Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models

• URL: http://arxiv.org/abs/2607.09785v1
• Date: Wed, 08 Jul 2026 13:44:58 GMT
• Title: Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
• Abstract summary: We present a comprehensive survey of continual self-supervised learning (CSSL) for vision.<n>We examine why self-supervised objectives exhibit improved robustness to catastrophic forgetting.<n>We identify open challenges such as scalability and the need for fast adaptability.
• Score: 26.65040437876567
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams. This has led to the development of continual self-supervised learning (CSSL), a rapidly growing area that lacks a dedicated, systematic review. In this work, we present a comprehensive survey of CSSL for vision, with connections to emerging vision-language settings. First, we analyze existing evaluation protocols and highlight inconsistencies that hinder fair comparison. We then examine why self-supervised objectives exhibit improved robustness to catastrophic forgetting, relating this to task-agnostic representations and smoother loss landscapes. Next, we organize existing methods into a unified taxonomy based on their forgetting-mitigation strategies, including distillation, replay, regularization, architectural approaches, model merging, and objective-level adaptation. Finally, we identify open challenges such as scalability and the need for fast adaptability. We argue that advancing CSSL requires moving beyond small-scale benchmarks towards continual pre-training paradigms for large-scale systems.

Related papers

• Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis [39.81956241706565]
  We present CLeaRS, a benchmark for continual vision-language learning in remote sensing.<n>CLeaRS comprises 10 curated subsets with over 207k image-text pairs, spanning diverse interpretation tasks, sensing modalities, and application scenarios.<n>Extensive benchmarking of diverse vision-language models reveals catastrophic forgetting across all settings.
  arXiv  Detail & Related papers  (2026-04-01T12:27:31Z)
• LibContinual: A Comprehensive Library towards Realistic Continual Learning [62.34449396069085]
  A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones.<n>We propose LibContinual, a comprehensive and reproducible library designed to serve as a foundational platform for realistic CL.
  arXiv  Detail & Related papers  (2025-12-26T13:59:13Z)
• Learning Affordances at Inference-Time for Vision-Language-Action Models [50.93181349331096]
  In robotics, Vision-Language-Action models (VLAs) offer a promising path towards solving complex control tasks.<n>We introduce Learning from Inference-Time Execution (LITEN), which connects a VLA low-level policy to a high-level VLM that conditions on past experiences.<n>Our approach iterates between a reasoning phase that generates and executes plans for the low-level VLA, and an assessment phase that reflects on the resulting execution.
  arXiv  Detail & Related papers  (2025-10-22T16:43:29Z)
• LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics [10.638045151201084]
  We present a principled taxonomy of twelve recent stateful unlearning methods.<n>We revisit the evaluation of unlearning effectiveness (UE), utility retention (UT), and robustness (Rob)<n>Our analysis shows that current evaluations, dominated by multiple-choice question (MCQ) accuracy, offer only a narrow perspective.
  arXiv  Detail & Related papers  (2025-10-08T23:47:05Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• Evolving Machine Learning: A Survey [8.382299491159852]
  This survey focuses on five core challenges: data drift, concept drift, catastrophic forgetting, skewed learning, and network adaptation.<n>We systematically review over 100 studies, categorizing state-of-the-art methods across supervised, unsupervised, and semi-supervised approaches.<n>Our findings aim to guide researchers and practitioners in developing robust, ethical, and scalable systems for real-world deployment.
  arXiv  Detail & Related papers  (2025-05-23T13:50:02Z)
• Temporal-Difference Variational Continual Learning [77.92320830700797]
  We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Semi-Supervised and Unsupervised Deep Visual Learning: A Survey [76.2650734930974]
  Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. We review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective.
  arXiv  Detail & Related papers  (2022-08-24T04:26:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.