Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

01/13/2020
by   Xinyu Zhang, et al.
4

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 underlying similarity-and-dissimilarity relationships among the unlabelled samples in the target domain. In order to use the whole data relationships efficiently in mini-batch training, we apply a series of memory modules to maintain an up-to-date representation of the entire dataset. Unlike the simple exemplar memory in previous works, we propose a novel multi-level memory network (MMN) to discover multi-level complementary information in the target domain, relying on three memory modules, i.e., part-level memory, instance-level memory, and domain-level memory. The proposed memory modules store multi-level representations of the target domain, which capture both the fine-grained differences between images and the global structure for the holistic target domain. The three memory modules complement each other and systematically integrate multi-level supervision from bottom to up. Experiments on three datasets demonstrate that the multi-level memory modules cooperatively boost the unsupervised cross-domain Re-ID task, and the proposed MMN achieves competitive results.

READ FULL TEXT

page 1

page 7

page 8

page 10

page 11

research
10/19/2020

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Aiming at recognizing images of the same person across distinct camera v...
research
04/06/2019

A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification

Unsupervised cross-domain person re-identification (Re-ID) faces two key...
research
08/01/2019

Learning to Adapt Invariance in Memory for Person Re-identification

This work considers the problem of unsupervised domain adaptation in per...
research
07/31/2019

Self-training with progressive augmentation for unsupervised cross-domain person re-identification

Person re-identification (Re-ID) has achieved great improvement with dee...
research
07/28/2019

Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID

Person re-identification (ReID) remains a very difficult challenge in co...
research
03/24/2018

Multi-Level Factorisation Net for Person Re-Identification

Key to effective person re-identification (Re-ID) is modelling discrimin...
research
05/02/2017

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner

Impressive image captioning results are achieved in domains with plenty ...

Please sign up or login with your details

Forgot password? Click here to reset