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

08/24/2020
by   Yixiao Ge, et al.
2

In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual Mean-Teaching (MMT) frameworks. SDA, a domain-translation-based framework, focuses on carefully translating the source-domain images to the target domain. MMT, a pseudo-label-based framework, focuses on conducting pseudo label refinery with robust soft labels. Specifically, there are three main steps in our training pipeline. (i) We adopt SDA to generate source-to-target translated images, and (ii) such images serve as informative training samples to pre-train the network. (iii) The pre-trained network is further fine-tuned by MMT on the target domain. Note that we design an improved MMT (dubbed MMT+) to further mitigate the label noise by modeling inter-sample relations across two domains and maintaining the instance discrimination. Our proposed method achieved 74.78

READ FULL TEXT
research
03/14/2020

Structured Domain Adaptation for Unsupervised Person Re-identification

Unsupervised domain adaptation (UDA) aims at adapting the model trained ...
research
05/26/2022

CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement

Recent works on unsupervised domain adaptation (UDA) focus on the select...
research
02/15/2022

Beyond Deterministic Translation for Unsupervised Domain Adaptation

In this work we challenge the common approach of using a one-to-one mapp...
research
07/29/2020

Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

In unsupervised domain adaptation (UDA), classifiers for the target doma...
research
08/07/2021

Towards Discriminative Representation Learning for Unsupervised Person Re-identification

In this work, we address the problem of unsupervised domain adaptation f...
research
09/02/2020

Mutual Teaching for Graph Convolutional Networks

Graph convolutional networks produce good predictions of unlabeled sampl...

Please sign up or login with your details

Forgot password? Click here to reset