atlas

Research map / Continual learning / Domain and prompt-based

Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

CVPR 2021 · Continual learning › Domain and prompt-based · approach: Lifelong person re-identification · 99 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 AKA instead of CRLLifelong person ReID · LReID-UnseenmAP: 39.6$\pm$ 0.4 -> 44.3$\pm$ 0.2Helped
Use AKA instead of CRLLifelong person ReID · LReID-Seen (average across domains)mAP: 30.8 -> 32.3Helped
Add plasticity loss to the LwF baseline (ablation)LReID model · LReID-UnseenmAP: 38.3 -> 41.6Helped
Add plasticity loss to the LwF baseline (ablation)LReID model · LReID-SeenmAP: 29.6 -> 29.5No clear effect
Add stability loss to the model with plasticity loss (ablation)LReID model · LReID-SeenmAP: 29.5 -> 32.3Helped
Add stability loss to the model with plasticity loss (ablation)LReID model · LReID-UnseenmAP: 41.6 -> 44.3Helped
Remove distillation loss from full AKA (ablation)AKA · LReID-SeenmAP: 32.3 -> 28.5Hurt
Remove distillation loss from full AKA (ablation)AKA · LReID-UnseenmAP: 44.3 -> 42.1Hurt
Increase the number of knowledge graph vertices (ablation)AKA · LReID-UnseenmAPHelped
Set the plasticity weight very large (ablation)AKA · LReID generalizationrepresentation generalizationHurt

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