AdalReID: Auto-selected Knowledge Adapters for Lifelong Person Re-identification
cs.CV
Submitted: 2024-05-29
Updated: 2026-10-29
Comments: Accepted by TPAMI
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations…
Terminology
Abstract
Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of previous ones. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting since they try to cram diverse knowledge into one fixed model. To overcome this limitation, we introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning. Concretely, we incrementally build distinct adapters to learn domain-specific knowledge at each step, which can effectively learn and preserve knowledge across different datasets. Meanwhile, the proposed auto-selection strategy adaptively calculates the knowledge similarity between the input set and the adapters. On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model. Extensive experiments are conducted to demonstrate the superiority of our AdalReID, which significantly beats SOTAs by about 5% and 3% mAP on seen and unseen domains.
Sources
- Vision Transformer Adapter for Dense Predictions
- In Defense of the Triplet Loss for Person Re-Identification
- LoRA: Low-Rank Adaptation of Large Language Models
- Diverse Representation Embedding for Lifelong Person Re-Identification
- Progressive Neural Networks
- Decentralised Person Re-Identification with Selective Knowledge Aggregation
- Joint Detection and Identification Feature Learning for Person Search
- MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning
- Lifelong Learning with Dynamically Expandable Networks
- Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs