Unsupervised Domain Adaptive Re-Identification: Theory and Practice

By Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du, Qian Zhang, Chang Huang, Xinggang Wang. Pattern Recognition, 2018

363 citations recorded by the source corpus.

We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classification theories to re-ID tasks. Concretely, we introduce some assumptions on the extracted feature space and then derive several loss functions guided by these assumptions. To optimize them, a novel self-training scheme for unsupervised domain adaptive re-ID tasks is proposed. It iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels. Extensive experiments on unsupervised domain adaptive person re-ID and vehicle re-ID tasks with comparisons to the state-of-the-arts confirm the effectiveness of the proposed theories and self-training framework. Our code is available at \url{this https URL}.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/42656cf2b75dccc7f8f224f7a86c2ea4de1ae671

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiebo Luo
2. Zhengjun Zha
3. Tao Mei
4. Hongsheng Li
5. Cuiling Lan
6. Wenjun Zeng
7. Zhibo Chen
8. Dapeng Chen

In Computer Vision and Pattern Recognition

1. Hongsheng Li
2. Xiaogang Wang
3. Jiebo Luo
4. Luc Van Gool
5. Tao Mei
6. Yi Yang
7. Dacheng Tao
8. Zhengjun Zha

Citations in the corpus

• Group-aware Label Transfer for Domain Adaptive Person Re-identification (2021, methodology): “Existing UDA ReID approaches [14, 26, 35, 45, 55] typically include three steps: feature pre-training with labeled source domain data, clustering-based pseudo-label prediction for the target domain data, and feature representation learning/fine-tuning with the pseudo-labels.”
• Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification (2019, neutral): “For all clustering-guided re-ID [14, 6, 20], the quality of pseudo labels generated by clusters directly determines the performance of the model.”
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (2020, methodology): “State-of-the-art UDA methods (Song et al., 2018; Zhang et al., 2019b; Yang et al., 2019) for person re-ID group unannotated images with clustering algorithms and train the network with clusteringgenerated pseudo labels.”
• Style Normalization and Restitution for Generalizable Person Re-Identification (2020, methodology): “UDAbased ReID methods can be roughly divided into three categories: style transfer [3, 44, 26], attribute recognition [43, 49, 33], and target-domain pseudo label estimation [5, 37, 58, 40, 52, 50].”