AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

AdalReID: Auto-selected Knowledge Adapters for Lifelong Person Re-identification

Xuelin Qian, Ruiqi Wu, Zhongling Huang, Dingwen Zhang, Junwei Han

TPAMI 2026 · Continual learning › Domain and prompt-based · approach: Lifelong person re-identification · 9 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
use temperature scheduling instead of one-hot similarity (fine-tuning) (ablation)AdalReID · CUHK02 unseenmAP: 79.6 -> 82.5Improved
use temperature scheduling instead of one-hot similarity (fine-tuning) (ablation)AdalReID · seen-averagemAP: 84.2 -> 83.1Hurt
use temperature scheduling instead of uniform merging (t=2.0) (ablation)AdalReID · seen-averagemAP: 78.2 -> 83.1Improved
use temperature scheduling instead of learnable t (ablation)AdalReID · seen-averagemAP: 79.4 -> 83.1Improved
use 2-Wasserstein auto-selection instead of random selection (ablation)AdalReID · seen-averagemAP: 69.7 -> 83.1Improved
use 2-Wasserstein auto-selection instead of latest selection (ablation)AdalReID · seen-averagemAP: 71.4 -> 83.1Improved
use 2-Wasserstein instead of MMD for distribution distance (ablation)AdalReID · CUHK02 unseenRank-1: 80.0 -> 81.4No clear effect
add Projection adapter on top of Q,V (ablation)knowledge adapters · seen-averagemAP: 82.0 -> 82.9Improved
add FFN adapters to Q,K,V,Proj adapters (ablation)knowledge adapters · seen-averagemAP: 83.1 -> 84.7Improved
use task-wise instead of sample-wise adapter selection (ablation)AdalReID · Order-1 seen-averagemAP: 72.1 -> 76.5Improved
increase adapter rank from 16 to 64 (ablation)knowledge adapters · seen domainsmAPImproved
use large adapter scale alpha/r=8 (ablation)knowledge adapters · seen domainsmAPHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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