Research map / Continual learning / Domain and prompt-based
Lifelong Person Re-identification via Knowledge Refreshing and Consolidation
Read the paperCheck 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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add knowledge refreshing to knowledge rehearsal (ablation) | KRC · Average | average incremental R-1: 55.8 -> 70.7 | Helped |
| Add model-space and feature-space consolidation to knowledge rehearsal (ablation) | KRC · Average | average incremental R-1: 55.8 -> 63.0 | Helped |
| Add model-space consolidation to knowledge rehearsal and refreshing (ablation) | KRC · Average | average incremental R-1: 73.5 -> 71.8 | Hurt |
| Add feature-space consolidation to knowledge rehearsal and refreshing (ablation) | KRC · Average | average incremental R-1: 71.8 -> 77.0 | Helped |
| Use model-space and feature-space consolidation together rather than feature-space consolidation alone (ablation) | KRC · Average | average incremental R-1: 73.5 -> 71.8 | Hurt |
| Refresh the memory model using new-task data to support backward transfer | KRC · Seen-domain tasks | BWT: 3.4 -> 5.3 | Helped |
| Use the refreshing-and-consolidation framework to support forward transfer | KRC · Seen-domain tasks | FWT R-1: -13.2 -> 3.9 | Helped |
Closest papers by meaning
- LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification (AAAI 2024 · similarity 0.94)
- Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification (CVPR 2024 · similarity 0.89)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 2025 · similarity 0.88)
- DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification (AAAI 2025 · similarity 0.87)
- A Unified and General Framework for Continual Learning (ICLR 2024 · similarity 0.86)
- Do Your Best and Get Enough Rest for Continual Learning (CVPR 2025 · similarity 0.84)
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.