SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.06468 · 2022

Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain. However, an adapted ReID model usually only works well on a certain target domain, but can hardly memorize the source domain knowledge and generalize to upcoming unseen data. In this paper, we propose unsupervised lifelong person ReID, which focuses on continuously conducting unsupervised domain adaptation on new domains without forgetting the knowledge learnt from old domains. To tackle unsupervised lifelong ReID, we conduct a contrastive rehearsal on a small number of stored old samples while sequentially adapting to new domains. We further set an image-to-image similarity constraint between old and new models to regularize the model updates in a way that suits old knowledge. We sequentially train our model on several large-scale datasets in an unsupervised manner and test it on all seen domains as well as several unseen domains to validate the generalizability of our method. Our proposed unsupervised lifelong method achieves strong generalizability, which significantly outperforms previous lifelong methods on both seen and unseen domains. Code will be made available at https://github.com/chenhao2345/UCR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.06468")
get_code_for_paper("2203.06468")
have("2203.06468")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.06468.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.06468.svg)](https://syntology.ai/paper/2203.06468)

Connect an agent — have() is free.