Towards Discriminative Representation Learning for Unsupervised Person Re-identification

by   Takashi Isobe, et al.

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 network is first pre-trained on source and then fine-tuned on target with pseudo labels created by feature clustering. Such methods sustain two main limitations. (1) The label noise may hinder the learning of discriminative features for recognizing target classes. (2) The domain gap may hinder knowledge transferring from source to target. We propose three types of technical schemes to alleviate these issues. First, we propose a cluster-wise contrastive learning algorithm (CCL) by iterative optimization of feature learning and cluster refinery to learn noise-tolerant representations in the unsupervised manner. Second, we adopt a progressive domain adaptation (PDA) strategy to gradually mitigate the domain gap between source and target data. Third, we propose Fourier augmentation (FA) for further maximizing the class separability of re-ID models by imposing extra constraints in the Fourier space. We observe that these proposed schemes are capable of facilitating the learning of discriminative feature representations. Experiments demonstrate that our method consistently achieves notable improvements over the state-of-the-art unsupervised re-ID methods on multiple benchmarks, e.g., surpassing MMT largely by 8.1%, 9.9%, 11.4% and 11.1% mAP on the Market-to-Duke, Duke-to-Market, Market-to-MSMT and Duke-to-MSMT tasks, respectively.


Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Person re-identification (re-ID) aims at identifying the same persons' i...

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

The unsupervised domain adaptive person re-identification (re-ID) task h...

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification

Unsupervised domain adaptation (UDA) for person re-identification is cha...

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Domain adaptive object re-ID aims to transfer the learned knowledge from...

AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification

Domain adaptive person re-identification (re-ID) is a challenging task, ...

Progressive Cluster Purification for Unsupervised Feature Learning

In unsupervised feature learning, sample specificity based methods ignor...

Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID

In this technical report, we present our submission to the VisDA Challen...

Please sign up or login with your details

Forgot password? Click here to reset