# Continual Representation Learning for Biometric Identification

arXiv: https://arxiv.org/abs/2006.04455 · HTML: https://mlsanity.com/paper/2006.04455/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 25 of 25)

- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Layerwise Optimization by Gradient Decomposition for Continual Learning](https://mlsanity.com/paper/2105.07561/) (2021)
- [Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting](https://mlsanity.com/paper/2108.08165/) (2021)
- [Continual Learning for Visual Search with Backward Consistent Feature Embedding](https://mlsanity.com/paper/2205.13384/) (2022)
- [Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges](https://mlsanity.com/paper/2207.11759/) (2022)
- [DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification](https://mlsanity.com/paper/2412.09224/) (2024)
- [Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2308.10716/) (2023)
- [Diverse Representation Embedding for Lifelong Person Re-Identification](https://mlsanity.com/paper/2403.16003/) (2024)
- [Auto-selected Knowledge Adapters for Lifelong Person Re-identification](https://mlsanity.com/paper/2405.19005/) (2024)
- [Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification](https://mlsanity.com/paper/2405.19695/) (2024)
- [Open-World Dynamic Prompt and Continual Visual Representation Learning](https://mlsanity.com/paper/2409.05312/) (2024)
- [Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification](https://mlsanity.com/paper/2504.15041/) (2025)
- [Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification](https://mlsanity.com/paper/2210.01600/) (2022)
- [CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition](https://mlsanity.com/paper/2411.13886/) (2024)
- [GaitAdapt: Continual Learning for Evolving Gait Recognition](https://mlsanity.com/paper/2508.03375/) (2025)
- [A Stationary (and Therefore Compatible) Representation is All You Need](https://mlsanity.com/paper/2606.12488/) (2026)
- [Gradient Regularized Contrastive Learning for Continual Domain Adaptation](https://mlsanity.com/paper/2103.12294/) (2021)
- [Camera-Incremental Object Re-Identification with Identity Knowledge Evolution](https://mlsanity.com/paper/2305.15909/) (2023)
- [Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification](https://mlsanity.com/paper/2411.06023/) (2024)
- [DSKC: Domain Style Modeling with Adaptive Knowledge Consolidation for Exemplar-free Lifelong Person Re-Identification](https://mlsanity.com/paper/2508.03516/) (2025)
- [Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification](https://mlsanity.com/paper/2512.25000/) (2025)
- [Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification](https://mlsanity.com/paper/2607.19122/) (2026)
- [Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints](https://mlsanity.com/paper/2609.01014/) (2026)
- [SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification](https://mlsanity.com/paper/2609.12577/) (2026)

## Abstract (arXiv)

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning (CL) setting, namely ``continual representation learning'', which focuses on learning better representation in a continuous way. We also provide two large-scale multi-step benchmarks for biometric identification, where the visual appearance of different classes are highly relevant. In contrast to requiring the model to recognize more learned classes, we aim to learn feature representation that can be better generalized to not only previously unseen images but also unseen classes/identities. For the new setting, we propose a novel approach that performs the knowledge distillation over a large number of identities by applying the neighbourhood selection and consistency relaxation strategies to improve scalability and flexibility of the continual learning model. We demonstrate that existing CL methods can improve the representation in the new setting, and our method achieves better results than the competitors.