paper-with-me

홈 › Papers

CLA: Latent Alignment for Online Continual Self-Supervised Learning

2025-07-14 · Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta arxiv

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply with a fixed computational budget, and task boundaries are absent. We introduce Continual Latent Alignment (CLA), a novel SSL strategy for Online CL that aligns the representations learned by the current model with past representations to mitigate forgetting. We found that our CLA is able to speed up the convergence of the training process in the online scenario, outperforming state-of-the-art approaches under the same computational budget. Surprisingly, we also discovered that using CLA as a pretraining protocol in the early stages of pretraining leads to a better final performance when compared to a full i.i.d. pretraining.

📄 PDF Abstract BibTeX arXiv:2507.10434

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning

2026-06-30 · Julien Lefebvre, Stefan Duffner, Mathieu Lefort arxiv

Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints. Existing methods rely either …

Self-Supervised LearningKnowledge DistillationContrastive LearningContinual Learning

Self-Supervised Training Enhances Online Continual Learning

2021-03-25 · Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale i…

Continual Learningimage-classificationImage Classification

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR

2026-04-12 · Giacomo Cignoni, Simone Magistri, Andrew D. Bagdanov, Antonio Carta arxiv

This paper explores Online Continual Self-Supervised Learning (OCSSL), a scenario in which models learn from continuous streams of unlabeled, non-stationary data, where methods typically employ replay and fast convergenc…

Self-Supervised Learning

Replay-free Online Continual Learning with Self-Supervised MultiPatches

2025-02-13 · Giacomo Cignoni, Andrea Cossu, Alex Gomez-Villa, Joost Van de Weijer 외

Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden…

Continual LearningSelf-Supervised Learning

SCoDA: Self-supervised Continual Domain Adaptation

2025-09-12 · Chirayu Agrawal, Snehasis Mukherjee arxiv

Source-Free Domain Adaptation (SFDA) addresses the challenge of adapting a model to a target domain without access to the data of the source domain. Prevailing methods typically start with a source model pre-trained with…

Source-Free Domain Adaptation