检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model’s generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On -additive polycyclic codes and their Gray images

引用

Designs, Codes and Cryptography 2021年第11期90卷 2551-2562页

作者： Wu, Rongsheng Shi, Minjia Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei P.R. China

In this paper, we first generalize the polycyclic codes over finite fields to polycyclic codes over the mixed alphabet $$\mathbb {Z}_2\mathbb {Z}_4$$ , and we show that these codes can be identified as $$\mathbb {Z}_4[x]$$ -submodules of $$\mathcal {R}_{\alpha ,\beta }$$ with $$\mathcal {R}_{\alpha ,\beta }=\mathbb {Z}_2[x]/\langle t_1(x)\rangle \times \mathbb {Z}_4[x]/\langle t_2(x)\rangle $$ , where $$t_1(x)$$ and $$t_2(x)$$ are monic polynomials over $$\mathbb {Z}_2$$ and $$\mathbb {Z}_4$$ , respectively. Then we provide the generator polynomials and minimal generating sets for this family of codes based on the strong Gröbner basis. In particular, under the proper defined inner product, we study the dual of $$\mathbb {Z}_2\mathbb {Z}_4$$ -additive polycyclic codes. Finally, we focus on the characterization of the $$\mathbb {Z}_2\mathbb {Z}_4$$ -MDSS and MDSR codes, and as examples, we also present some (almost) optimal binary codes derived from the $$\mathbb {Z}_2\mathbb {Z}_4$$ -additive polycyclic codes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method to Verify Internal Parameters of Camera Calibration in World Coordinate System

A Method to Verify Internal Parameters of Camera Calibration...

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Zheng Xing Qingchun Wang Yingsong Li Junwei Qi College of Information and Communication Engineering Harbin Engineering University Harbin China Shanghai Yanding Information Technology Co. Ltd. Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Aiming at the problem that reprojection error (RE) cannot reflect the camera calibration accuracy intuitively, this paper proposes a method to verify the camera calibration results in world coordinate system. Firstly, the checkerboard calibration target is photographed with the camera under test, and the internal parameters and distortion parameters of the camera are calculated by using the pinhole model and the Kannala-Brandt (KB) fisheye model, respectively. Then, the same camera is used to shoot two targets in the field of view (FOV), and the pixel coordinates of the two target points are detected from the image. Thirdly, the inverse projection model is used to calculate the distance between the two objects and the angle between the camera and the two objects, and the real distance and angle are compared. The experimental results show that the average distance errors of the pinhole model and the KB fisheye model are 0.34% and 0.35%, respectively, and the angle errors are 0.40% and 0.12%, respectively, which proves that the verification method can effectively characterize the calibration accuracy of the camera.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ResFormer: Scaling ViTs with Multi-Resolution Training

ResFormer: Scaling ViTs with Multi-Resolution Training

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rui Tian Zuxuan Wu Qi Dai Han Hu Yu Qiao Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia Shanghai AI Laboratory

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions effectively, especially novel ones in testing, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range of resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototypical Residual Networks for Anomaly Detection and Localization

Prototypical Residual Networks for Anomaly Detection and Loc...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hui Zhang Zuxuan Wu Zheng Wang Zhineng Chen Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Zhejiang University of Technology

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, anomalies are typically subtle, hard to discern, and of various appearance, making it difficult to detect anomalies and let alone locate anomalous regions. To address these issues, we propose a framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. PRN mainly consists of two parts: multi-scale prototypes that explicitly represent the residual features of anomalies to normal patterns; a multisize self-attention mechanism that enables variable-sized anomalous feature learning. Besides, we present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies. Extensive experiments on the challenging and widely used MVTec AD benchmark show that PRN outperforms current state-of-the-art unsupervised and supervised methods. We further report SOTA results on three additional datasets to demonstrate the effectiveness and generalizability of PRN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CoSign: Exploring Co-occurrence signals in Skeleton-based Continuous Sign Language Recognition

CoSign: Exploring Co-occurrence Signals in Skeleton-based Co...

引用

International Conference on Computer Vision (ICCV)

作者： Peiqi Jiao Yuecong Min Yanan Li Xiaotao Wang Lei Lei Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Xiaomi Inc. China

The co-occurrence signals (e.g., hand shape, facial expression, and lip pattern) play a critical role in Continuous Sign Language Recognition (CSLR). Compared to RGB data, skeleton data provide a more efficient and concise option, and lay a good foundation for the co-occurrence exploration in CSLR. However, skeleton data are often used as a tool to assist visual grounding and have not attracted sufficient attention. In this paper, we propose a simple yet effective GCN-based approach, named CoSign, to incorporate Co-occurrence signals and explore the potential of skeleton data in CSLR. Specifically, we propose a group-specific GCN to better exploit the knowledge of each signal and a complementary regularization to prevent complex co-adaptation across signals. Furthermore, we propose a two-stream framework that gradually fuses both static and dynamic information in skeleton data. Experimental results on three public CSLR datasets (PHOENIX14, PHOENIX14-T and CSL-Daily) show that the proposed CoSign achieves competitive performance with recent video-based approaches while reducing the computation cost during training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implicit Temporal Modeling with Learnable Alignment for Video Recognition

Implicit Temporal Modeling with Learnable Alignment for Vide...

引用

International Conference on Computer Vision (ICCV)

作者： Shuyuan Tu Qi Dai Zuxuan Wu Zhi-Qi Cheng Han Hu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia Carnegie Mellon University

Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint spatial-temporal modeling trades off between the efficiency and performance. While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention. To this end, in this paper, we proposed a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. Specifically, for a frame pair, an interactive point is predicted in each frame, serving as a mutual information rich region. By enhancing the features around the interactive point, two frames are implicitly aligned. The aligned features are then pooled into a single token, which is leveraged in the subsequent spatial self-attention. Our method allows eliminating the costly or insufficient temporal self-attention in video. Extensive experiments on benchmarks demonstrate the superiority and generality of our module. Particularly, the proposed ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H. Code is released at https://***/Francis-Rings/ILA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens

arXiv

引用

arXiv 2024年

作者： Sun, Dengdi Pan, Yajie Lu, Andong Li, Chenglong Luo, Bin The Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230026 China The Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Many RGBT tracking researches primarily focus on modal fusion design, while overlooking the effective handling of target appearance changes. While some approaches have introduced historical frames or fuse and replace initial templates to incorporate temporal information, they have the risk of disrupting the original target appearance and accumulating errors over time. To alleviate these limitations, we propose a novel Transformer RGBT tracking approach, which mixes spatio-temporal multimodal tokens from the static multimodal templates and multimodal search regions in Transformer to handle target appearance changes, for robust RGBT tracking. We introduce independent dynamic template tokens to interact with the search region, embedding temporal information to address appearance changes, while also retaining the involvement of the initial static template tokens in the joint feature extraction process to ensure the preservation of the original reliable target appearance information that prevent deviations from the target appearance caused by traditional temporal updates. We also use attention mechanisms to enhance the target features of multimodal template tokens by incorporating supplementary modal cues, and make the multimodal search region tokens interact with multimodal dynamic template tokens via attention mechanisms, which facilitates the conveyance of multimodal-enhanced target change information. Our module is inserted into the transformer backbone network and inherits joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three RGBT benchmark datasets show that the proposed approach maintains competitive performance compared to other state-of-the-art tracking algorithms while running at 39.1 FPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Article reranking by memory-enhanced key sentence matching for detecting previously fact-checked claims 59

Article reranking by memory-enhanced key sentence matching f...

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language processing, ACL-IJCNLP 2021

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Xirong Zhong, Lei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

ISBN: (纸本)9781954085527

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrieve fact-checking articles (FC-articles) for detection and focus on reranking candidate articles in the typical two-stage retrieval framework. However, their performance may be limited as they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics;and (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. In this paper, we propose a novel reranker, MTM (Memoryenhanced Transformers for Matching), to rank FC-articles using key sentences selected using event (lexical and semantic) and pattern information. For event information, we propose to finetune the Transformer with regression of ROUGE. For pattern information, we generate pattern vectors as a memory bank to match with the parts containing patterns. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://***/ICTMCG/MTM. © 2021 Association for Computational Linguistics

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Rapidly Solving Wideband RCS by Combining UCBFM and Compressive Sensing

引用

Progress In Electromagnetics Research C 2022年 124卷 33-42页

作者： Wang, Zhonggen Li, Chenwei Sun, Yufa Nie, Wenyan Wang, Pan Lin, Han School of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China Key Lab of Intelligent Computing & Signal Processing Anhui University Hefei230039 China School of Mechanical and Electrical Engineering Huainan Normal University Huainan232001 China

While analyzing wideband electromagnetic scattering problems using ultra-wideband characteristic basis function method (UCBFM), the reconstruction of a reduced matrix and the recalculation of an impedance matrix at each frequency point cost a large amount of time. To overcome this issue, a novel method that combines UCBFM with compressive sensing (CS) is proposed in this paper to rapidly analyse the wideband RCS. The proposed method makes the ultra-wideband characteristic basis functions (UCBFs) generated at the highest frequency as the sparse basis, introduces the CS theory, randomly extracts several rows from the original matrix as the measurement matrix, utilizes the corresponding excitation vector as the measurement value, and then employs the recovery algorithm, through which the solution of target induced current can be obtained. Due to partial filling of impedance matrix and efficient recovery algorithm, the wideband RCS computation time of the object is significantly reduced using the proposed method. Furthermore, the numerical simulation results show that the computation efficiency for the target wideband RCS can be further enhanced compared with that of the stand-alone UCBFM. © 2022, Electromagnetics Academy. All rights reserved.

关键词： Computational efficiency

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：