AI Paper Atlas

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

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 167 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 prediction-space bridge loss (ablation)IDM on Strong Baseline · Market->DukemAP: 67.3 -> 70.5Improved
add feature-space bridge loss (ablation)IDM on Strong Baseline · Market->DukemAP: 69.0 -> 70.5Improved
add diversity loss (ablation)IDM on Strong Baseline · Market->DukemAP: 67.8 -> 70.5Improved
add prediction-space bridge loss (ablation)IDM on Naive Baseline · Market->DukemAP: 66.2 -> 68.6Improved
add feature-space bridge loss (ablation)IDM on Naive Baseline · Market->DukemAP: 65.8 -> 68.6Improved
add diversity loss (ablation)IDM on Naive Baseline · Market->DukemAP: 64.8 -> 68.6Improved
add IDM moduleStrong Baseline · Market->DukemAP: 65.8 -> 70.5Improved
add IDM moduleNaive Baseline · Market->DukemAP: 63.4 -> 68.6Improved
add XBM memory bank for hard negativesNaive Baseline · Market->DukemAP: 63.4 -> 65.8Improved
plug IDM after stage-0 instead of stage-4 (ablation)IDM on Strong Baseline · Market->DukemAP: 68.4 -> 70.5Improved
use IBN-ResNet-50 instead of ResNet-50IDM · Market->MSMT17mAP: 33.5 -> 39.3Improved
use IBN-ResNet-50 instead of ResNet-50IDM · Duke->MarketmAP: 82.8 -> 83.9Improved

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