检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Shen, Yanqing Zhou, Sanping Fu, Jingwen Wang, Ruotong Chen, Shitao Zheng, Nanning National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

Visual place recognition is a challenging task for autonomous driving and robotics, which is usually considered as an image retrieval problem. A commonly used two-stage strategy involves global retrieval followed by re-ranking using patch-level descriptors. Most deep learning-based methods in an end-to-end manner cannot extract global features with sufficient semantic information from RGB images. In contrast, re-ranking can utilize more explicit structural and semantic information in one-to-one matching process, but it is time-consuming. To bridge the gap between global retrieval and re-ranking and achieve a good trade-off between accuracy and efficiency, we propose StructVPR++, a framework that embeds structural and semantic knowledge into RGB global representations via segmentation-guided distillation. Our key innovation lies in decoupling label-specific features from global descriptors, enabling explicit semantic alignment between image pairs without requiring segmentation during deployment. Furthermore, we introduce a sample-wise weighted distillation strategy that prioritizes reliable training pairs while suppressing noisy ones. Experiments on four benchmarks demonstrate that StructVPR++ surpasses state-of-the-art global methods by 5-23% in Recall@1 and even outperforms many two-stage approaches, achieving real-time efficiency with a single RGB input. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年 PP卷 PP页

作者： Zhu, Fei Zhang, Xu-Yao Cheng, Zhen Liu, Cheng-Lin Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics 999077 Hong Kong Institute of Automation of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing 100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing 100049 China

Class-incremental learning (CIL) aims to continually recognize new classes while preserving the discriminability of previously learned ones. Most existing CIL methods are exemplar-based, relying on the storage and replay of a subset of old data during training. Without access to such data, these methods typically suffer from catastrophic forgetting. In this paper, we identify two fundamental causes of forgetting in CIL: representation bias and classifier bias. To address these challenges, we propose a simple yet effective dual-bias reduction framework, which leverages self-supervised transformation (SST) in the input space and prototype augmentation (protoAug) in the feature space. On one hand, SST mitigates representation bias by encouraging the model to learn generic, diverse representations that generalize across tasks. On the other hand, protoAug tackles classifier bias by explicitly or implicitly augmenting the prototypes of old classes in the feature space, thereby imposing stronger constraints to preserve decision boundaries. We further enhance the framework with hardness-aware prototype augmentation and multi-view ensemble strategies, yielding significant performance gains. The proposed framework can be easily integrated with pre-trained models. Without storing any samples of old classes, our method performs comparably to state-of-the-art exemplar-based approaches that rely on extensive data storage. We hope to draw the attention of researchers back to non-exemplar CIL by rethinking the necessity of storing old samples. © 1979-2012 IEEE.

关键词： Catastrophic forgetting class-incremental learning continual learning prototype augmentation self-supervision

来源：评论

学校读者我要写书评

暂无评论

Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors

arXiv

引用

arXiv 2025年

作者： Zhao, Yi Zhang, Youzhi Department of Computing The Hong Kong Polytechnic University Hong Kong Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences China

Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes the vulnerabilities of LLMs, current efforts focus primarily on single-turn attacks, overlooking the multi-turn strategies used by real-world adversaries. Existing multi-turn methods rely on static patterns or predefined logical chains, failing to account for the dynamic strategies during attacks. We propose Siren, a learning-based multi-turn attack framework designed to simulate real-world human jailbreak behaviors. Siren consists of three stages: (1) training set construction utilizing Turn-Level LLM feedback (Turn-MF), (2) post-training attackers with supervised fine-tuning (SFT) and direct preference optimization (DPO), and (3) interactions between the attacking and target LLMs. Experiments demonstrate that Siren achieves an attack success rate (ASR) of 90% with LLaMA-3-8B as the attacker against Gemini-1.5Pro as the target model, and 70% with Mistral-7B against GPT-4o, significantly outperforming single-turn baselines. Moreover, Siren with a 7B-scale model achieves performance comparable to a multi-turn baseline that leverages GPT-4o as the attacker, while requiring fewer turns and employing decomposition strategies that are better semantically aligned with attack goals. We hope Siren inspires the development of stronger defenses against advanced multi-turn jailbreak attacks under realistic scenarios. Code is available at https://***/YiyiyiZhao/siren. Warning: This paper contains potentially harmful text. © 2025, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation

arXiv

引用

arXiv 2025年

作者： Kienle, Claudius Alt, Benjamin Schneider, Finn Pertlwieser, Tobias Jäkel, Rainer Rayyes, Rania ArtiMinds Robotics Karlsruhe Germany IAS Lab Computer Science Department TU Darmstadt Germany AICOR Institute for Artificial Intelligence University of Bremen Germany Karlsruhe Germany

Despite the widespread adoption of industrial robots in automotive assembly, wire harness installation remains a largely manual process, as it requires precise and flexible manipulation. To address this challenge, we design a novel AI-based framework that automates cable connector mating by integrating force control with deep visuotactile learning. Our system optimizes search-and-insertion strategies using first-order optimization over a multimodal transformer architecture trained on visual, tactile, and proprioceptive data. Additionally, we design a novel automated data collection and optimization pipeline that minimizes the need for machine learning expertise. The framework optimizes robot programs that run natively on standard industrial controllers, permitting human experts to audit and certify them. Experimental validations on a center console assembly task demonstrate significant improvements in cycle times and robustness compared to conventional robot programming approaches. Videos are available under https: //***/*** Codes 68T40 © 2025, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

CLIPping Imbalances: A Novel Evaluation Baseline and PEARL Dataset for Pedestrian Attribute Recognition

CLIPping Imbalances: A Novel Evaluation Baseline and PEARL D...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Kamalakar Vijay Thakare Lalit Lohani Kamakshya Prasad Nayak Debi Prosad Dogra Heeseung Choi Hyungjoo Jung Ig-Jae Kim Artificial Intelligence and Robotics Institute Korea Institute of Science and Technology Seoul Republic of Korea Indian Institute of Technology Bhubaneswar Odisha India Yonsei-KIST Convergence Research Institute Yonsei University Seoul Republic of Korea

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Pedestrian Attribute Recognition (PAR) serves as a fun-damental task in computer vision and is crucial for upgradign security systems. It helps in precisely identifying and characterizing various attributes of pedestrians. However, current PAR datasets have certain issues in representing a wide range of attributes correctly, which makes the ex-isting PAR methods less effective in real-world scenarios. Addressing this limitation, this paper introduces PEARL, a comprehensive dataset comprising of diverse pedestrian images annotated with 146 attributes. These samples have been sourced from surveillance videos across twelve coun-tries. This paper also formulates an image-based PAR using language-image fusion strategy and utilizes CLIP as a new evaluation baseline. Specifically, we leverage textual infor-mation by transforming sets of attributes into meaningful sentences. Addressing the inherent data imbalance in PAR, we provide three types of prompt settings to optimize the training of the CLIP model. Our evaluation encompasses a thorough assessment of the proposed baseline model across various datasets, including PEARL dataset as well as estab-lished PAR benchmarks such as PA100K, RAP, and PETA.

关键词： Training Computer vision Pedestrians Computational modeling Surveillance Contrastive learning Benchmark testing Data models Security Videos

来源：评论

学校读者我要写书评

暂无评论

A Novel Dense Object Detector with Scale Balanced Sample Assignment and Refinement

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Dong, Jinpeng Yao, Dingyi Hu, Yufeng Zhou, Sanping Zheng, Nanning Xi’an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an710049 China Xi’an Jiaotong University Shaanxi Xi’an710049 China

Scale variation of objects remains one of the crucial challenges in object detection. Currently, conventional dense detectors with fixed receptive fields and label weights are not conducive to the detection of multi-scale objects. However, the design limitations of unbalanced label weights and fixed refinement for multi-scale objects and multi-tasks in these studies make it difficult to achieve better detection performance. In this paper, we propose a novel dense detector named Balanced FCOS which consists of two components: Balanced Label Assignment (BLA) and Flexible Shape-based Refinement (FSR). The BLA implements scale-balanced sample assignment by introducing reweighting factors consisting of localization and classification scores into the label assignment. Low-quality but high-weight samples can be weakened by the BLA. Furthermore, we design a cross-reweighting mechanism in the BLA to ensure score consistency between classification and localization. The FSR implements scale-balanced sample refinement by learning flexible sample points’ offsets for multi-scale objects and multi-tasks based on objects’ coarse features to get more discriminative features with appropriate receptive field. In addition, better features obtained by FSR are beneficial to get better classification and localization scores, which can be used by BLA to produce accurate label weights. Only equipped with the BLA, we can achieve 41.7/46.6 AP under R50/R101-FCOS without any additional parameters. When combining the BLA with the FSR, our Balanced FCOS achieves SOTA results among dense detectors on the COCO test-dev set. Experiments conducted on other heads (T-Head, DyHead), detectors (DINO), and datasets (AI-TOD) further demonstrate the effectiveness of our method. (Figure presented) © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Transforming Classification with Federated Learning on Blockchain: A Unique Model Integration Approach

Transforming Classification with Federated Learning on Block...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhihao Hao Bob Zhang Haisheng Li School of Computer Science and Artificial Intelligence Beijing Technology and Business University Beijing China Dept. of Computer and Information Science Faculty of Science and Technology University of Macau Taipa Macau Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa Macau

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The need for robust machine learning models is particularly evident in the realm of biological pattern recognition. Traditional centralized methods often struggle, as they frequently depend on large datasets that are challenging to gather due to stringent data privacy regulations. To address these limitations while maintaining classification accuracy, we propose an innovative approach that unifies models with diverse architectures within a federated learning framework built on a blockchain network. This decentralized and trustworthy system fosters effective collaboration among various models. Furthermore, we have implemented a weight distribution mechanism designed to maximize the individual strengths of each model. By leveraging blockchains inherent transparency and auditability, this approach also ensures secure and traceable data exchanges among participants. Additionally, the adaptability of the framework allows it to be extended to other domains where privacy-preserving data sharing is critical. Our experimental results showcase that the proposed methodology significantly enhances performance in classification tasks compared to existing alternatives.

关键词： Training Adaptation models Federated learning Biological system modeling Collaboration Signal processing Regulation Blockchains Security Speech processing

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Predictive Counterfactual Regret Minimization+ Algorithm in Solving Extensive-Form Games

arXiv

引用

arXiv 2025年

作者： Meng, Linjian Zhang, Youzhi Ge, Zhenxing Yang, Tianpei Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong

Counterfactual Regret Minimization (CFR) algorithms are widely used to compute a Nash equilibrium (NE) in two-player zero-sum imperfect-information extensive-form games (IIGs). Among them, Predictive CFR+ (PCFR+) is particularly powerful, achieving an exceptionally fast empirical convergence rate via the prediction in many games. However, the empirical convergence rate of PCFR+ would significantly degrade if the prediction is inaccurate, leading to unstable performance on certain IIGs. To enhance the robustness of PCFR+, we propose a novel variant, Asynchronous PCFR+ (APCFR+), which employs an adaptive asynchronization of step-sizes between the updates of implicit and explicit accumulated counterfactual regrets to mitigate the impact of the prediction inaccuracy on convergence. We present a theoretical analysis demonstrating why APCFR+ can enhance the robustness. Finally, we propose a simplified version of APCFR+ called Simple APCFR+ (SAPCFR+), which uses a fixed asynchronization of step-sizes to simplify the implementation that only needs a single-line modification of the original PCFR+. Interestingly, SAPCFR+ achieves a constant-factor lower theoretical regret bound than PCFR+ in the worst case. Experimental results demonstrate that (i) both APCFR+ and SAPCFR+ outperform PCFR+ in most of the tested games, as well as (ii) SAPCFR+ achieves a comparable empirical convergence rate with APCFR+ © 2025, CC BY.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

CSCC: Cross-Scene Crowd Counting via Learning to Diversify for Domain Generalization

引用

IEEE Transactions on Multimedia 2025年

作者： Chen, Yuehai Wang, Qingzhong Yang, Jing Chen, Badong Xiong, Haoyi Du, Shaoyi Xi'an Jiaotong University School of Automation Science and Engineering Xi'an710049 China Baidu Research Beijing100085 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Shanxi Xi'an710049 China

It is challenging for crowd counting models to generalize to new scenes due to domain shifts in training and test data. Although domain adaptation approaches have made notable progress in bridging the domain gap, they require target domain data. In this paper, we propose a novel framework for cross-scene crowd counting, which unifies domain generalization and adaptation. For domain generalization, we train a model only using single-domain data and the model can be generalized to any scene with satisfying performance. Regarding domain adaptation, we use both source and target domain data to further improve the performance. We first design a generation network that diversifies the generated samples to cover the unseen target domains as much as possible by minimizing mutual information. This approach simulates training data in various domains, thereby enhancing the model's generalization ability. Then we develop a pixel-wise supervised contrastive loss function that pulls the human heads in the source images and generated images closer to each other and pushes them further away from the background. This loss helps extract a domain-invariant feature representation, thus improving the model's generalization ability. Moreover, if information about the target domain is available, our generalization method can be easily applied as an adaptation method by replacing the mutual information minimization loss with the mutual information maximization loss. This can further improve cross-scene crowd counting performance. The experimental results demonstrate the strong generalizability of our method across different datasets. © 1999-2012 IEEE.

关键词： Cross-Sence crowd counting Domain adaptation Domain generalization

来源：评论

学校读者我要写书评

暂无评论

E2BA: Environment Exploration and Backtracking Agent for Visual Language Object Navigation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Shi, Yuhong Liu, Jianyi Sun, Lihang Zheng, Xinhu Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications China The Hong Kong University of Science and Technology Intelligent Transportation Thrust Guangzhou China

Robot navigation in an unknown environment is a challenging task, due to the lack of spatial awareness and semantic understanding of the environment. Previous works predominantly relied on prior scene knowledge and semantic information, lacking generalization and transferability. This paper proposes an environment exploration and backtracking agent (E2BA) for visual language object navigation, which leverages the rich semantic prior knowledge and commonsense reasoning of large language models (LLMs) to explore the environment and find the object. By fusing LLM scores and spatial geometric costs using particle filters, we select a redefined optimal frontier as sub-goal for environment exploration. To avoid redundant exploration and paths, we design a backtracking discriminator to evaluate the state of the agent and determine the timing of backtracking triggering through a double-level cascade mechanism. Additionally, we design a random instruction fuzzy semantic guessing task to verify the application diversity of this method. Comprehensive experiments on the Habitat-Matterport 3D dataset show that our method achieves a success rate of 0.704, which is higher than the existing baseline method. This study explores the potential application of LLMs in environment exploration without the need for additional training and semantic supplementation. © 1991-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：