paper-with-me

Papers

Controlling Forgetting with Test-Time Data in Continual Learning

2024-06-19 · Vaibhav Singh, Rahaf Aljundi, Eugene Belilovsky

Foundational vision-language models have shown impressive performance on various downstream tasks. Yet, there is still a pressing need to update these models later as new tasks or domains become available. Ongoing Continual Learning (CL) research provides techniques to overcome catastrophic forgetting of previous information when new knowledge is acquired. To date, CL techniques focus only on the supervised training sessions. This results in significant forgetting yielding inferior performance to even the prior model zero shot performance. In this work, we argue that test-time data hold great information that can be leveraged in a self supervised manner to refresh the model's memory of previous learned tasks and hence greatly reduce forgetting at no extra labelling cost. We study how unsupervised data can be employed online to improve models' performance on prior tasks upon encountering representative samples. We propose a simple yet effective student-teacher model with gradient based sparse parameters updates and show significant performance improvements and reduction in forgetting, which could alleviate the role of an offline episodic memory/experience replay buffer.

📄 PDF Abstract BibTeX arXiv:2406.13653

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning

2026-05-07 · Md Anwar Hossen, Fatema Siddika, Juan Pablo Munoz, Tanya Roosta 외 arxiv

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model …

Continual Learning

Continual Learning by Three-Phase Consolidation

2024-03-12 · Davide Maltoni, Lorenzo Pellegrini

TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge. Each experien…

Continual Learning

Adversarial Targeted Forgetting in Regularization and Generative Based Continual Learning Models

2021-02-16 · Muhammad Umer, Robi Polikar

Continual (or "incremental") learning approaches are employed when additional knowledge or tasks need to be learned from subsequent batches or from streaming data. However these approaches are typically adversary agnosti…

Backdoor Attackclass-incremental learningClass Incremental LearningContinual Learning+2

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

2026-05-10 · Yuanyi Wang, Yifan Yang, Su Lu, Yanggan Gu 외 arxiv

Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential updates enable capability transfer and when they cause catastrophic fo…

Forgetting, plasticity, and co-observation: a third facet of continual learning

2026-08-19 · Timm Hess, Abhishek Jha, Gido M. van de Ven, Tinne Tuytelaars arxiv

Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two …

Continual Learning