检索结果-内蒙古大学图书馆

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Qinliang Luo, Cheng Niu, Zenghao He, Xilin Xie, Weicheng Hou, Yuanbo Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China WAVES Research Group Ghent University Belgium University of Leicester United Kingdom

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://***/LinQinLiang/DeCoWA. © 2024, CC BY-NC-SA.

关键词： Semantics

OPTIHROV: Optically Linked Hybrid Autonomous/Remotely Operated Vehicle, Beyond Teleoperation in a New Generation of Underwater Intervention Vehicles

学校读者我要写书评

暂无评论

OPTIHROV: Optically Linked Hybrid Autonomous/Remotely Operat...

OCEANS

作者： Roger Pi Joan Esteba Patryk Cieslak Narcís Palomeras Pedro J. Sanz Raúl Marín Pere Ridao Computer Vision and Robotics Research Institute (VICOROB) Universitat de Girona Girona Interactive and Robotic Systems Lab (IRS-Lab) Universitat Jaume I Castelló de la Plana

OPTIHROV is a proof-of-concept project to demonstrate a telerobotic system, based on an untethered, OPTIcally-connected, Hybrid Autonomous-ROV, that aims to replace light intervention ROVs operating at close range to networked infrastructures. The system is designed to bridge the gap between current ROVs, tethered to a Docking Station, and the dream of the future Intervention Autonomous Underwater Vehicle (I-AUV). OPTIHROV is a telerobotic system to perform inspection and light intervention tasks in potentially unknown and unstructured environments. It uses human-robot interaction (HRI) methods that allow the user to remotely guide the robot by launching a set of sensory-motion primitives performed by the robot *** paper presents a proof of concept demonstration of the OPTIHROV concept, where the wireless Hybrid Remotely Operated Vehicle (HROV), located in the test tank of the Universitat de Girona (UdG), is controlled/supervised from the Universitat Jaume I (UJI) in Castelló de la Plana, about 330 km away.

关键词：

Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Qucheng Zheng, Ce Ding, Zhengming Wang, Pu Chen, Chen Center for Research in Computer Vision University of Central Florida Orlando United States Robotics Institute Carnegie Mellon University Pittsburgh United States Department of Computer Science Tulane University New Orleans United States University of North Carolina at Charlotte Charlotte United States

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the time- and labor-intensive annotation. To cope with the label deficiency issue, one common solution is to train the HPE models with easily available synthetic datasets (source) and apply them to real-world data (target) through domain adaptation (DA). Unfortunately, prevailing domain adaptation techniques within the HPE domain remain predominantly fixated on effecting alignment and aggregation between source and target features, often sidestepping the crucial task of excluding domain-specific representations. To rectify this, we introduce a novel framework that capitalizes on both representation aggregation and segregation for domain adaptive human pose estimation. Within this framework, we address the network architecture aspect by disentangling representations into distinct domain-invariant and domain-specific components, facilitating aggregation of domain-invariant features while simultaneously segregating domain-specific ones. Moreover, we tackle the discrepancy measurement facet by delving into various keypoint relationships and applying separate aggregation or segregation mechanisms to enhance alignment. Extensive experiments on various benchmarks, e.g., Human3.6M, LSP, H3D, and FreiHand, show that our method consistently achieves state-of-the-art performance. The project is available at https: //***/davidpengucf/EPIC. © 2024, CC BY.

关键词： Virtual reality

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Szatkowski, Filip Zheng, Yaoyue Yang, Fei Trzciński, Tomasz Twardowski, Bartlomiej van de Weijer, Joost Warsaw University of Technology Poland IDEAS NCBR Poland Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China Computer Vision Center Barcelona Spain VCIP College of Computer Science Nankai University China NKIARI Futian Shenzhen China IDEAS Research Institute Tooploox Poland Universitat Autonoma de Barcelona Spain

Continual learning is crucial for applying machine learning in challenging, dynamic, and often resource-constrained environments. However, catastrophic forgetting — overwriting previously learned knowledge when new information is acquired — remains a major challenge. In this work, we examine the intermediate representations in neural network layers during continual learning and find that such representations are less prone to forgetting, highlighting their potential to accelerate computation. Motivated by these findings, we propose to use auxiliary classifiers (ACs) to enhance performance and demonstrate that integrating ACs into various continual learning methods consistently improves accuracy across diverse evaluation settings, yielding an average 10% relative gain. We also leverage the ACs to reduce the average cost of the inference by 10-60% without compromising accuracy, enabling the model to return the predictions before computing all the layers. Our approach provides a scalable and efficient solution for continual learning. © 2024, CC BY.

关键词： Classifiers

HPPS: A Hierarchical Progressive Perception System for Luggage Trolley Detection and Localization at Airports

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Zhirui Zhang, Zhe Zhao, Jieting Ye, Hanjing Wang, Jiankun Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Shenzhen Key Laboratory of Robotics and Computer Vision Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

The robotic autonomous luggage trolley collection system employs robots to gather and transport scattered luggage trolleys at airports. However, existing methods for detecting and locating these luggage trolleys often fail when they are not fully visible. To address this, we introduce the Hierarchical Progressive Perception System (HPPS), which enhances the detection and localization of luggage trolleys under partial occlusion. The HPPS processes the luggage trolley’s position (x, y) and orientation (θ) separately, which requires only RGB images for labeling and training, eliminating the need for 3D coordinates and alignment. The HPPS can accurately determine the position of the luggage trolley with just one well-detected keypoint and estimate the luggage trolley’s orientation when it is partially occluded. Once the luggage trolley’s initial pose is detected, HPPS updates this information continuously to refine its accuracy until the robot begins grasping. The experiments on detection and localization demonstrate that HPPS is more reliable under partial occlusion compared to existing methods. Its effectiveness and robustness have also been confirmed through practical tests in actual luggage trolley collection tasks. A website about this work is available at HPPS. Copyright © 2024, The Authors. All rights reserved.

关键词： robotics

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Qitao Zheng, Ce Liu, Mengyuan Chen, Chen Robotics Institute Carnegie Mellon University United States Center for Research in Computer Vision University of Central Florida United States Key Laboratory of Machine Perception Peking University Shenzhen Graduate School China

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [77], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dhiaf, Marwa Souibgui, Mohamed Ali Wang, Kai Liu, Yuyang Kessentini, Yousri Fornés, Alicia Rouhou, Ahmed Cheikh InstaDeep United Kingdom Computer Vision Center UAB Spain Digital Research Center of Sfax SM@RTS Tunisia State Key Laboratory of Robotics China Shenyang Institute of Automation Chinese Academy of Sciences China

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, i.e. when data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance in English, Italian, and Russian, whilst adding only a few parameters per task. The code and trained models will be publicly available1 © 2023, CC BY.

关键词： Supervised learning

Hyperspectral Imaging for Identifying Foreign Objects on Pork Belly

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ghimpeteanu, Gabriela Rajani, Hayat Quintana, Josep Garcia, Rafael Coronis Computing SL University of Girona Science and Technology Park Carrer Pic de Peguera 11 Edifici Giroemprèn Girona17003 Spain Computer Vision and Robotics Research Institute University of Girona Campus Montilivi Edifici P4 Girona17003 Spain

Ensuring food safety and quality is critical in the food processing industry, where the detection of contaminants remains a persistent challenge. This study presents an automated solution for detecting foreign objects on pork belly meat using hyperspectral imaging (HSI). A hyperspectral camera was used to capture data across various bands in the near-infrared (NIR) spectrum (900-1700 nm), enabling accurate identification of contaminants that are often undetectable through traditional visual inspection methods. The proposed solution combines pre-processing techniques with a segmentation approach based on a lightweight vision Transformer (ViT) to distinguish contaminants from meat, fat, and conveyor belt materials. The adopted strategy demonstrates high detection accuracy and training efficiency, while also addressing key industrial challenges such as inherent noise, temperature variations, and spectral similarity between contaminants and pork belly. Experimental results validate the effectiveness of hyperspectral imaging in enhancing food safety, highlighting its potential for broad real-time applications in automated quality control processes. © 2025, CC BY-NC-SA.

关键词： Belt conveyors

FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Elbatel, Marawan Martí, Robert Li, Xiaomeng The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The Computer Vision and Robotics Institute University of Girona Spain The Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China

Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often overlook the frequency-dependent behavior of these models, thereby limiting their effectiveness in transferring representations and generalizations to rare diseases. In this paper, we propose FoPro-KD, a novel framework that leverages the power of frequency patterns learned from frozen pretrained models to enhance their transferability and compression, presenting a few unique insights: 1) We demonstrate that leveraging representations from publicly available pre-trained models can substantially improve performance, specifically for rare classes, even when utilizing representations from a smaller pre-trained model. 2) We observe that pre-trained models exhibit frequency preferences, which we explore using our proposed Fourier Prompt Generator (FPG), allowing us to manipulate specific frequencies in the input image, enhancing the discriminative representational transfer. 3) By amplifying or diminishing these frequencies in the input image, we enable Effective Knowledge Distillation (EKD). EKD facilitates the transfer of knowledge from pre-trained models to smaller models. Through extensive experiments in long-tailed gastrointestinal image recognition and skin lesion classification, where rare diseases are prevalent, our FoPro-KD framework outperforms existing methods, enabling more accessible medical models for rare disease classification. Code is available at https://***/xmed-lab/FoPro-KD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation