SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.03024 · 2021

Rethinking Sampling Strategies for Unsupervised Person Re-identification

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

Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role. We analyze the reasons for the performance differences between various sampling strategies under the same framework and loss function. We suggest that deteriorated over-fitting is an important factor causing poor performance, and enhancing statistical stability can rectify this problem. Inspired by that, a simple yet effective approach is proposed, termed group sampling, which gathers samples from the same class into groups. The model is thereby trained using normalized group samples, which helps alleviate the negative impact of individual samples. Group sampling updates the pipeline of pseudo-label generation by guaranteeing that samples are more efficiently classified into the correct classes. It regulates the representation learning process, enhancing statistical stability for feature representation in a progressive fashion. Extensive experiments on Market-1501, DukeMTMC-reID and MSMT17 show that group sampling achieves performance comparable to state-of-the-art methods and outperforms the current techniques under purely camera-agnostic settings. Code has been available at https://github.com/ucas-vg/GroupSampling.

For agents

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

get_harvested_code_for_paper("2107.03024")
get_code_for_paper("2107.03024")
have("2107.03024")

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

curl https://syntology.ai/api/ran/2107.03024.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.03024.svg)](https://syntology.ai/paper/2107.03024)

Connect an agent — have() is free.