中文
相关论文

相关论文: Mutual Mean-Teaching: Pseudo Label Refinery for Un…

200 篇论文

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a…

计算机视觉与模式识别 · 计算机科学 2020-09-22 Fabian Dubourvieux , Romaric Audigier , Angelique Loesch , Samia Ainouz , Stephane Canu

Unsupervised Domain Adaptation (UDA) methods for person Re-Identification (Re-ID) rely on target domain samples to model the marginal distribution of the data. To deal with the lack of target domain labels, UDA methods leverage information…

计算机视觉与模式识别 · 计算机科学 2021-01-06 Tiago de C. G. Pereira , Teofilo E. de Campos

In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Yixiao Ge , Shijie Yu , Dapeng Chen

In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the…

计算机视觉与模式识别 · 计算机科学 2021-08-17 Takashi Isobe , Dong Li , Lu Tian , Weihua Chen , Yi Shan , Shengjin Wang

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate…

计算机视觉与模式识别 · 计算机科学 2021-09-29 Yongxing Dai , Jun Liu , Yan Bai , Zekun Tong , Ling-Yu Duan

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Yangru Huang , Peixi Peng , Yi Jin , Yidong Li , Junliang Xing , Shiming Ge

Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations. Clustering-based methods conduct training with the generated pseudo labels and currently dominate this…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Xiao Zhang , Yixiao Ge , Yu Qiao , Hongsheng Li

Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that…

计算机视觉与模式识别 · 计算机科学 2021-09-08 Suncheng Xiang , Yuzhuo Fu , Mengyuan Guan , Ting Liu

Clustering-based unsupervised domain adaptive (UDA) person re-identification (ReID) reduces exhaustive annotations. However, owing to unsatisfactory feature embedding and imperfect clustering, pseudo labels for target domain data inherently…

计算机视觉与模式识别 · 计算机科学 2022-04-29 Jian Han , Ya-Li li , Shengjin Wang

Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the…

计算机视觉与模式识别 · 计算机科学 2020-01-14 Xinyu Zhang , Dong Gong , Jiewei Cao , Chunhua Shen

Many unsupervised domain adaptive (UDA) person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of domain gap, the pseudo-labels are not always reliable and…

计算机视觉与模式识别 · 计算机科学 2020-12-18 Kecheng Zheng , Cuiling Lan , Wenjun Zeng , Zhizheng Zhang , Zheng-Jun Zha

Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine…

计算机视觉与模式识别 · 计算机科学 2021-03-24 Kecheng Zheng , Wu Liu , Lingxiao He , Tao Mei , Jiebo Luo , Zheng-Jun Zha

Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepancy, existing methods mainly attempt to generate pseudo labels…

计算机视觉与模式识别 · 计算机科学 2020-09-15 Junhui Yin , Jiayan Qiu , Siqing Zhang , Zhanyu Ma , Jun Guo

Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source…

计算机视觉与模式识别 · 计算机科学 2019-12-04 Fengxiang Yang , Ke Li , Zhun Zhong , Zhiming Luo , Xing Sun , Hao Cheng , Xiaowei Guo , Feiyue Huang , Rongrong Ji , Shaozi Li

Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused…

计算机视觉与模式识别 · 计算机科学 2024-10-21 Zia-ur-Rehman , Arif Mahmood , Wenxiong Kang

Although unsupervised person re-identification (RE-ID) has drawn increasing research attentions due to its potential to address the scalability problem of supervised RE-ID models, it is very challenging to learn discriminative information…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Hong-Xing Yu , Wei-Shi Zheng , Ancong Wu , Xiaowei Guo , Shaogang Gong , Jian-Huang Lai

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity…

计算机视觉与模式识别 · 计算机科学 2023-01-31 Qiong Wu , Jiahan Li , Pingyang Dai , Qixiang Ye , Liujuan Cao , Yongjian Wu , Rongrong Ji

Person re-identification (re-ID) has gained more and more attention due to its widespread applications in intelligent video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to…

计算机视觉与模式识别 · 计算机科学 2021-10-27 Qi Wang , Sikai Bai , Junyu Gao , Yuan Yuan , Xuelong Li

In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing…

计算机视觉与模式识别 · 计算机科学 2021-02-24 Hao Feng , Minghao Chen , Jinming Hu , Dong Shen , Haifeng Liu , Deng Cai

Person re-identification (Re-ID) models usually show a limited performance when they are trained on one dataset and tested on another dataset due to the inter-dataset bias (e.g. completely different identities and backgrounds) and the…

计算机视觉与模式识别 · 计算机科学 2021-04-29 Jiajie Tian , Zhu Teng , Rui Li , Yan Li , Baopeng Zhang , Jianping Fan
‹ 上一页 1 2 3 10 下一页 ›