. To harness the potential of every possible data source for optimal performance, we design a robust LiDAR and camera cross-modality fusion module, Radian-Glue-Attention (RG-Attn), applicable to both intra-agent cross-modality fusion and inter-agent cross-modality fusion scenarios, owing to the convenient coordinate conversion by transformation matrix and the unified sampling/inversion mechanism. We also propose two different architectures, named Paint-To-Puzzle (PTP) and Co-Sketching-Co-Coloring (CoS-CoCo), for conducting cooperative perception. PTP aims for maximum precision performance and achieves smaller data packet size by limiting cross-agent fusion to a single instance, but requiring all participants to be equipped with LiDAR. In contrast, CoS-CoCo supports agents with any configuration-LiDAR-only, camera-only, or LiDAR-camera-both, presenting more generalization ability. Our approach achieves state-of-the-art (SOTA) performance on both real and simulated cooperative perception datasets. The code will be released at GitHub in early 2025.
Authors: Jos\'e V. Manj\'on, Sergio Morell-Ortega, Marina Ruiz-Perez, Boris Mansencal, Edern Le Bot, Marien Gadea, Enrique Lanuza, Gwenaelle Catheline, Thomas Tourdias, Vincent Planche, R\'emi Giraud, Denis Rivi\`ere, Jean-Fran\c{c}ois Mangin, Nicole Labra-Avila, Roberto Vivo-Hernando, Gregorio Rubio, Fernando Aparici, Maria de la Iglesia-Vaya, Pierrick Coup\'e
Abstract: In this paper, we introduce holiAtlas, a holistic, multimodal and high-resolution human brain atlas. This atlas covers different levels of details of the human brain anatomy, from the organ to the substructure level, using a new dense labelled protocol generated from the fusion of multiple local protocols at different scales. This atlas has been constructed averaging images and segmentations of 75 healthy subjects from the Human Connectome Project database. Specifically, MR images of T1, T2 and WMn (White Matter nulled) contrasts at 0.125 $mm^{3}$ resolution that were nonlinearly registered and averaged using symmetric group-wise normalisation to construct the atlas. At the finest level, the holiAtlas protocol has 350 different labels derived from 10 different delineation protocols. These labels were grouped at different scales to provide a holistic view of the brain at different levels in a coherent and consistent manner. This multiscale and multimodal atlas can be used for the development of new ultra-high resolution segmentation methods that can potentially leverage the early detection of neurological disorders.
Authors: Kanishk Chaturvedi, Johannes Gasthuber, Mohamed Abdelaal
Abstract: This paper introduces EdgeMLOps, a framework leveraging Cumulocity IoT and thin-edge.io for deploying and managing machine learning models on resource-constrained edge devices. We address the challenges of model optimization, deployment, and lifecycle management in edge environments. The framework's efficacy is demonstrated through a visual quality inspection (VQI) use case where images of assets are processed on edge devices, enabling real-time condition updates within an asset management system. Furthermore, we evaluate the performance benefits of different quantization methods, specifically static and dynamic signed-int8, on a Raspberry Pi 4, demonstrating significant inference time reductions compared to FP32 precision. Our results highlight the potential of EdgeMLOps to enable efficient and scalable AI deployments at the edge for industrial applications.
Authors: Nuwan T. Attygalle, Matja\v{z} Kljun, Aaron Quigley, Klen \v{c}Opi\v{c} Pucihar, Jens Grubert, Verena Biener, Luis A. Leiva, Juri Yoneyama, Alice Toniolo, Angela Miguel, Hirokazu Kato, Maheshya Weerasinghe
Abstract: The 'keyword method' is an effective technique for learning vocabulary of a foreign language. It involves creating a memorable visual link between what a word means and what its pronunciation in a foreign language sounds like in the learner's native language. However, these memorable visual links remain implicit in the people's mind and are not easy to remember for a large set of words. To enhance the memorisation and recall of the vocabulary, we developed an application that combines the keyword method with text-to-image generators to externalise the memorable visual links into visuals. These visuals represent additional stimuli during the memorisation process. To explore the effectiveness of this approach we first run a pilot study to investigate how difficult it is to externalise the descriptions of mental visualisations of memorable links, by asking participants to write them down. We used these descriptions as prompts for text-to-image generator (DALL-E2) to convert them into images and asked participants to select their favourites. Next, we compared different text-to-image generators (DALL-E2, Midjourney, Stable and Latent Diffusion) to evaluate the perceived quality of the generated images by each. Despite heterogeneous results, participants mostly preferred images generated by DALL-E2, which was used also for the final study. In this study, we investigated whether providing such images enhances the retention of vocabulary being learned, compared to the keyword method only. Our results indicate that people did not encounter difficulties describing their visualisations of memorable links and that providing corresponding images significantly improves memory retention.
Authors: Suresh Babu Nettur, Shanthi Karpurapu, Unnati Nettur, Likhit Sagar Gajja, Sravanthy Myneni, Akhil Dusi, Lalithya Posham
Abstract: Early detection of COVID-19 is crucial for effective treatment and controlling its spread. This study proposes a novel hybrid deep learning model for detecting COVID-19 from CT scan images, designed to assist overburdened medical professionals. Our proposed model leverages the strengths of VGG16, DenseNet121, and MobileNetV2 to extract features, followed by Principal Component Analysis (PCA) for dimensionality reduction, after which the features are stacked and classified using a Support Vector Classifier (SVC). We conducted comparative analysis between the proposed hybrid model and individual pre-trained CNN models, using a dataset of 2,108 training images and 373 test images comprising both COVID-positive and non-COVID images. Our proposed hybrid model achieved an accuracy of 98.93%, outperforming the individual models in terms of precision, recall, F1 scores, and ROC curve performance.
Authors: Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, Yi Ma
Abstract: Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the difference between SFT and RL on generalization and memorization, focusing on text-based rule variants and visual variants. We introduce GeneralPoints, an arithmetic reasoning card game, and adopt V-IRL, a real-world navigation environment, to assess how models trained with SFT and RL generalize to unseen variants in both textual and visual domains. We show that RL, especially when trained with an outcome-based reward, generalizes across both rule-based textual and visual variants. SFT, in contrast, tends to memorize training data and struggles to generalize out-of-distribution scenarios. Further analysis reveals that RL improves the model's underlying visual recognition capabilities, contributing to its enhanced generalization in the visual domain. Despite RL's superior generalization, we show that SFT remains essential for effective RL training; SFT stabilizes the model's output format, enabling subsequent RL to achieve its performance gains. These findings demonstrates the capability of RL for acquiring generalizable knowledge in complex, multi-modal tasks.
Authors: Feihong Shen, Jun Liu, Ping Hu
Abstract: zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based on the generative model Most new proposed works added structures on the same architecture to enhance this model. However, we found that, from the view of causal inference, the result of the original model has been influenced by spurious statistical relationships. Thus the performance of the prediction shows severe bias. In this work, we consider counterfactual methods to avoid the confounder in the original model. Based on this method, we proposed a new framework for zero-shot semantic segmentation. Our model is compared with baseline models on two real-world datasets, Pascal-VOC and Pascal-Context. The experiment results show proposed models can surpass previous confounded models and can still make use of additional structures to improve the performance. We also design a simple structure based on Graph Convolutional Networks (GCN) in this work.
Authors: Riccardo Barbano, Alexander Denker, Hyungjin Chung, Tae Hoon Roh, Simon Arridge, Peter Maass, Bangti Jin, Jong Chul Ye
Abstract: Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge. Using a diffusion model on an out-of-distribution dataset, realistic reconstructions can be generated, but with hallucinating image features that are uniquely present in the training dataset. To address this discrepancy during train-test time and improve reconstruction accuracy, we introduce a novel sampling framework called Steerable Conditional Diffusion. Specifically, this framework adapts the diffusion model, concurrently with image reconstruction, based solely on the information provided by the available measurement. Utilising our proposed method, we achieve substantial enhancements in out-of-distribution performance across diverse imaging modalities, advancing the robust deployment of denoising diffusion models in real-world applications.
Authors: Olatunji Mumini Omisore, Toluwanimi Akinyemi, Anh Nguyen, Lei Wang
Abstract: Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking of endovascular tools during cardiac procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is both labor-intensive time consuming, and costly. In this study, we propose a weakly-supervised learning method with multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations, augmenting available partial labels. The pseudo labels are self-generated using a mixed loss function with shared consistency across the decoders. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the model could perform closer to fully-supervised models. Also, the proposed weakly-supervised multi-lateral method outperforms three well known methods used for weakly-supervised learning, offering the highest segmentation performance across the three angiogram datasets. Furthermore, numerous ablation studies confirmed the model's consistent performance under different parameters. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean processing time of 35 ms per frame.
Authors: Giuseppe Vecchio
Abstract: We introduce StableMaterials, a novel approach for generating photorealistic physical-based rendering (PBR) materials that integrate semi-supervised learning with Latent Diffusion Models (LDMs). Our method employs adversarial training to distill knowledge from existing large-scale image generation models, minimizing the reliance on annotated data and enhancing the diversity in generation. This distillation approach aligns the distribution of the generated materials with that of image textures from an SDXL model, enabling the generation of novel materials that are not present in the initial training dataset. Furthermore, we employ a diffusion-based refiner model to improve the visual quality of the samples and achieve high-resolution generation. Finally, we distill a latent consistency model for fast generation in just four steps and propose a new tileability technique that removes visual artifacts typically associated with fewer diffusion steps. We detail the architecture and training process of StableMaterials, the integration of semi-supervised training within existing LDM frameworks and show the advantages of our approach. Comparative evaluations with state-of-the-art methods show the effectiveness of StableMaterials, highlighting its potential applications in computer graphics and beyond. StableMaterials is publicly available at https://gvecchio.com/stablematerials.
Authors: Chih-Hsuan Yang, Benjamin Feuer, Zaki Jubery, Zi K. Deng, Andre Nakkab, Md Zahid Hasan, Shivani Chiranjeevi, Kelly Marshall, Nirmal Baishnab, Asheesh K Singh, Arti Singh, Soumik Sarkar, Nirav Merchant, Chinmay Hegde, Baskar Ganapathysubramanian
Abstract: We introduce BioTrove, the largest publicly accessible dataset designed to advance AI applications in biodiversity. Curated from the iNaturalist platform and vetted to include only research-grade data, BioTrove contains 161.9 million images, offering unprecedented scale and diversity from three primary kingdoms: Animalia ("animals"), Fungi ("fungi"), and Plantae ("plants"), spanning approximately 366.6K species. Each image is annotated with scientific names, taxonomic hierarchies, and common names, providing rich metadata to support accurate AI model development across diverse species and ecosystems. We demonstrate the value of BioTrove by releasing a suite of CLIP models trained using a subset of 40 million captioned images, known as BioTrove-Train. This subset focuses on seven categories within the dataset that are underrepresented in standard image recognition models, selected for their critical role in biodiversity and agriculture: Aves ("birds"), Arachnida ("spiders/ticks/mites"), Insecta ("insects"), Plantae ("plants"), Fungi ("fungi"), Mollusca ("snails"), and Reptilia ("snakes/lizards"). To support rigorous assessment, we introduce several new benchmarks and report model accuracy for zero-shot learning across life stages, rare species, confounding species, and multiple taxonomic levels. We anticipate that BioTrove will spur the development of AI models capable of supporting digital tools for pest control, crop monitoring, biodiversity assessment, and environmental conservation. These advancements are crucial for ensuring food security, preserving ecosystems, and mitigating the impacts of climate change. BioTrove is publicly available, easily accessible, and ready for immediate use.
Authors: Zhaojie Fang, Shenghao Zhu, Yifei Chen, Binfeng Zou, Fan Jia, Linwei Qiu, Chang Liu, Xiang Feng, Changmiao Wang, Feiwei Qin, Jin Fan, Changbiao Chu
Abstract: Alzheimer's Disease (AD) is a progressive, irreversible neurodegenerative disorder that often originates from Mild Cognitive Impairment (MCI). This progression results in significant memory loss and severely affects patients' quality of life. Clinical trials have consistently shown that early and targeted interventions for individuals with MCI may slow or even prevent the advancement of AD. Research indicates that accurate medical classification requires diverse multimodal data, including detailed assessment scales and neuroimaging techniques like Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). However, simultaneously collecting the aforementioned three modalities for training presents substantial challenges. To tackle these difficulties, we propose GFE-Mamba, a multimodal classifier founded on Generative Feature Extractor. The intermediate features provided by this Extractor can compensate for the shortcomings of PET and achieve profound multimodal fusion in the classifier. The Mamba block, as the backbone of the classifier, enables it to efficiently extract information from long-sequence scale information. Pixel-level Bi-cross Attention supplements pixel-level information from MRI and PET. We provide our rationale for developing this cross-temporal progression prediction dataset and the pre-trained Extractor weights. Our experimental findings reveal that the GFE-Mamba model effectively predicts the progression from MCI to AD and surpasses several leading methods in the field. Our source code is available at https://github.com/Tinysqua/GFE-Mamba.
Authors: Yihong Lin, Zhaoxin Fan, Xianjia Wu, Lingyu Xiong, Liang Peng, Xiandong Li, Wenxiong Kang, Songju Lei, Huang Xu
Abstract: Speech-driven talking head generation is a critical yet challenging task with applications in augmented reality and virtual human modeling. While recent approaches using autoregressive and diffusion-based models have achieved notable progress, they often suffer from modality inconsistencies, particularly misalignment between audio and mesh, leading to reduced motion diversity and lip-sync accuracy. To address this, we propose GLDiTalker, a novel speech-driven 3D facial animation model based on a Graph Latent Diffusion Transformer. GLDiTalker resolves modality misalignment by diffusing signals within a quantized spatiotemporal latent space. It employs a two-stage training pipeline: the Graph-Enhanced Quantized Space Learning Stage ensures lip-sync accuracy, while the Space-Time Powered Latent Diffusion Stage enhances motion diversity. Together, these stages enable GLDiTalker to generate realistic, temporally stable 3D facial animations. Extensive evaluations on standard benchmarks demonstrate that GLDiTalker outperforms existing methods, achieving superior results in both lip-sync accuracy and motion diversity.
Authors: Yihong Lin, Liang Peng, Xianjia Wu, Jianqiao Hu, Xiandong Li, Wenxiong Kang, Songju Lei, Huang Xu
Abstract: The creation of increasingly vivid 3D talking face has become a hot topic in recent years. Currently, most speech-driven works focus on lip synchronisation but neglect to effectively capture the correlations between emotions and facial motions. To address this problem, we propose a two-stream network called EmoFace, which consists of an emotion branch and a content branch. EmoFace employs a novel Mesh Attention mechanism to analyse and fuse the emotion features and content features. Particularly, a newly designed spatio-temporal graph-based convolution, SpiralConv3D, is used in Mesh Attention to learn potential temporal and spatial feature dependencies between mesh vertices. In addition, to the best of our knowledge, it is the first time to introduce a new self-growing training scheme with intermediate supervision to dynamically adjust the ratio of groundtruth adopted in the 3D face animation task. Comprehensive quantitative and qualitative evaluations on our high-quality 3D emotional facial animation dataset, 3D-RAVDESS ($4.8863\times 10^{-5}$mm for LVE and $0.9509\times 10^{-5}$mm for EVE), together with the public dataset VOCASET ($2.8669\times 10^{-5}$mm for LVE and $0.4664\times 10^{-5}$mm for EVE), demonstrate that our approach achieves state-of-the-art performance.
Authors: Junkun Chen, Jilin Mei, Liang Chen, Fangzhou Zhao, Yan Xing, Yu Hu
Abstract: Neural networks that are trained on limited category samples often mispredict out-of-distribution (OOD) objects. We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed. Based on this, we propose using prototype similarity for OOD detection. Drawing on widely used prototype features in few-shot learning, we introduce a novel OOD detection network structure (Proto-OOD). Proto-OOD enhances the representativeness of category prototypes using contrastive loss and detects OOD data by evaluating the similarity between input features and category prototypes. During training, Proto-OOD generates OOD samples for training the similarity module with a negative embedding generator. When Pascal VOC are used as the in-distribution dataset and MS-COCO as the OOD dataset, Proto-OOD significantly reduces the FPR (false positive rate). Moreover, considering the limitations of existing evaluation metrics, we propose a more reasonable evaluation protocol. The code will be released.
Authors: Fran\c{c}ois David, Alexey A. Novikov, Ruslan Parkhomenko, Artem Voronin, Alix Melchy
Abstract: This paper introduces a comprehensive model for age estimation, verification, and comparability, offering a comprehensive solution for a wide range of applications. It employs advanced learning techniques to understand age distribution and uses confidence scores to create probabilistic age ranges, enhancing its ability to handle ambiguous cases. The model has been tested on both proprietary and public datasets and compared against one of the top-performing models in the field. Additionally, it has recently been evaluated by NIST as part of the FATE challenge, achieving top places in many categories.
Authors: Zhaorui Tan, Xi Yang, Qiufeng Wang, Anh Nguyen, Kaizhu Huang
Abstract: Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories. In this paper, we explore the relationship between logical reasoning and deep learning generalization in visual classification. A logical regularization termed L-Reg is derived which bridges a logical analysis framework to image classification. Our work reveals that L-Reg reduces the complexity of the model in terms of the feature distribution and classifier weights. Specifically, we unveil the interpretability brought by L-Reg, as it enables the model to extract the salient features, such as faces to persons, for classification. Theoretical analysis and experiments demonstrate that L-Reg enhances generalization across various scenarios, including multi-domain generalization and generalized category discovery. In complex real-world scenarios where images span unknown classes and unseen domains, L-Reg consistently improves generalization, highlighting its practical efficacy.
Authors: Juliette Marrie, Romain Menegaux, Michael Arbel, Diane Larlus, Julien Mairal
Abstract: We address the problem of extending the capabilities of vision foundation models such as DINO, SAM, and CLIP, to 3D tasks. Specifically, we introduce a novel method to uplift 2D image features into Gaussian Splatting representations of 3D scenes. Unlike traditional approaches that rely on minimizing a reconstruction loss, our method employs a simpler and more efficient feature aggregation technique, augmented by a graph diffusion mechanism. Graph diffusion refines 3D features, such as coarse segmentation masks, by leveraging 3D geometry and pairwise similarities induced by DINOv2. Our approach achieves performance comparable to the state of the art on multiple downstream tasks while delivering significant speed-ups. Notably, we obtain competitive segmentation results using generic DINOv2 features, despite DINOv2 not being trained on millions of annotated segmentation masks like SAM. When applied to CLIP features, our method demonstrates strong performance in open-vocabulary object localization tasks, highlighting the versatility of our approach.
Authors: Julian Bigge, Maite Ogueta, Luis Garcia, Benjamin Risse
Abstract: In this paper we propose the Hatching-Box, a novel imaging and analysis system to automatically monitor and quantify the developmental behavior of Drosophila in standard rearing vials and during regular rearing routines, rendering explicit experiments obsolete. This is achieved by combining custom tailored imaging hardware with dedicated detection and tracking algorithms, enabling the quantification of larvae, filled/empty pupae and flies over multiple days. Given the affordable and reproducible design of the Hatching-Box in combination with our generic client/server-based software, the system can easily be scaled to monitor an arbitrary amount of rearing vials simultaneously. We evaluated our system on a curated image dataset comprising nearly 470,000 annotated objects and performed several studies on real world experiments. We successfully reproduced results from well-established circadian experiments by comparing the eclosion periods of wild type flies to the clock mutants $\textit{per}^{short}$, $\textit{per}^{long}$ and $\textit{per}^0$ without involvement of any manual labor. Furthermore we show, that the Hatching-Box is able to extract additional information about group behavior as well as to reconstruct the whole life-cycle of the individual specimens. These results not only demonstrate the applicability of our system for long-term experiments but also indicate its benefits for automated monitoring in the general cultivation process.
Authors: Deven B. Dangi, Beni B. Dangi, Oliver Steinbock
Abstract: When microliter drops of salt solutions dry on non-porous surfaces, they form erratic yet characteristic deposit patterns influenced by complex crystallization dynamics and fluid motion. Using OpenAI's image-enabled language models, we analyzed deposits from 12 salts with 200 images per salt and per model. GPT-4o classified 57% of the salts accurately, significantly outperforming random chance and GPT-4o mini. This study underscores the promise of general-use AI tools for reliably identifying salts from their drying patterns.
Authors: Zhifei Chen, Tianshuo Xu, Wenhang Ge, Leyi Wu, Dongyu Yan, Jing He, Luozhou Wang, Lu Zeng, Shunsi Zhang, Yingcong Chen, Hui Xiong
Abstract: Rendering and inverse rendering are pivotal tasks in both computer vision and graphics. The rendering equation is the core of the two tasks, as an ideal conditional distribution transfer function from intrinsic properties to RGB images. Despite achieving promising results of existing rendering methods, they merely approximate the ideal estimation for a specific scene and come with a high computational cost. Additionally, the inverse conditional distribution transfer is intractable due to the inherent ambiguity. To address these challenges, we propose a data-driven method that jointly models rendering and inverse rendering as two conditional generation tasks within a single diffusion framework. Inspired by UniDiffuser, we utilize two distinct time schedules to model both tasks, and with a tailored dual streaming module, we achieve cross-conditioning of two pre-trained diffusion models. This unified approach, named Uni-Renderer, allows the two processes to facilitate each other through a cycle-consistent constrain, mitigating ambiguity by enforcing consistency between intrinsic properties and rendered images. Combined with a meticulously prepared dataset, our method effectively decomposition of intrinsic properties and demonstrates a strong capability to recognize changes during rendering. We will open-source our training and inference code to the public, fostering further research and development in this area.
Authors: Shaoyan Pan, Yikang Liu, Lin Zhao, Eric Z. Chen, Xiao Chen, Terrence Chen, Shanhui Sun
Abstract: The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.
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: Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao
Abstract: In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. The meaning of "vision-centric" is two-fold: the vision-centric training paradigm and vision-centric framework design. The key insight of our vision-centric training paradigm is that high-quality image-text data is crucial for both image and video understanding. Instead of preparing massive video-text datasets, we focus on constructing large-scale and high-quality image-text datasets. VideoLLaMA3 has four training stages: 1) Vision Encoder Adaptation, which enables vision encoder to accept images of variable resolutions as input; 2) Vision-Language Alignment, which jointly tunes the vision encoder, projector, and LLM with large-scale image-text data covering multiple types (including scene images, documents, charts) as well as text-only data. 3) Multi-task Fine-tuning, which incorporates image-text SFT data for downstream tasks and video-text data to establish a foundation for video understanding. 4) Video-centric Fine-tuning, which further improves the model's capability in video understanding. As for the framework design, to better capture fine-grained details in images, the pretrained vision encoder is adapted to encode images of varying sizes into vision tokens with corresponding numbers, rather than a fixed number of tokens. For video inputs, we reduce the number of vision tokens according to their similarity so that the representation of videos will be more precise and compact. Benefit from vision-centric designs, VideoLLaMA3 achieves compelling performances in both image and video understanding benchmarks.
Authors: Taegyeong Lee, Jinsik Bang, Soyeong Kwon, Taehwan Kim
Abstract: Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs). Our approach involves: 1) querying Large Language Model with multi-aspect questions relevant to the knowledge we want to transfer to the model, 2) extracting corresponding logits from MLLM, and 3) expanding the model's output dimensions to distill these multi-aspect logits. We then apply cross-entropy loss to class logits and binary cross-entropy loss to multi-aspect logits. Through our method, the model can learn not only the knowledge about visual aspects but also the abstract and complex aspects that require a deeper understanding. We primarily apply our method to image classification, and to explore the potential for extending our model, we expand it to other tasks, such as object detection. In all experimental results, our method improves the performance of the baselines. Additionally, we analyze the effect of multi-aspect knowledge distillation. These results demonstrate that our method can transfer knowledge about various aspects to the model and the aspect knowledge can enhance model performance in computer vision tasks. This paper demonstrates the great potential of multi-aspect knowledge distillation, and we believe it offers a promising direction for future research in computer vision and beyond.
Authors: Yimeng Fan, Changsong Liu, Mingyang Li, Wei Zhang
Abstract: As the third generation of neural networks, Spiking Neural Networks (SNNs) have gained widespread attention due to their low energy consumption and biological interpretability. Recently, SNNs have made considerable advancements in computer vision. However, efficiently conducting feature extraction and fusion under the spiking characteristics of SNNs for object detection remains a pressing challenge. To address this problem, we propose the SpikSSD, a novel Spiking Single Shot Multibox Detector. Specifically, we design a full-spiking backbone network, MDS-ResNet, which effectively adjusts the membrane synaptic input distribution at each layer, achieving better spiking feature extraction. Additionally, for spiking feature fusion, we introduce the Spiking Bi-direction Fusion Module (SBFM), which for the first time realizes bi-direction fusion of spiking features, enhancing the multi-scale detection capability of the model. Experimental results show that SpikSSD achieves 40.8% mAP on the GEN1 dataset, 76.3% and 52.4% mAP@0.5 on VOC 2007 and COCO 2017 datasets respectively with the lowest firing rate, outperforming existing SNN-based approaches at ultralow energy consumption. This work sets a new benchmark for future research in SNN-based object detection. Our code is publicly available in https://github.com/yimeng-fan/SpikSSD.
Authors: Zecheng Li, Wengang Zhou, Weichao Zhao, Kepeng Wu, Hezhen Hu, Houqiang Li
Abstract: Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks. However, existing methods often suffer from a gap between pre-training and fine-tuning, leading to suboptimal results. To address this, we propose Uni-Sign, a unified pre-training framework that eliminates the gap between pre-training and downstream SLU tasks through a large-scale generative pre-training strategy and a novel fine-tuning paradigm. First, we introduce CSL-News, a large-scale Chinese Sign Language (CSL) dataset containing 1,985 hours of video paired with textual annotations, which enables effective large-scale pre-training. Second, Uni-Sign unifies SLU tasks by treating downstream tasks as a single sign language translation (SLT) task during fine-tuning, ensuring seamless knowledge transfer between pre-training and fine-tuning. Furthermore, we incorporate a prior-guided fusion (PGF) module and a score-aware sampling strategy to efficiently fuse pose and RGB information, addressing keypoint inaccuracies and improving computational efficiency. Extensive experiments across multiple SLU benchmarks demonstrate that Uni-Sign achieves state-of-the-art performance across multiple downstream SLU tasks. Dataset and code are available at github.com/ZechengLi19/Uni-Sign.
Authors: Emma Most, Jonas Hein, Fr\'ed\'eric Giraud, Nicola A. Cavalcanti, Lukas Zingg, Baptiste Brument, Nino Louman, Fabio Carrillo, Philipp F\"urnstahl, Lilian Calvet
Abstract: Advances in computer vision, particularly in optical image-based 3D reconstruction and feature matching, enable applications like marker-less surgical navigation and digitization of surgery. However, their development is hindered by a lack of suitable datasets with 3D ground truth. This work explores an approach to generating realistic and accurate ex vivo datasets tailored for 3D reconstruction and feature matching in open orthopedic surgery. A set of posed images and an accurately registered ground truth surface mesh of the scene are required to develop vision-based 3D reconstruction and matching methods suitable for surgery. We propose a framework consisting of three core steps and compare different methods for each step: 3D scanning, calibration of viewpoints for a set of high-resolution RGB images, and an optical-based method for scene registration. We evaluate each step of this framework on an ex vivo scoliosis surgery using a pig spine, conducted under real operating room conditions. A mean 3D Euclidean error of 0.35 mm is achieved with respect to the 3D ground truth. The proposed method results in submillimeter accurate 3D ground truths and surgical images with a spatial resolution of 0.1 mm. This opens the door to acquiring future surgical datasets for high-precision applications.
Authors: Ashim Dahal, Saydul Akbar Murad, Nick Rahimi
Abstract: Algorithmic level developments like Convolutional Neural Networks, transformers, attention mechanism, Retrieval Augmented Generation and so on have changed Artificial Intelligence. Recent such development was observed by Kolmogorov-Arnold Networks that suggested to challenge the fundamental concept of a Neural Network, thus change Multilayer Perceptron, and Convolutional Neural Networks. They received a good reception in terms of scientific modeling, yet had some drawbacks in terms of efficiency. In this paper, we train Convolutional Kolmogorov Arnold Networks (CKANs) with the ImageNet-1k dataset with 1.3 million images, MNIST dataset with 60k images and a tabular biological science related MoA dataset and test the promise of CKANs in terms of FLOPS, Inference Time, number of trainable parameters and training time against the accuracy, precision, recall and f-1 score they produce against the standard industry practice on CNN models. We show that the CKANs perform fair yet slower than CNNs in small size dataset like MoA and MNIST but are not nearly comparable as the dataset gets larger and more complex like the ImageNet. The code implementation of this paper can be found on the link: \href{https://github.com/ashimdahal/Study-of-Convolutional-Kolmogorov-Arnold-networks}{https://github.com/ashimdahal/Study-of-Convolutional-Kolmogorov-Arnold-networks}
URLs: https://github.com/ashimdahal/Study-of-Convolutional-Kolmogorov-Arnold-networks, https://github.com/ashimdahal/Study-of-Convolutional-Kolmogorov-Arnold-networks
Authors: Adil Kaan Akan, Yucel Yemez
Abstract: We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion models, while avoiding their text-centric conditioning bias. We also incorporate an additional guidance loss into our architecture to align cross-attention from adapter layers with slot attention. This enhances the alignment of our model with the objects in the input image without using external supervision. Experimental results show that our method outperforms state-of-the-art techniques in object discovery and image generation tasks across multiple datasets, including those with real images. Furthermore, we demonstrate through experiments that our method performs remarkably well on complex real-world images for compositional generation, in contrast to other slot-based generative methods in the literature. The project page can be found at https://kaanakan.github.io/SlotAdapt/.
Authors: Li Pang, Jing Yao, Kaiyu Li, Xiangyong Cao
Abstract: Hyperspectral image (HSI) classification aims at categorizing each pixel in an HSI into a specific land cover class, which is crucial for applications like remote sensing, environmental monitoring, and agriculture. Although deep learning-based HSI classification methods have achieved significant advancements, existing methods still rely on manually labeled data for training, which is both time-consuming and labor-intensive. To address this limitation, we introduce a novel zero-shot hyperspectral image classification framework based on CLIP (SPECIAL), aiming to eliminate the need for manual annotations. The SPECIAL framework consists of two main stages: (1) CLIP-based pseudo-label generation, and (2) noisy label learning. In the first stage, HSI is spectrally interpolated to produce RGB bands. These bands are subsequently classified using CLIP, resulting in noisy pseudo-labels that are accompanied by confidence scores. To improve the quality of these labels, we propose a scaling strategy that fuses predictions from multiple spatial scales. In the second stage, spectral information and a label refinement technique are incorporated to mitigate label noise and further enhance classification accuracy. Experimental results on three benchmark datasets demonstrate that our SPECIAL outperforms existing methods in zero-shot HSI classification, showing its potential for more practical applications. The code is available at https://github.com/LiPang/SPECIAL.
Authors: Alexandre Filiot, Nicolas Dop, Oussama Tchita, Auriane Riou, R\'emy Dubois, Thomas Peeters, Daria Valter, Marin Scalbert, Charlie Saillard, Genevi\`eve Robin, Antoine Olivier
Abstract: In recent years, the advent of foundation models (FM) for digital pathology has relied heavily on scaling the pre-training datasets and the model size, yielding large and powerful models. While it resulted in improving the performance on diverse downstream tasks, it also introduced increased computational cost and inference time. In this work, we explore the distillation of a large foundation model into a smaller one, reducing the number of parameters by several orders of magnitude. Leveraging distillation techniques, our distilled model, H0-mini, achieves nearly comparable performance to large FMs at a significantly reduced inference cost. It is evaluated on several public benchmarks, achieving 3rd place on the HEST benchmark and 5th place on the EVA benchmark. Additionally, a robustness analysis conducted on the PLISM dataset demonstrates that our distilled model reaches excellent robustness to variations in staining and scanning conditions, significantly outperforming other state-of-the art models. This opens new perspectives to design lightweight and robust models for digital pathology, without compromising on performance.
Authors: Nicolas von L\"utzow, Matthias Nie{\ss}ner
Abstract: Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we explore an alternative volumetric scene representation. More specifically, we introduce two new scene representations based on linear primitives-octahedra and tetrahedra-both of which define homogeneous volumes bounded by triangular faces. This formulation aligns naturally with standard mesh-based tools, minimizing overhead for downstream applications. To optimize these primitives, we present a differentiable rasterizer that runs efficiently on GPUs, allowing end-to-end gradient-based optimization while maintaining realtime rendering capabilities. Through experiments on real-world datasets, we demonstrate comparable performance to state-of-the-art volumetric methods while requiring fewer primitives to achieve similar reconstruction fidelity. Our findings provide insights into the geometry of volumetric rendering and suggest that adopting explicit polyhedra can expand the design space of scene representations.
Authors: Hanrui Wang, Zirui Li, Jiaqi Gu, Yongshan Ding, David Z. Pan, Song Han
Abstract: Parameterized Quantum Circuits (PQC) are drawing increasing research interest thanks to its potential to achieve quantum advantages on near-term Noisy Intermediate Scale Quantum (NISQ) hardware. In order to achieve scalable PQC learning, the training process needs to be offloaded to real quantum machines instead of using exponential-cost classical simulators. One common approach to obtain PQC gradients is parameter shift whose cost scales linearly with the number of qubits. We present QOC, the first experimental demonstration of practical on-chip PQC training with parameter shift. Nevertheless, we find that due to the significant quantum errors (noises) on real machines, gradients obtained from naive parameter shift have low fidelity and thus degrading the training accuracy. To this end, we further propose probabilistic gradient pruning to firstly identify gradients with potentially large errors and then remove them. Specifically, small gradients have larger relative errors than large ones, thus having a higher probability to be pruned. We perform extensive experiments with the Quantum Neural Network (QNN) benchmarks on 5 classification tasks using 5 real quantum machines. The results demonstrate that our on-chip training achieves over 90% and 60% accuracy for 2-class and 4-class image classification tasks. The probabilistic gradient pruning brings up to 7% PQC accuracy improvements over no pruning. Overall, we successfully obtain similar on-chip training accuracy compared with noise-free simulation but have much better training scalability. The QOC code is available in the TorchQuantum library.
Authors: Amandine Brunetto, Sascha Hornauer, Fabien Moutarde
Abstract: Sound plays a major role in human perception. Along with vision, it provides essential information for understanding our surroundings. Despite advances in neural implicit representations, learning acoustics that align with visual scenes remains a challenge. We propose NeRAF, a method that jointly learns acoustic and radiance fields. NeRAF synthesizes both novel views and spatialized room impulse responses (RIR) at new positions by conditioning the acoustic field on 3D scene geometric and appearance priors from the radiance field. The generated RIR can be applied to auralize any audio signal. Each modality can be rendered independently and at spatially distinct positions, offering greater versatility. We demonstrate that NeRAF generates high-quality audio on SoundSpaces and RAF datasets, achieving significant performance improvements over prior methods while being more data-efficient. Additionally, NeRAF enhances novel view synthesis of complex scenes trained with sparse data through cross-modal learning. NeRAF is designed as a Nerfstudio module, providing convenient access to realistic audio-visual generation.
Authors: Matej Gazda, Samuel Kadoury, Jakub Gazda, Peter Drotar
Abstract: Transthoracic Echocardiography (TTE) is a fundamental, non-invasive diagnostic tool in cardiovascular medicine, enabling detailed visualization of cardiac structures crucial for diagnosing various heart conditions. Despite its widespread use, TTE ultrasound imaging faces inherent limitations, notably the trade-off between field of view (FoV) and resolution. This paper introduces a novel application of conditional Generative Adversarial Networks (cGANs), specifically designed to extend the FoV in TTE ultrasound imaging while maintaining high resolution. Our proposed cGAN architecture, termed echoGAN, demonstrates the capability to generate realistic anatomical structures through outpainting, effectively broadening the viewable area in medical imaging. This advancement has the potential to enhance both automatic and manual ultrasound navigation, offering a more comprehensive view that could significantly reduce the learning curve associated with ultrasound imaging and aid in more accurate diagnoses. The results confirm that echoGAN reliably reproduce detailed cardiac features, thereby promising a significant step forward in the field of non-invasive cardiac naviagation and diagnostics.
Authors: Guohui Cai, Ruicheng Zhang, Hongyang He, Zeyu Zhang, Daji Ergu, Yuanzhouhan Cao, Jinman Zhao, Binbin Hu, Zhinbin Liao, Yang Zhao, Ying Cai
Abstract: Pulmonary nodules are critical indicators for the early diagnosis of lung cancer, making their detection essential for timely treatment. However, traditional CT imaging methods suffered from cumbersome procedures, low detection rates, and poor localization accuracy. The subtle differences between pulmonary nodules and surrounding tissues in complex lung CT images, combined with repeated downsampling in feature extraction networks, often lead to missed or false detections of small nodules. Existing methods such as FPN, with its fixed feature fusion and limited receptive field, struggle to effectively overcome these issues. To address these challenges, our paper proposed three key contributions: Firstly, we proposed MSDet, a multiscale attention and receptive field network for detecting tiny pulmonary nodules. Secondly, we proposed the extended receptive domain (ERD) strategy to capture richer contextual information and reduce false positives caused by nodule occlusion. We also proposed the position channel attention mechanism (PCAM) to optimize feature learning and reduce multiscale detection errors, and designed the tiny object detection block (TODB) to enhance the detection of tiny nodules. Lastly, we conducted thorough experiments on the public LUNA16 dataset, achieving state-of-the-art performance, with an mAP improvement of 8.8% over the previous state-of-the-art method YOLOv8. These advancements significantly boosted detection accuracy and reliability, providing a more effective solution for early lung cancer diagnosis. The code will be available at https://github.com/CaiGuoHui123/MSDet
Authors: Xin Li, Zhihong Xia, Hongkun Zhang
Abstract: We have developed a novel activation function, named the Cauchy Activation Function. This function is derived from the Cauchy Integral Theorem in complex analysis and is specifically tailored for problems requiring high precision. This innovation has led to the creation of a new class of neural networks, which we call (Comple)XNet, or simply XNet. We will demonstrate that XNet is particularly effective for high-dimensional challenges such as image classification and solving Partial Differential Equations (PDEs). Our evaluations show that XNet significantly outperforms established benchmarks like MNIST and CIFAR-10 in computer vision, and offers substantial advantages over Physics-Informed Neural Networks (PINNs) in both low-dimensional and high-dimensional PDE scenarios.
Authors: Jan Obrist, Miguel Zamora, Hehui Zheng, Ronan Hinchet, Firat Ozdemir, Juan Zarate, Robert K. Katzschmann, Stelian Coros
Abstract: Data-driven methods have shown great potential in solving challenging manipulation tasks; however, their application in the domain of deformable objects has been constrained, in part, by the lack of data. To address this lack, we propose PokeFlex, a dataset featuring real-world multimodal data that is paired and annotated. The modalities include 3D textured meshes, point clouds, RGB images, and depth maps. Such data can be leveraged for several downstream tasks, such as online 3D mesh reconstruction, and it can potentially enable underexplored applications such as the real-world deployment of traditional control methods based on mesh simulations. To deal with the challenges posed by real-world 3D mesh reconstruction, we leverage a professional volumetric capture system that allows complete 360{\deg} reconstruction. PokeFlex consists of 18 deformable objects with varying stiffness and shapes. Deformations are generated by dropping objects onto a flat surface or by poking the objects with a robot arm. Interaction wrenches and contact locations are also reported for the latter case. Using different data modalities, we demonstrated a use case for our dataset training models that, given the novelty of the multimodal nature of Pokeflex, constitute the state-of-the-art in multi-object online template-based mesh reconstruction from multimodal data, to the best of our knowledge. We refer the reader to our website ( https://pokeflex-dataset.github.io/ ) for further demos and examples.
Authors: Zhenhailong Wang, Haiyang Xu, Junyang Wang, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, Heng Ji
Abstract: Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent framework capable of self-evolution through past experience. By hierarchical, we mean an explicit separation of high-level planning and low-level action execution. The framework comprises a Manager, responsible for devising overall plans by breaking down complex tasks into subgoals, and four subordinate agents--Perceptor, Operator, Action Reflector, and Notetaker--which handle fine-grained visual perception, immediate action execution, error verification, and information aggregation, respectively. Mobile-Agent-E also features a novel self-evolution module which maintains a persistent long-term memory comprising Tips and Shortcuts. Tips are general guidance and lessons learned from prior tasks on how to effectively interact with the environment. Shortcuts are reusable, executable sequences of atomic operations tailored for specific subroutines. The inclusion of Tips and Shortcuts facilitates continuous refinement in performance and efficiency. Alongside this framework, we introduce Mobile-Eval-E, a new benchmark featuring complex mobile tasks requiring long-horizon, multi-app interactions. Empirical results show that Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches across three foundation model backbones. Project page: https://x-plug.github.io/MobileAgent.
Authors: Guiqiu Liao, Matjaz Jogan, Marcel Hussing, Kenta Nakahashi, Kazuhiro Yasufuku, Amin Madani, Eric Eaton, Daniel A. Hashimoto
Abstract: Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical videos. While conventional object-centric methods for videos leverage recurrent processing to achieve efficiency, they often struggle with maintaining long-range temporal coherence required for long videos in surgical applications. On the other hand, fully parallel processing of entire videos enhances temporal consistency but introduces significant computational overhead, making it impractical for implementation on hardware in medical facilities. We present Slot-BERT, a bidirectional long-range model that learns object-centric representations in a latent space while ensuring robust temporal coherence. Slot-BERT scales object discovery seamlessly to long videos of unconstrained lengths. A novel slot contrastive loss further reduces redundancy and improves the representation disentanglement by enhancing slot orthogonality. We evaluate Slot-BERT on real-world surgical video datasets from abdominal, cholecystectomy, and thoracic procedures. Our method surpasses state-of-the-art object-centric approaches under unsupervised training achieving superior performance across diverse domains. We also demonstrate efficient zero-shot domain adaptation to data from diverse surgical specialties and databases.