Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Re-Identification

HARI MOHAN PANDEY*, Yang Yang, Guan'an Wang, Prayag Tiwari, Zhen Lei

*Corresponding author for this work

Research output: Contribution to journalArticle (journal)peer-review

4 Citations (Scopus)
145 Downloads (Pure)


Recently, unsupervised cross-dataset person reidentification (Re-ID) has attracted more and more attention, which aims to transfer knowledge of a labeled source domain to an unlabeled target domain. There are two common frameworks: one is pixel-alignment of transferring low-level knowledge and the other is feature-alignment of transferring high-level knowledge. In this paper, we propose a novel Recurrent Auto-Encoder (RAE) framework to unify these two kinds of methods and inherit their merits. Specifically, the proposed RAE includes three modules, i.e. a feature-transfer module, a pixel-transfer module and a fusion module. The feature-transfer module utilizes an encoder to map source and target images to a shared feature space. In the space, not only features are identity-discriminative, but also the gap between source and target features is reduced. The pixel-transfer module takes a decoder to reconstruct original images with its features. Here, we hope the images reconstructed from target features are in source-style. Thus, the low-level knowledge can be propagated to the target domain. After transferring both high- and low-level knowledge with the two proposed module above, we design another bilinear pooling layer to fuse both kinds of knowledge. Extensive experiments on Market-1501, DukeMTMC-ReID and MSMT17 datasets show that our method significantly outperforms either pixel-alignment or feature-alignment Re-ID methods, and achieves new state-of-the-art results.
Original languageEnglish
Article numberTNNLS-2020-I-14474.R2
JournalIEEE Transactions on Neural Networks and Learning Systems
Early online date1 Dec 2021
Publication statusE-pub ahead of print - 1 Dec 2021


  • —Person Re-Identification
  • Unsupervised Learning
  • Adversarial Nets
  • Feature Fusion


Dive into the research topics of 'Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Re-Identification'. Together they form a unique fingerprint.

Cite this