paper-with-me

Papers

Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning

2023-01-01 · ICCV 2023 1 · Haoyang Cheng, Haitao Wen, Xiaoliang Zhang, Heqian Qiu, Lanxiao Wang, Hongliang Li

Self-supervised learning has attracted a lot of attention recently, which is able to learn powerful representations without any manual annotations. However, self-supervised learning needs to develop the ability to continuously learn to cope with a variety of real-world challenges, i.e., Continual Self-Supervised Learning (CSSL). Catastrophic forgetting is a notorious problem in CSSL, where the model tends to forget the learned knowledge. In practice, simple rehearsal or regularization will bring extra negative effects while alleviating catastrophic forgetting in CSSL, e.g., overfitting on the rehearsal samples or hindering the model from encoding fresh information. In order to address catastrophic forgetting without overfitting on the rehearsal samples, we propose Augmentation Stability Rehearsal (ASR) in this paper, which selects the most representative and discriminative samples by estimating the augmentation stability for rehearsal. Meanwhile, we design a matching strategy for ASR to dynamically update the rehearsal buffer. In addition, we further propose Contrastive Continuity on Augmentation Stability Rehearsal (C2ASR) based on ASR. We show that C2ASR is an upper bound of the Information Bottleneck (IB) principle, which suggests that C2ASR essentially preserves as much information shared among seen task streams as possible to prevent catastrophic forgetting and dismisses the redundant information between previous task streams and current task stream to free up the ability to encode fresh information. Our method obtains a great achievement compared with state-of-the-art CSSL methods on a variety of CSSL benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Self-Supervised LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning

2023-07-10 · Gaurav Bagwe, Xiaoyong Yuan, Miao Pan, Lan Zhang

Federated continual learning (FCL) learns incremental tasks over time from confidential datasets distributed across clients. This paper focuses on rehearsal-free FCL, which has severe forgetting issues when learning new …

Continual LearningPrompt Learning

Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning

2023-03-16 · Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang 외

In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and…

class-incremental learningClass Incremental LearningContinual LearningContrastive Learning+1

Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal

2024-09-04 · Jifeng Hu, Li Shen, Sili Huang, Zhejian Yang 외

Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world ap…

Reinforcement Learning (RL)

Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt

2025-10-01 · Aopeng Wang, Ke Deng, Yongli Ren, Jun Luo arxiv

The main challenge of continual learning is \textit{catastrophic forgetting}. Because of processing data in one pass, online continual learning (OCL) is one of the most difficult continual learning scenarios. To address …

Continual Learning

Escaping Stability-Plasticity Dilemma in Online Continual Learning for Motion Forecasting via Synergetic Memory Rehearsal

2025-08-27 · Yunlong Lin, Chao Lu, Tongshuai Wu, Xiaocong Zhao 외 arxiv

Deep neural networks (DNN) have achieved remarkable success in motion forecasting. However, most DNN-based methods suffer from catastrophic forgetting and fail to maintain their performance in previously learned scenario…

Continual LearningMotion Forecasting