AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Towards Discriminative Representation Learning for Unsupervised Person Re-Identification

Takashi Isobe, Dong Li, Lu Tian, Weihua Chen, Yi Shan, Shengjin Wang

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 89 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cluster-wise contrastive learning (CCL) (ablation)two-stage baseline · Market-to-DukemAP: 53.7 -> 59.6Improved
add progressive domain adaptation (PDA) on top of CCL (ablation)Baseline + CCL · Market-to-DukemAP: 59.6 -> 67.3Improved
add Fourier augmentation (FA) on top of CCL and PDA (ablation)Baseline + CCL + PDA · Market-to-DukemAP: 67.3 -> 69.4Improved
use cluster-wise pairs instead of instance-wise pairs (ablation)CCL · Market-to-DukemAP: 37.3 -> 69.4Improved
add past negatives from the queue (ablation)CCL · Market-to-DukemAP: 66.8 -> 69.4Improved
drop same-class instances from the queue (ablation)CCL · Market-to-DukemAP: 68.1 -> 69.4Improved
set queue size to 1024 instead of 2048 (ablation)CCL · Market-to-DukemAP: 67.6 -> 69.4Improved
use progressive weights instead of two-stage training (ablation)PDA · Market-to-DukemAP: 62.1 -> 69.4Improved
use progressive weights instead of best static weights (0.2;0.8) (ablation)PDA · Market-to-DukemAP: 58.8 -> 69.4Improved
use 3-step policy instead of linear policy (ablation)PDA · Market-to-DukemAP: 67.6 -> 69.4Improved
use Fourier plus spatial loss instead of spatial only (ablation)FA · Market-to-DukemAP: 67.3 -> 69.4Improved
use Fourier amplitude features instead of a single MLP layer (ablation)FA · Market-to-DukemAP: 68.2 -> 69.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy