Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models

• URL: http://arxiv.org/abs/2510.21175v1
• Date: Fri, 24 Oct 2025 05:53:32 GMT
• Title: Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
• Abstract summary: We introduce NuSA-CL (Null Space Adaptation for Continual Learning), a memory-free continual learning framework.<n>NuSA-CL employs low-rank adaptation and constrains task-specific weight updates to lie within an approximate null space of the model's current parameters.<n>Unlike methods relying on replay buffers or costly distillation, NuSA-CL imposes minimal computational and memory overhead.
• Score: 8.646932742603452
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range of real-world tasks without additional task-specific training. However, in real deployment scenarios with evolving environments or emerging classes, these models inevitably face distributional shifts and novel tasks. In such contexts, static zero-shot capabilities are insufficient, and there is a growing need for continual learning methods that allow models to adapt over time while avoiding catastrophic forgetting. We introduce NuSA-CL (Null Space Adaptation for Continual Learning), a lightweight memory-free continual learning framework designed to address this challenge. NuSA-CL employs low-rank adaptation and constrains task-specific weight updates to lie within an approximate null space of the model's current parameters. This strategy minimizes interference with previously acquired knowledge, effectively preserving the zero-shot capabilities of the original model. Unlike methods relying on replay buffers or costly distillation, NuSA-CL imposes minimal computational and memory overhead, making it practical for deployment in resource-constrained, real-world continual learning environments. Experiments show that our framework not only effectively preserves zero-shot transfer capabilities but also achieves highly competitive performance on continual learning benchmarks. These results position NuSA-CL as a practical and scalable solution for continually evolving zero-shot VLMs in real-world applications.

Related papers

• SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning [19.243037567371875]
  Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting.<n>We present SAILS -- Segment Anything with Incrementally Learned Semantics, a training-free framework for Class-Incremental Semantic (CISS)<n>Our results demonstrate that, despite requiring no incremental training, SAILS typically surpasses the performance of existing training-based approaches.
  arXiv  Detail & Related papers  (2026-02-16T14:14:02Z)
• VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models [49.78447737655287]
  VITA is a zero-shot value function learning method that enhances both capabilities via test-time adaptation.<n>We demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning.
  arXiv  Detail & Related papers  (2025-06-11T18:05:33Z)
• Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning [19.27175827358111]
  Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones.<n>We propose a novel continual full fine-tuning approach leveraging adaptive singular value decomposition (SVD)<n>We evaluate our approach extensively on standard continual learning benchmarks using both encoder-decoder (T5-Large) and decoder-only (LLaMA-2 7B) models.
  arXiv  Detail & Related papers  (2025-04-09T17:59:42Z)
• Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning [29.65600202138321]
  In high-speed data stream environments, data do not pause to accommodate slow models. Model's ignorance: the single-pass nature of OCL challenges models to learn effective features within constrained training time. Model's myopia: the local learning nature of OCL leads the model to adopt overly simplified, task-specific features.
  arXiv  Detail & Related papers  (2024-09-28T05:24:56Z)
• CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning [17.614980614656407]
  We propose Continual Generative training for Incremental prompt-Learning. We exploit Variational Autoencoders to learn class-conditioned distributions. We show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities.
  arXiv  Detail & Related papers  (2024-07-22T16:51:28Z)
• Realistic Continual Learning Approach using Pre-trained Models [1.2582887633807602]
  We introduce Realistic Continual Learning (RealCL), a novel CL paradigm where class distributions across tasks are random. We also present CLARE (Continual Learning Approach with pRE-trained models for RealCL scenarios), a pre-trained model-based solution designed to integrate new knowledge while preserving past learning.
  arXiv  Detail & Related papers  (2024-04-11T13:19:46Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• 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)
• Continual Zero-Shot Learning through Semantically Guided Generative Random Walks [56.65465792750822]
  We address the challenge of continual zero-shot learning where unseen information is not provided during training, by leveraging generative modeling. We propose our learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss. Our algorithm achieves state-of-the-art performance on AWA1, AWA2, CUB, and SUN datasets, surpassing existing CZSL methods by 3-7%.
  arXiv  Detail & Related papers  (2023-08-23T18:10:12Z)
• Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning [46.80199921638615]
  Large pre-trained, zero-shot capable models have shown considerable success both for standard transfer and adaptation tasks. However, through naive fine-tuning, these zero-shot models lose their generalizability and robustness towards distribution shifts. In this work, we showcase that where fine-tuning falls short to adapt such zero-shot capable models, simple momentum-based weight can provide consistent improvements.
  arXiv  Detail & Related papers  (2022-11-06T17:41:39Z)
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning [82.07273754143547]
  We propose a meta-continual zero-shot learning (MCZSL) approach to generalizing a model to categories unseen during training. By pairing self-gating of attributes and scaled class normalization with meta-learning based training, we are able to outperform state-of-the-art results.
  arXiv  Detail & Related papers  (2021-02-23T18:36:14Z)

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.