Research map / Continual learning / Domain and prompt-based
Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a flatness-aware learning approach for exemplar-free lifelong person re-identification that addresses gradient conflicts in flat-minima optimization to reduce catastrophic forgetting.
Problem
Lifelong person re-identification must learn sequentially arriving domains without old data (exemplar-free) while avoiding catastrophic forgetting of previously seen identities.
Approach
Identifies a gradient conflict that undermines flat-minima optimization in continual learning and uses flatness-aware learning to resolve it for better generalization in LReID.
Experimental setup
Builds on: sharpness-aware minimization
Closest papers by meaning
- Lifelong Person Re-identification by Pseudo Task Knowledge Preservation (AAAI 2022 · similarity 0.91)
- Generalising without Forgetting for Lifelong Person Re-Identification (AAAI 2021 · similarity 0.90)
- Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification (CVPR 2024 · similarity 0.89)
- DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification (AAAI 2025 · similarity 0.89)
- LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification (AAAI 2024 · similarity 0.88)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 2025 · similarity 0.86)
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.