【论文推荐】最新5篇行人重识别( Person Re-ID)相关论文—样本生成、超越人类、实践指南、姿态归一化、图像生成

2018 年 2 月 14 日 专知 专知内容组(编)
【论文推荐】最新5篇行人重识别( Person Re-ID)相关论文—样本生成、超越人类、实践指南、姿态归一化、图像生成

【导读】专知内容组整理了最近五篇行人重识别( Person Re-Identification)相关文章,为大家进行介绍,欢迎查看!

1. Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification(行人重识别:基于多伪正则化标签的样本生成方法




作者Yan Huang,Jinsong Xu,Qiang Wu,Zhedong Zheng,Zhaoxiang Zhang,Jian Zhang

摘要Sufficient training data is normally required to train deeply learned models. However, the number of pedestrian images per ID in person re-identification (re-ID) datasets is usually limited, since manually annotations are required for multiple camera views. To produce more data for training deeply learned models, generative adversarial network (GAN) can be leveraged to generate samples for person re-ID. However, the samples generated by vanilla GAN usually do not have labels. So in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated images. With MpRL, the generated samples will be used as supplementary of real training data to train a deep model in a semi-supervised learning fashion. Considering data bias between generated and real samples, MpRL utilizes different contributions from predefined training classes. The contribution-based virtual labels are automatically assigned to generated samples to reduce ambiguous prediction in training. Meanwhile, MpRL only relies on predefined training classes without using extra classes. Furthermore, to reduce over-fitting, a regularized manner is applied to MpRL to regularize the learning process. To verify the effectiveness of MpRL, two state-of-the-art convolutional neural networks (CNNs) are adopted in our experiments. Experiments demonstrate that by assigning MpRL to generated samples, we can further improve the person re-ID performance on three datasets i.e., Market-1501, DukeMTMCreID, and CUHK03. The proposed method obtains +6.29%, +6.30% and +5.58% improvements in rank-1 accuracy over a strong CNN baseline respectively, and outperforms the state-of-the- art methods.

x

期刊:arXiv, 2018年1月29日

网址

http://www.zhuanzhi.ai/document/735fe58ab843f2fb02adb71bd0dcbbb7

2. AlignedReID: Surpassing Human-Level Performance in Person Re-IdentificationAlignedReID:在行人重识别中超越了人类水平




作者Xuan Zhang,Hao Luo,Xing Fan,Weilai Xiang,Yixiao Sun,Qiqi Xiao,Wei Jiang,Chi Zhang,Jian Sun

摘要In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.

期刊:arXiv, 2018年1月31日

网址

http://www.zhuanzhi.ai/document/bc360742187b5572c5e07cb0a2284fe7

3. Re-ID done right: towards good practices for person re-identificationRe-ID:行人重识别中实践指南




作者Jon Almazan,Bojana Gajic,Naila Murray,Diane Larlus

摘要Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism.

期刊:arXiv, 2018年1月17日

网址

http://www.zhuanzhi.ai/document/074aefb3ce8c22258d68c3e721e21e8a

4. Pose-Normalized Image Generation for Person Re-identification(基于姿态归一化图像生成的行人重识别方法




作者Xuelin Qian,Yanwei Fu,Wenxuan Wang,Tao Xiang,Yang Wu,Yu-Gang Jiang,Xiangyang Xue

摘要Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on pose. The model is based on a generative adversarial network (GAN) and used specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and highly complementary to features learned with the original images. Importantly, we now have a model that generalizes to any new re-id dataset without the need for collecting any training data for model fine-tuning, thus making a deep re-id model truly scalable. Extensive experiments on five benchmarks show that our model outperforms the state-of-the-art models, often significantly. In particular, the features learned on Market-1501 can achieve a Rank-1 accuracy of 68.67% on VIPeR without any model fine-tuning, beating almost all existing models fine-tuned on the dataset.

期刊:arXiv, 2018年1月18日

网址

http://www.zhuanzhi.ai/document/7ef1e354b55bce36833394c4270ca649

5. Disentangled Person Image Generation(分解行人图像生成方法)




作者Liqian Ma,Qianru Sun,Stamatios Georgoulis,Luc Van Gool,Bernt Schiele,Mario Fritz

摘要Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task.

期刊:arXiv, 2018年1月22日

网址

http://www.zhuanzhi.ai/document/85812c4cdf8ae54ce0e29c7ff251c2b5

-END-

专 · 知

人工智能领域主题知识资料查看获取【专知荟萃】人工智能领域26个主题知识资料全集(入门/进阶/论文/综述/视频/专家等)

同时欢迎各位用户进行专知投稿,详情请点击

诚邀】专知诚挚邀请各位专业者加入AI创作者计划了解使用专知!

请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料

请扫一扫如下二维码关注我们的公众号,获取人工智能的专业知识!

请加专知小助手微信(Rancho_Fang),加入专知主题人工智能群交流!

点击“阅读原文”,使用专知

登录查看更多
7

相关内容

行人重识别(Person re-identification)也称行人再识别,是利用计算机视觉技术判断图像或者视频序列中是否存在特定行人的技术。广泛被认为是一个图像检索的子问题。给定一个监控行人图像,检索跨设备下的该行人图像。旨在弥补目前固定的摄像头的视觉局限,并可与行人检测/行人跟踪技术相结合,可广泛应用于智能视频监控、智能安保等领域。 由于不同摄像设备之间的差异,同时行人兼具刚性和柔性的特性 ,外观易受穿着、尺

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等

While attributes have been widely used for person re-identification (Re-ID) that matches the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image person matching task. However, how to find a set of person images according to a given attribute description, which is very practical in many surveillance applications, remains a rarely investigated cross-modal matching problem in Person Re-ID. In this work, we present this challenge and employ adversarial learning to formulate the attribute-image cross-modal person Re-ID model. By imposing the regularization on the semantic consistency constraint across modalities, the adversarial learning enables generating image-analogous concepts for query attributes and getting it matched with image in both global level and semantic ID level. We conducted extensive experiments on three attribute datasets and demonstrated that the adversarial modelling is so far the most effective for the attributeimage cross-modal person Re-ID problem.

0
7
下载
预览

Sufficient training data is normally required to train deeply learned models. However, the number of pedestrian images per ID in person re-identification (re-ID) datasets is usually limited, since manually annotations are required for multiple camera views. To produce more data for training deeply learned models, generative adversarial network (GAN) can be leveraged to generate samples for person re-ID. However, the samples generated by vanilla GAN usually do not have labels. So in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated images. With MpRL, the generated samples will be used as supplementary of real training data to train a deep model in a semi-supervised learning fashion. Considering data bias between generated and real samples, MpRL utilizes different contributions from predefined training classes. The contribution-based virtual labels are automatically assigned to generated samples to reduce ambiguous prediction in training. Meanwhile, MpRL only relies on predefined training classes without using extra classes. Furthermore, to reduce over-fitting, a regularized manner is applied to MpRL to regularize the learning process. To verify the effectiveness of MpRL, two state-of-the-art convolutional neural networks (CNNs) are adopted in our experiments. Experiments demonstrate that by assigning MpRL to generated samples, we can further improve the person re-ID performance on three datasets i.e., Market-1501, DukeMTMCreID, and CUHK03. The proposed method obtains +6.29%, +6.30% and +5.58% improvements in rank-1 accuracy over a strong CNN baseline respectively, and outperforms the state-of-the- art methods.

0
11
下载
预览
小贴士
相关资讯
相关VIP内容
专知会员服务
46+阅读 · 2020年3月19日
专知会员服务
21+阅读 · 2020年1月10日
八篇 ICCV 2019 【图神经网络(GNN)+CV】相关论文
专知会员服务
26+阅读 · 2020年1月10日
【浙江大学】对抗样本生成技术综述
专知会员服务
58+阅读 · 2020年1月6日
斯坦福&谷歌Jeff Dean最新Nature论文:医疗深度学习技术指南
【深度学习视频分析/多模态学习资源大列表】
专知会员服务
63+阅读 · 2019年10月16日
计算机视觉最佳实践、代码示例和相关文档
专知会员服务
9+阅读 · 2019年10月9日
相关论文
Adversarial Metric Attack for Person Re-identification
Song Bai,Yingwei Li,Yuyin Zhou,Qizhu Li,Philip H. S. Torr
3+阅读 · 2019年1月30日
Are Generative Classifiers More Robust to Adversarial Attacks?
Yingzhen Li,John Bradshaw,Yash Sharma
4+阅读 · 2018年7月9日
Hanxiao Wang,Shaogang Gong,Xiatian Zhu,Tao Xiang
3+阅读 · 2018年5月4日
Wentong Liao,Michael Ying Yang,Ni Zhan,Bodo Rosenhahn
3+阅读 · 2018年2月9日
Zhou Yin,Wei-Shi Zheng,Ancong Wu,Hong-Xing Yu,Hai Wang,Jianhuang Lai
7+阅读 · 2018年2月6日
Yan Huang,Jinsong Xu,Qiang Wu,Zhedong Zheng,Zhaoxiang Zhang,Jian Zhang
11+阅读 · 2018年1月29日
Liqian Ma,Qianru Sun,Stamatios Georgoulis,Luc Van Gool,Bernt Schiele,Mario Fritz
6+阅读 · 2018年1月21日
Weijian Deng,Liang Zheng,Guoliang Kang,Yi Yang,Qixiang Ye,Jianbin Jiao
7+阅读 · 2018年1月10日
Chengyuan Zhang,Lin Wu,Yang Wang
10+阅读 · 2018年1月4日
Lingxiao He,Jian Liang,Haiqing Li,Zhenan Sun
9+阅读 · 2018年1月3日
Top
微信扫码咨询专知VIP会员