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

arXiv: https://arxiv.org/abs/2008.10313 · HTML: https://mlsanity.com/paper/2008.10313/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 2 of 2)

- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation](https://mlsanity.com/paper/2111.14014/) (2021)

## Abstract (arXiv)

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% accuracies in terms of mAP, ranked the 2nd place out of 153 teams.