paper-with-me

Papers

CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition

2024-11-21 · Md Mahedi Hasan, Shoaib Meraj Sami, Nasser Nasrabadi

An important aspect of deploying face recognition (FR) algorithms in real-world applications is their ability to learn new face identities from a continuous data stream. However, the online training of existing deep neural network-based FR algorithms, which are pre-trained offline on large-scale stationary datasets, encounter two major challenges: (I) catastrophic forgetting of previously learned identities, and (II) the need to store past data for complete retraining from scratch, leading to significant storage constraints and privacy concerns. In this paper, we introduce CLFace, a continual learning framework designed to preserve and incrementally extend the learned knowledge. CLFace eliminates the classification layer, resulting in a resource-efficient FR model that remains fixed throughout lifelong learning and provides label-free supervision to a student model, making it suitable for open-set face recognition during incremental steps. We introduce an objective function that employs feature-level distillation to reduce drift between feature maps of the student and teacher models across multiple stages. Additionally, it incorporates a geometry-preserving distillation scheme to maintain the orientation of the teacher model's feature embedding. Furthermore, a contrastive knowledge distillation is incorporated to continually enhance the discriminative power of the feature representation by matching similarities between new identities. Experiments on several benchmark FR datasets demonstrate that CLFace outperforms baseline approaches and state-of-the-art methods on unseen identities using both in-domain and out-of-domain datasets.

📄 PDF Abstract BibTeX arXiv:2411.13886

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningFace RecognitionKnowledge DistillationLifelong learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Evaluating Pretrained models for Deployable Lifelong Learning

2023-11-22 · Kiran Lekkala, Eshan Bhargava, Yunhao Ge, Laurent Itti

We create a novel benchmark for evaluating a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset, and propose a novel Scalable Lifelong Learning system capab…

Atari Gamesclass-incremental learningClass Incremental LearningContinual Learning+4

Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks

2026-01-30 · Jiyuan Pei, Yi Mei, Jialin Liu, Mengjie Zhang 외 arxiv

Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficie…

Scalable Recollections for Continual Lifelong Learning

2017-11-17 · Matthew Riemer, Tim Klinger, Djallel Bouneffouf, Michele Franceschini

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning…

Lifelong learning

Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation

2021-06-19 · CVPR 2021 1 · Mengyao Zhai, Lei Chen, Greg Mori

Deep neural networks are susceptible to catastrophic forgetting: when encountering a new task, they can only remember the new task and fail to preserve its ability to accomplish previously learned tasks. In this pape…

Continual LearningLifelong learning

Task-free Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation

2024-10-03 · Pengzhi Yang, Xinyu Wang, Ruipeng Zhang, Cong Wang 외

A fundamental objective in intelligent robotics is to move towards lifelong learning robot that can learn and adapt to unseen scenarios over time. However, continually learning new tasks would introduce catastrophic forg…

Lifelong learningRetrieval