Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification

2021-06-14 · Chih-Ting Liu, Man-Yu Lee, Tsai-Shien Chen, Shao-Yi Chien

Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this paper, we propose a Hard Samples Rectification (HSR) learning scheme which resolves the weakness of original clustering-based methods being vulnerable to the hard positive and negative samples in the target unlabelled dataset. Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative). By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks.

📄 PDF Abstract BibTeX arXiv:2106.07204

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringPerson Re-Identification Unsupervised Domain Adaptation Unsupervised Person Re-Identification

Hard Class Rectification for Domain Adaptation

2020-08-08 · Yunlong Zhang, Changxing Jing, Huangxing Lin, Chaoqi Chen 외

Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) to a label-scare domain (target domain). Pseudo-labeling has recently been widely explored and used in DA. However, t…

Domain Adaptation Semi-supervised Domain Adaptation Unsupervised Domain Adaptation

Prior Knowledge Guided Unsupervised Domain Adaptation

2022-07-18 · Tao Sun, Cheng Lu, Haibin Ling

The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges as model adaptation becomes harder witho…

Domain Adaptation Unsupervised Domain Adaptation

Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations

2023-01-01 · CVPR 2023 1 · Rui Gong, Qin Wang, Martin Danelljan, Dengxin Dai 외

Unsupervised domain adaptation (UDA) for semantic segmentation aims at improving the model performance on the unlabeled target domain by leveraging a labeled source domain. Existing approaches have achieved impressiv…

Domain Adaptation Pseudo Label Semantic Segmentation Unsupervised Domain Adaptation

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

2023-09-27 · ICCV 2023 1 · Yizhe Xiong, Hui Chen, Zijia Lin, Sicheng Zhao 외

Unsupervised domain adaptation aims to transfer knowledge from a fully-labeled source domain to an unlabeled target domain. However, in real-world scenarios, providing abundant labeled data even in the source domain can …

Domain Adaptation Self-Supervised Learning Transfer Learning Unsupervised Domain Adaptation

BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective

2022-02-19 · Shanshan Wang, Lei Zhang, Pichao Wang

Triplet loss, one of the deep metric learning (DML) methods, is to learn the embeddings where examples from the same class are closer than examples from different classes. Motivated by DML, we propose an effective BP-Tri…

Domain Adaptation Metric Learning Triplet Unsupervised Domain Adaptation