Attention Retention for Continual Learning with Vision Transformers

• URL: http://arxiv.org/abs/2602.05454v1
• Date: Thu, 05 Feb 2026 08:55:58 GMT
• Title: Attention Retention for Continual Learning with Vision Transformers
• Authors: Yue Lu, Xiangyu Zhou, Shizhou Zhang, Yinghui Xing, Guoqiang Liang, Wencong Zhang,
• Abstract summary: Continual learning (CL) empowers AI systems to acquire knowledge from non-stationary data streams.<n>We identify attention drift in Vision Transformers as a primary source of catastrophic forgetting.<n>We propose a novel attention-retaining framework to mitigate forgetting in CL.
• Score: 23.71599936772596
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers as a primary source of catastrophic forgetting, where the attention to previously learned visual concepts shifts significantly after learning new tasks. Inspired by neuroscientific insights into the selective attention in the human visual system, we propose a novel attention-retaining framework to mitigate forgetting in CL. Our method constrains attention drift by explicitly modifying gradients during backpropagation through a two-step process: 1) extracting attention maps of the previous task using a layer-wise rollout mechanism and generating instance-adaptive binary masks, and 2) when learning a new task, applying these masks to zero out gradients associated with previous attention regions, thereby preventing disruption of learned visual concepts. For compatibility with modern optimizers, the gradient masking process is further enhanced by scaling parameter updates proportionally to maintain their relative magnitudes. Experiments and visualizations demonstrate the effectiveness of our method in mitigating catastrophic forgetting and preserving visual concepts. It achieves state-of-the-art performance and exhibits robust generalizability across diverse CL scenarios.

Related papers

• Attention Schema-based Attention Control (ASAC): A Cognitive-Inspired Approach for Attention Management in Transformers [6.853513140582486]
  We introduce ASAC (Attention-based Attention Control), which integrates the attention schema concept into artificial neural networks.<n>By explicitly modeling attention allocation, our approach aims to enhance system efficiency.<n>We demonstrate ASAC's effectiveness in both the vision and NLP domains, highlighting its ability to improve classification accuracy and expedite the learning process.
  arXiv  Detail & Related papers  (2025-09-19T15:08:30Z)
• Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent [72.1517476116743]
  Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets.<n>Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue.<n>We introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation forgetting.<n>We propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations.
  arXiv  Detail & Related papers  (2025-02-17T12:26:34Z)
• Point Cloud Understanding via Attention-Driven Contrastive Learning [64.65145700121442]
  Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms. PointACL is an attention-driven contrastive learning framework designed to address these limitations. Our method employs an attention-driven dynamic masking strategy that guides the model to focus on under-attended regions.
  arXiv  Detail & Related papers  (2024-11-22T05:41:00Z)
• A Primal-Dual Framework for Transformers and Neural Networks [52.814467832108875]
  Self-attention is key to the remarkable success of transformers in sequence modeling tasks. We show that the self-attention corresponds to the support vector expansion derived from a support vector regression problem. We propose two new attentions: Batch Normalized Attention (Attention-BN) and Attention with Scaled Head (Attention-SH)
  arXiv  Detail & Related papers  (2024-06-19T19:11:22Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• Continual Attentive Fusion for Incremental Learning in Semantic Segmentation [43.98082955427662]
  Deep architectures trained with gradient-based techniques suffer from catastrophic forgetting. We introduce a novel attentive feature distillation approach to mitigate catastrophic forgetting. We also introduce a novel strategy to account for the background class in the distillation loss, thus preventing biased predictions.
  arXiv  Detail & Related papers  (2022-02-01T14:38:53Z)
• Self-Regulated Learning for Egocentric Video Activity Anticipation [147.9783215348252]
  Self-Regulated Learning (SRL) aims to regulate the intermediate representation consecutively to produce representation that emphasizes the novel information in the frame of the current time-stamp. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets.
  arXiv  Detail & Related papers  (2021-11-23T03:29:18Z)
• Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection [7.324459578044212]
  Face presentation attack detection (PAD) is attracting a lot of attention and playing a key role in securing face recognition systems. We propose a dual-stream convolution neural networks (CNNs) framework to deal with unseen scenarios. We successfully prove the design of our proposed PAD solution in a step-wise ablation study.
  arXiv  Detail & Related papers  (2021-09-16T13:06:43Z)
• Untangling tradeoffs between recurrence and self-attention in neural networks [81.30894993852813]
  We present a formal analysis of how self-attention affects gradient propagation in recurrent networks. We prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies. We propose a relevancy screening mechanism that allows for a scalable use of sparse self-attention with recurrence.
  arXiv  Detail & Related papers  (2020-06-16T19:24:25Z)

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.