Auto-selected Knowledge Adapters for Lifelong Person Re-identification

• URL: http://arxiv.org/abs/2405.19005v2
• Date: Thu, 30 May 2024 05:42:46 GMT
• Title: Auto-selected Knowledge Adapters for Lifelong Person Re-identification
• Authors: Xuelin Qian, Ruiqi Wu, Gong Cheng, Junwei Han,
• Abstract summary: Lifelong Person Re-Identification requires systems to continually learn from non-overlapping datasets across different times and locations. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting. We introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning.
• Score: 54.42307214981537
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 outperforms SOTAs by about 10$\sim$20\% mAP on both seen and unseen domains.

Related papers

• CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
  A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement. We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class. A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
  arXiv  Detail & Related papers  (2025-01-13T11:34:55Z)
• Adapter-Enhanced Semantic Prompting for Continual Learning [91.63494614012362]
  Continual learning (CL) enables models to adapt to evolving data streams. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge. We propose a novel lightweight CL framework, which integrates prompt tuning and adapter techniques.
  arXiv  Detail & Related papers  (2024-12-15T06:14:55Z)
• KIF: Knowledge Identification and Fusion for Language Model Continual Learning [41.28933724210434]
  We introduce a novel framework for language models, named Knowledge Identification and Fusion (KIF) KIF segregates the model into'skill units' based on parameter dependencies, allowing for more precise control. It employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task. As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks.
  arXiv  Detail & Related papers  (2024-08-09T17:44:45Z)
• Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification [43.32960398077722]
  Lifelong person Re-IDentification (LReID) is a type of person Re-IDentification (Re-ID) system. LReID relies on replaying exemplars from old domains and applying knowledge distillation in logits with old models. We argue that a Re-ID model trained on diverse and challenging pedestrian images at a large scale can acquire robust and general human semantic knowledge.
  arXiv  Detail & Related papers  (2024-05-30T05:15:38Z)
• Image-Text-Image Knowledge Transferring for Lifelong Person Re-Identification with Hybrid Clothing States [78.52704557647438]
  We propose a more practical task, namely lifelong person re-identification with hybrid clothing states. We take a series of cloth-changing and cloth-consistent domains into account during lifelong learning. We propose a novel framework, dubbed $Teata$, to effectively align, transfer and accumulate knowledge in an "image-text-image" closed loop.
  arXiv  Detail & Related papers  (2024-05-26T15:25:26Z)
• Diverse Representation Embedding for Lifelong Person Re-Identification [10.824003066938234]
  Lifelong Person Re-Identification (LReID) aims to continuously learn from successive data streams, matching individuals across multiple cameras. Existing methods based on CNN backbone are insufficient to explore the representation of each instance from different perspectives. We propose a Diverse Representations Embedding (DRE) framework that first explores a pure transformer for LReID.
  arXiv  Detail & Related papers  (2024-03-24T04:22:37Z)
• Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher [52.2926020848095]
  Federated learning is vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. This paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD.
  arXiv  Detail & Related papers  (2023-04-04T12:04:19Z)
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation [18.4671957106297]
  Lifelong person re-identification (LReID) enables to learn continuously across multiple domains. We design an Adaptive Knowledge Accumulation framework that is endowed with two crucial abilities: knowledge representation and knowledge operation. Our method alleviates catastrophic forgetting on seen domains and demonstrates the ability to generalize to unseen domains.
  arXiv  Detail & Related papers  (2021-03-23T11:30:38Z)
• K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters [136.75235546149995]
  We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. We propose K-Adapter, a framework that retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused model.
  arXiv  Detail & Related papers  (2020-02-05T14:30:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.