检索结果-内蒙古大学图书馆

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Wu, Pingyu Zhai, Wei Cao, Yang Univ Sci & Technol China Hefei Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Weakly supervised object localization (WSOL) aims to localize objects using only image-level labels. Recently a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve localization task. Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator. We argue for using activation value to achieve more efficient learning. It is based on the experimental observation that, for a trained network, CE converges to zero when the foreground mask covers only part of the object region. While activation value increases until the mask expands to the object boundary, which indicates that more object areas can be learned by using activation value. In this paper;we propose a Background Activation Suppression (BAS) method. Specifically, an Activation Map Constraint module (AMC) is designed to facilitate the learning of generator by suppressing the background activation value. Meanwhile, by using the foreground region guidance and the area constraint, BAS can learn the whole region of the object. In the inference phase, we consider the prediction maps of different categories together to obtain the final localization results. Extensive experiments show that BAS achieves significant and consistent improvement over the baseline methods on the CUB-200-2011 and ILSVRC datasets.

关键词： Location awareness computer vision Correlation Codes Generators pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Lepard: Learning partial point cloud matching in rigid and deformable scenes

Lepard: Learning partial point cloud matching in rigid and d...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Li, Yang Harada, Tatsuya Univ Tokyo Tokyo Japan RIKEN Wako Saitama Japan

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the crosspoint-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. In rigid cases, Lepard combined with RANSAC and ICP demonstrates state-of-the-art registration recall of 93.9% / 71.3% on the 3DMatch / 3DLoMatch. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark. Code and data are available at https://***/rabbityl/lepard.

关键词： Point cloud compression computer vision Three-dimensional displays Codes Art Motion segmentation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Few-shot Learning via Multi-Factor Clustering

Semi-Supervised Few-shot Learning via Multi-Factor Clusterin...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Ling, Jie Liao, Lei Yang, Meng Shuai, Jia Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp SYSU Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

The scarcity of labeled data and the problem of model overfitting have been the challenges in few-shot learning. Recently, semi-supervised few-shot learning has been developed to obtain pseudo-labels of unlabeled samples for expanding the support set. However, the relationship between unlabeled and labeled data is not well exploited in generating pseudo labels, the noise of which will directly harm the model learning. In this paper, we propose a Clustering-based semi-supervised Few-Shot Learning (cluster-FSL) method to solve the above problems in image classification. By using multi-factor collaborative representation, a novel Multi-Factor Clustering (MFC) is designed to fuse the information of few-shot data distribution, which can generate soft and hard pseudo-labels for unlabeled samples based on labeled data. And we exploit the pseudo labels of unlabeled samples by MFC to expand the support set for obtaining more distribution information. Furthermore, robust data augmentation is used for support set in the fine-tuning phase to increase the labeled samples' diversity. We verified the validity of the cluster-FSL by comparing it with other few-shot learning methods on three popular benchmark datasets, miniImageNet, tieredImageNet, and CUB-200-2011. The ablation experiments further demonstrate that our MFC can effectively fuse distribution information of labeled samples and provide high-quality pseudo-labels. Our code is available at: https://***/smartllvlab/cluster-fsl

关键词： Manifolds Learning systems computer vision Codes Fuses Collaboration Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Variable Few Shot Class Incremental and OpenWorld Learning

Variable Few Shot Class Incremental and OpenWorld Learning

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Ahmad, Touqeer Dhamija, Akshay Raj Jafarzadeh, Mohsen Cruz, Steve Rabinowitz, Ryan Li, Chunchun Boult, Terrance E. Univ Colorado Vis & Secur Technol Lab Colorado Springs CO 80907 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Prior work on few-shot class incremental learning has operated with an unnatural assumption: the number of ways and number of shots are assumed to be known and fixed e.g., 10-ways 5-shots, 5-ways 5-shots, etc. Hence, we refer to this setting as Fixed-Few-Shot Class Incremental Learning (FFSCIL). In practice, the pre-specified fixed number of classes and examples per class may not be available, meaning one cannot update the model. Evaluation of FSCIL approaches in such unnatural settings renders their applicability questionable for practical scenarios where such assumptions do not hold. To mitigate the limitation of FFSCIL, we propose Variable-Few-Shot Class Incremental Learning (VFSCIL) and demonstrate it with Up-to N-Ways, Up-to K-Shots class incremental learning;wherein each incremental session, a learner may have up to N classes and up to K samples per class. Consequently, conventional FFSCIL is a special case of herein introduced VFSCIL. Further, we extend VFSCIL to a more practical problem of Variable-Few-Shot OpenWorld Learning (VFSOWL), where an agent is not only required to perform incremental learning, but must detect unknown samples and enroll only those that it detects correctly. We formulate and study VFSCIL and VFSOWL on two benchmark datasets conventionally employed for FFSCIL i.e., Caltech-UCSD Birds-200-2011 (CUB200) and miniImageNet. First, to serve as a strong baseline, we extend the state-of-the-art FSCIL approach to operate in Up-to N-Ways, Up-to K-Shots class incremental and open-world settings. Then, we propose a novel but simple approach for VFSCIL/VFSOWL where we leverage the current advancements in self-supervised feature learning. Utilizing both benchmark datasets, our proposed approach outperforms the strong baseline on the conventional FFSCIL setting and newly introduced VFSCIL/VFSOWL settings.

关键词： Representation learning computer vision Codes Conferences Benchmark testing Feature extraction Power capacitors

来源：评论

学校读者我要写书评

暂无评论

C²AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

C<SUP>2</SUP>AM: Contrastive learning of Class-agnostic Acti...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Xie, Jinheng Xiang, Jianfeng Chen, Junliang Hou, Xianxu Zhao, Xiaodong Shen, Linlin Shenzhen Univ Sch Comp Sci & Software Engn Shenzhen Peoples R China Wenzhou Kean Univ Dept Comp Sci Wenzhou Peoples R China Shenzhen Inst Artificial Intelligence Robot Soc Shenzhen Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C(2)AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds;ii) foreground objects with similar appearance or background with similar color/texture have similar representations in the feature space. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background with a class-agnostic activation map using a novel contrastive loss. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions. We successfully extracted from C(2)AM class-agnostic object bounding boxes for object localization and background cues to refine CAM generated by classification network for semantic segmentation. Extensive experiments on CUB-200-2011, ImageNet-1K, and PASCAL VOC2012 datasets show that both WSOL and WSSS can benefit from the proposed C(2)AM. Code will be available at https://***/CVISZU/CCAM.

关键词： Location awareness Image segmentation computer vision Codes Shape Semantics Force

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification by Siamese Network

引用

INTELIGENCIA ARTIFICIAL-IBEROAMERICAL JOURNAL OF ARTIFICIAL INTELLIGENCE 2023年第71期26卷 25-33页

作者： Shebiah, R. Newlin Arivazhagan, S. Amrith, S. G. Adarsh, S. Mepco Schlenk Engn Coll Dept Elect & Commun Engn Ctr Image Proc & Pattern Recognit Sivakasi Tamilnadu India

The re-identification of individuals aims to retrieve persons across multiple non-overlapping cameras. With the advancement of deep learning features and the increase in the number of surveillance videos, the computer vision community has experienced significant progress. However, person re-identification is still faced with various challenges such as low resolution images and pose variations. To overcome these challenges, state-of-the-art algorithms for person re-identification are supported by convolutional neural networks. This paper proposes the use of a Siamese network, which is a neural architecture that takes a pair of images or videos as input and predicts the similarity or dissimilarity of a person across two cameras. The output includes the prediction of similar and dissimilar persons along with their prediction scores. The proposed method was evaluated using iLIDS-VID and PRID 2011 datasets, and achieved recognition accuracy of 79.52% and 85.82%, respectively. These results demonstrate the effectiveness of the Siamese network for person re-identification tasks. Overall, this study contributes to the ongoing research on improving the accuracy of person re-identification across multiple cameras in surveillance videos.

关键词： Siamese Network Person re-identification Surveillance videos Deep learning

来源：评论

学校读者我要写书评

暂无评论

Recombining vision Transformer Architecture for Fine-Grained Visual Categorization 29th

Recombining Vision Transformer Architecture for Fine-Grained...

引用

29th International Conference on MultiMedia Modeling (MMM)

作者： Deng, Xuran Liu, Chuanbin Lu, Zhiying Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China

ISBN: (纸本)9783031278174;9783031278181

Fine-grained visual categorization (FGVC) is a challenging task in the image analysis field which requires comprehensive discriminative feature extraction and representation. To get around this problem, previous works focus on designing complex modules, the so-called necks and heads, over simple backbones, while bringing a huge computational burden. In this paper, we bring a new insight: vision Transformer itself is an all-in-one FGVC framework that consists of basic Backbone for feature extraction, Neck for further feature enhancement and Head for selecting discriminative feature. We delve into the feature extraction and representation pattern of ViT for FGVC and empirically show that simply recombining the original ViT structure to leverage multi-level semantic representation without introducing any other parameters is able to achieve higher performance. Under such insight, we proposed RecViT, a simple recombination and modification of original ViT, which can capture multi-level semantic features and facilitate fine-grained recognition. In RecViT, the deep layers of the original ViT are served as Head, a few middle layers as Neck and shallow layers as Backbone. In addition, we adopt an optional Feature Processing Module to enhance discriminative feature representation at each semantic level and align them for final recognition. With the above simple modifications, RecViT obtains significant improvement in accuracy in FGVC benchmarks: CUB-200-2011, Stanford Cars and Stanford Dogs.

关键词： Fine-Grained Visual Categorization vision Transformer

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Filter Framework for Texture Image Representation Improvement Using Set of pattern Descriptors to Fingerprint Liveness Detection

引用

IEEE ACCESS 2022年 10卷 117681-117706页

作者： Contreras, Rodrigo Colnago Nonato, Luis Gustavo Boaventura, Maurilio Boaventura, Ines Aparecida Gasparotto Dos Santos, Francisco Lledo Zanin, Rodrigo Bruno Viana, Monique Simplicio Univ Sao Paulo Inst Math & Comp Sci BR-13566590 Sao Carlos SP Brazil Sao Paulo State Univ Inst Biosci Letters & Exact Sci BR-15054000 Sao Jose Do Rio Preto SP Brazil Mato Grosso State Univ Fac Architecture & Engn BR-78217900 Caceres MG Brazil Univ Fed Sao Carlos Comp Dept BR-13565905 Sao Carlos SP Brazil

The use of user recognition and authentication systems has become very common and is part of everyday routines for many people, guaranteeing access to the automatic teller machines, entrance to the gym or even to smartphones. Among all the biometrics that can be analyzed in this type of system, the fingerprint is the most considered due to the ease of collection, the uniqueness of each user, and the large amount of solid theories and computational libraries available in the scientific literature. However, in recent years, the falsification of these biometrics with synthetic materials, known as spoofing, has become a real threat to these systems. To circumvent these effects without the addition of hardware devices, techniques based on the analysis of texture pattern descriptors were developed. In this work, we propose a new framework based on steps of data augmentation, image processing and replication, and feature fusion and reduction. The method has as main objective to improve the ability of classifiers, or sets of classifiers, to recognize life in fingerprints. Furthermore, it is proposed a generalization of vector representation of patterns described in matrix form from the systematic use of sets of mapping functions. All the proposed material was analyzed on the well-established benchmark of the Liveness Detection competition of the 2009, 2011, 2013 and 2015 editions, presenting an average accuracy of 97.77% and being a competitive strategy in relation to the other techniques that make up the state of the art of specialized literature.

关键词： Fingerprint liveness detection spoofing detection pattern recognition texture analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective

CAM Back Again: Large Kernel CNNs from a Weakly Supervised O...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Shunsuke Yasuki Masato Taki Graduate School of Artificial Intelligence and Science Rikkyo University Japan

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recently, convolutional neural networks (CNNs) with large size kernels have attracted much attention in the computer vision field, following the success of the vision Transformers. Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance. The reason for the high performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested. We therefore revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization (WSOL) task. WSOL, a difficult downstream task that is not fully supervised, provides a new angle to explore the capabilities of the large kernel CNNs. Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance. Our analysis of the factors contributing to high performance provides a different perspective, in which the main factor is feature map improvement. Furthermore, we find that modern CNNs are robust to the CAM problems of local regions of objects being activated, which has long been discussed in WSOL. CAM is the most classic WSOL method, but because of the above-mentioned problems, it is often used as a baseline method for comparison. However, experiments on the CUB-200-2011 dataset show that simply combining a large kernel CNN, CAM, and simple data augmentation methods can achieve performance (90.99% MaxBoxAcc) comparable to the latest WSOL method, which is CNN-based and requires special training or complex post-processing.

关键词： Training Location awareness computer vision Systematics computer architecture Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Discrimination-Aware Mechanism for Fine-grained Representation Learning

Discrimination-Aware Mechanism for Fine-grained Representati...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Xu, Furong Wang, Meng Zhang, Wei Cheng, Yuan Chu, Wei Ant Financial Serv Grp Hangzhou Peoples R China

ISBN: (纸本)9781665445092

Recently, with the emergence of retrieval requirements for certain individual in the same superclass, e.g., birds, persons, cars, fine-grained recognition task has attracted a significant amount of attention from academia and industry. In fine-grained recognition scenario, the inter-class differences are quite diverse and subtle, which makes it challenging to extract all the discriminative cues. Traditional training mechanism optimizes the overall discriminativeness of the whole feature. It may stop early when some feature elements has been trained to distinguish training samples well, leaving other elements insufficiently trained for a feature. This would result in a less generalizable feature extractor that only captures major discriminative cues and ignores subtle ones. Therefore, there is a need for a training mechanism that enforces the discriminativeness of all the elements in the feature to capture more the subtle visual cues. In this paper, we propose a Discrimination-Aware Mechanism (DAM) that iteratively identifies insufficiently trained elements and improves them. DAM is able to increase the number of well learned elements, which captures more visual cues by the feature extractor. In this way, a more informative representation is learned, which brings better generalization performance. We show that DAM can be easily applied to both proxy-based and pair-based loss functions, and thus can be used in most existing fine-grained recognition paradigms. Comprehensive experiments on CUB200-2011, Cars196, Market-1501, and MSMT17 datasets demonstrate the advantages of our DAM based loss over the related state-of-the-art approaches.

关键词： Training Industries Visualization computer vision Dams Feature extraction Birds

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：