SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.06133 · CVPR · 2021

Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification

Xiao Zhang, Yixiao Ge, Hongsheng Li, Yu Qiao

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 object re-identification targets at learning discriminative representations for object retrieval without any annotations. 46,10] conduct training with the generated pseudo labels and currently dominate this research direction. However, they still suffer from the issue of pseudo label noise. To tackle the challenge, we propose to properly estimate pseudo label similarities between consecutive training generations with clustering consensus and refine pseudo labels with temporally propagated and ensembled pseudo labels. To the best of our knowledge, this is the first attempt to leverage the spirit of temporal ensembling [25] to improve classification with dynamically changing classes over generations. The proposed pseudo label refinery strategy is simple yet effective and can be seamlessly integrated into existing clustering-based unsupervised re-identification methods. With our proposed approach, state-of-the-art method [10] can be further boosted with up to 8.8% mAP improvements on the challenging MSMT17 [39] dataset.

For agents

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

get_harvested_code_for_paper("2106.06133")
get_code_for_paper("2106.06133")
have("2106.06133")

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

curl https://syntology.ai/api/ran/2106.06133.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.06133.svg)](https://syntology.ai/paper/2106.06133)

Connect an agent — have() is free.