检索结果-内蒙古大学图书馆

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

DeTrack: in-model latent denoising learning for visual object tracking 24

DeTrack: in-model latent denoising learning for visual objec...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Xinyu Zhou Jinglun Li Lingyi Hong Kaixun Jiang Pinxue Guo Weifeng Ge Wenqiang Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China and Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

ISBN: (纸本)9798331314385

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Split-Fusion Transformer

Adaptive Split-Fusion Transformer

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zixuan Su Jingjing Chen Lei Pang Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing City University of Hong Kong Singapore Management University

Neural networks for visual content understanding have recently evolved from convolutional ones to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range global connections between localities for holistic learning. Inspired by this complementary nature, there is a growing interest in designing hybrid models which utilize both techniques. Current hybrids merely replace convolutions as simple approximations of linear projection or juxtapose a convolution branch with attention without considering the importance of local/global modeling. To tackle this, we propose a new hybrid named Adaptive Split-Fusion Transformer (ASF-former) that treats convolutional and attention branches differently with adaptive weights. Specifically, an ASF-former encoder equally splits feature channels into half to fit dual-path inputs. Then, the outputs of the dual-path are fused with weights calculated from visual cues. We also design a compact convolutional path from a concern of efficiency. Extensive experiments on standard benchmarks show that our ASF-former outperforms its CNN, transformer, and hybrid counterparts in terms of accuracy (83.9% on ImageNet-1K), under similar conditions (12.9G MACs / 56.7M Params, without large-scale pre-training). The code is available at: https://***/szx503045266/ASF-former.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network 39

FaceA-Net: Facial Attribute-Driven ID Preserving Image Gener...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Jiayu Yu, Yue Chen, Jingjing Dai, Qi Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft Research Asia China

ISBN: (纸本)157735897X

Recent advances in diffusion-based generative models have demonstrated superior performance in subject-driven image generation. Identity (ID) preserving image generation, as a subtask of subject-driven image generation, aims to generate customized images for specific human identity and has broad application potential. However, this task remains challenging due to the requirement for high ID fidelity and precise detail preservation. Additionally, generating high-quality context presents another challenge, as existing methods struggle to achieve both high ID fidelity and satisfactory context simultaneously. To address the issues of insufficient ID fidelity, we introduce a simple yet effective test-time fine-tuning approach. Specifically, we propose an attribute-driven training method that establishes global-level and local-level tasks to learn the global face feature and fine-grained attribute features, respectively. Furthermore, we introduce a novel ID-context decoupling framework that decouples image context generation from human ID generation, ensuring the quality of contextual content as well as facilitating the learning of ID information. Through extensive experiments, we demonstrate the effectiveness of the proposed method and showcase its capabilities across various applications. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

arXiv

引用

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

BotScan: An Unsupervised Bot Detection Based on Adversarial Learning and Social Perception

BotScan: An Unsupervised Bot Detection Based on Adversarial ...

引用

Asian Control Conference

作者： Hong Lin Nuo Chen Yang Chen Xiang Li Cong Li Department of Electronic Engineering Adaptive Networks and Control Lab School of Information Science and Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Within online social networks, the rapid expansion of automated accounts, known as social bots, poses a significant challenge. This dynamic has sparked a strategic contest between bots and detectors. Both sides continually learn and adjust their strategies to gain an edge in this silent war. To effectively manage risks from bot evolution, proactive detection methods have garnered widespread attention. In this work, we propose a graph-based and structure-aware adversarial learning framework for multi-category social bot detection. In detail, we adopt a categorical generative adversarial network to create synthetic evolved bot samples for adversarial learning, aiming to boost the detection performance. Besides, we design a user representation learning module, including local and remote feature extractors to mine neighborhood information and achieve multiple network structure representations. Results demonstrate that our model outperforms state-of-the-art approaches and exhibits strong robustness.

关键词： Representation learning Training Technological innovation Social networking (online) Image edge detection Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Lightweight CNN for HRRP Recognition Based on Attention Mechanism Structured Pruning

Lightweight CNN for HRRP Recognition Based on Attention Mech...

引用

2023 IEEE International Radar Conference, RADAR 2023

作者： Wang, Yanhua Zhang, Zhilong Yuan, Mingchen Liao, Jiandong Zhang, Liang Beijing Institute of Technology Electromagnetic Sensing Research Center of Cemee State Key Lab Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Beijing Institute of Technology Advanced Technology Research Institute Shandong250300 China

ISBN: (纸本)9781665482783

Deep convolutional neural network (CNN) has been widely investigated for radar target high resolution range profile (HRRP) recognition. However, the deep structures of CNN require high storage and computational capabilities, thus restricting its applications with limited resources. In this paper, we design a lightweight CNN model with structure pruning based on the channel-wise attention mechanism. Specifically, the attention value is used to represent the importance of the filters in CNN. Furthermore, Greedy strategy and fine-tuning are adopted in the pruning process to minimize the loss of model performance. The results of public dataset show that the recognition accuracy of the proposed method decreases by less than 0.13% when the pruning ratio is 80%. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A method for enhancing infrared small target images under complex sky backgrounds

A method for enhancing infrared small target images under co...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yuhan Xu Linbo Tang Haotian Sun Beijing Key Laboratory of Embedded Real-Time Information Processing Radar Research LabSchool of Information and Electronics Beijing Institute of Technology Beijing China Advanced Technology Research Institute Beijing Institute of Technology Jinan China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Infrared target detection is currently widely used in both military and civilian fields. Due to the lower resolution of infrared images compared to visible light images and the lack of texture information in small targets, the quality of infrared small target images is often poor and not suitable for direct detection. Therefore, enhancing low-quality infrared small target images is a necessary step before object detection can be performed. This article presents a method for enhancing infrared images of small targets. The process begins with applying guided filtering to the original image. The resulting detail layer is then used as a guided image for a second guided filtering of the base layer, producing a second detail layer. Additionally, a novel approach to local contrast enhancement is introduced, which applies contrast enhancement specifically to this secondary detail layer. Experimental results has been demonstrated that the enhancement method proposed in this paper significantly improves the visibility of the target area while reducing background interference, without losing information about small targets. Additionally, this method outperforms other common techniques in terms of enhancement effect, as shown in comparative experiments.

关键词： Image quality Image resolution Object detection Interference information filters Data processing Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Semantic Link Network Model for Supporting Traceability of Logistics on Blockchain

arXiv

引用

arXiv 2025年

作者： Sun, Xiaoping Zhuge, Sirui Zhuge, Hai Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China King’s College London United Kingdom Publicis Sapient London United Kingdom Great Bay University Dongguan China Great Bay Institute for Advanced Study Dongguan China

The ability of tracing states of logistic transportations requires an efficient storage and retrieval of the state of logistic transportations and locations of logistic objects. However, the restriction of sharing states and locations of logistic objects across organizations from different countries makes it hard to deploy a centralized database for implementing the traceability in a cross-border logistic system. This paper proposes a semantic data model on Blockchain to represent a logistic process based on the Semantic Link Network model where each semantic link represents a logistic transportation of a logistic object between two parties. A state representation model is designed to represent the states of a logistic transportation with semantic links. It enables the locations of logistic objects to be derived from the link states. A mapping from the semantic links to the blockchain transactions is designed to enable schema of semantic links and states of semantic links to be published in blockchain transactions. To improve the efficiency of tracing a path of semantic links on blockchain platform, an algorithm is designed to build shortcuts along the path of semantic links to enable a query on the path of a logistic object to reach the target in logarithmic steps on the blockchain platform. A reward-penalty policy is designed to allow participants to confirm the state of links on blockchain. Analysis and simulation demonstrate the flexibility, effectiveness and the efficiency of Semantic Link Network on immutable blockchain for implementing logistic traceability. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Interactive Navigation Method with Effect-oriented Affordance

An Interactive Navigation Method with Effect-oriented Afford...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaohan Wang Yuehu Liu Xinhang Song Yuyi Liu Sixian Zhang Shuqiang Jiang Institute of Artificial Intelligence and Robotics Xi’ an Jiaotong University Xi'an Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Visual navigation is to let the agent reach the target according to the continuous visual input. In most previous works, visual navigation is usually assumed to be done in a static and ideal environment: the target is always reachable with no need to alter the environment. However, the “messy” environments are more general and practical in our daily lives, where the agent may get blocked by obstacles. Thus Interactive Navigation (InterNav) is introduced to navigate to the objects in more realistic “messy” environments according to the object interaction. Prior work on InterNav learns shortterm interaction through extensive trials with reinforcement learning. However, interaction does not guarantee efficient navigation, that is, plan-ning obstacle interactions that make shorter paths and con-sume less effort is also crucial. In this paper, we introduce an effect-oriented affordance map to enable longterm interactive navigation, extending the existing map-based nav-igation framework to the domain of dynamic environment. We train a set of affordance functions predicting available interactions and the time cost of removing obstacles, which informatively support an interactive modular system to ad-dress interaction and longterm planning. Experiments on the ProcTHOR simulator demonstrate the capability of our affordance-driven system in longterm navigation in complex dynamic environments.

关键词： Visualization Computer vision Uncertainty Costs Navigation Affordances Reinforcement learning

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：