IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

08/05/2021
by   Yongxing Dai, et al.
3

Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabeled target domain. From a novel perspective, we argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task, and we focus on explicitly modeling appropriate intermediate domains to characterize this bridging. Specifically, we propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly by mixing the source and target domains' hidden representations using two domain factors. Based on the "shortest geodesic path" definition, i.e., the intermediate domains along the shortest geodesic path between the two extreme domains can play a better bridging role, we propose two properties that these intermediate domains should satisfy. To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors. The bridge losses aim at guiding the distribution of appropriate intermediate domains to keep the right distance to the source and target domains. The diversity loss serves as a regularization to prevent the generated intermediate domains from being over-fitting to either of the source and target domains. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks, and the mAP gain is up to 7.7 is available at https://github.com/SikaStar/IDM.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/03/2022

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Cross-domain person re-identification (re-ID), such as unsupervised doma...
research
04/03/2019

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

This paper considers the domain adaptive person re-identification (re-ID...
research
09/16/2022

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

In unsupervised domain adaptation (UDA), directly adapting from the sour...
research
05/08/2022

Cross-lingual Adaptation for Recipe Retrieval with Mixup

Cross-modal recipe retrieval has attracted research attention in recent ...
research
05/25/2021

Feature Space Targeted Attacks by Statistic Alignment

By adding human-imperceptible perturbations to images, DNNs can be easil...
research
09/05/2022

Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain

Unsupervised domain adaptation (UDA) has attracted considerable attentio...
research
07/11/2022

Gradual Domain Adaptation without Indexed Intermediate Domains

The effectiveness of unsupervised domain adaptation degrades when there ...

Please sign up or login with your details

Forgot password? Click here to reset