Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning

• URL: http://arxiv.org/abs/2509.15347v1
• Date: Thu, 18 Sep 2025 18:41:06 GMT
• Title: Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
• Abstract summary: We propose a contrastive strategy named textbfGlobal textbfPre-fixing, textbfLocal textbfAdjusting for textbfSupervised textbfContrastive learning (GPLASC)<n>Specifically, we divide the entire unit hypersphere of representations into non-overlapping regions, with the centers of the regions forming an inter-task pre-fixed.<n>For individual tasks, our method helps regulate the feature structure and form intra-
• Score: 35.27260472296966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has been a promising direction in CL. Despite advancements, their performance is still limited due to confusion arising from both inter-task and intra-task features. To address the problem, we propose a simple yet effective contrastive strategy named \textbf{G}lobal \textbf{P}re-fixing, \textbf{L}ocal \textbf{A}djusting for \textbf{S}upervised \textbf{C}ontrastive learning (GPLASC). Specifically, to avoid task-level confusion, we divide the entire unit hypersphere of representations into non-overlapping regions, with the centers of the regions forming an inter-task pre-fixed \textbf{E}quiangular \textbf{T}ight \textbf{F}rame (ETF). Meanwhile, for individual tasks, our method helps regulate the feature structure and form intra-task adjustable ETFs within their respective allocated regions. As a result, our method \textit{simultaneously} ensures discriminative feature structures both between tasks and within tasks and can be seamlessly integrated into any existing contrastive continual learning framework. Extensive experiments validate its effectiveness.

Related papers

• GNSP: Gradient Null Space Projection for Preserving Cross-Modal Alignment in VLMs Continual Learning [27.9960664846484]
  Contrastive Language-Image Pretraining has demonstrated remarkable zero-shot generalization by aligning visual and textual modalities in a shared embedding space.<n>When continuously fine-tuned on diverse tasks, CLIP suffers from catastrophic forgetting and degradation of its embedding alignment.<n>We propose Gradient Null Space Projection (GNSP), an efficient continual learning method that projects task-specific gradients onto the null space of previously learned knowledge.
  arXiv  Detail & Related papers  (2025-07-26T07:22:12Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation [5.296260279593993]
  Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.<n>We propose an optimal transport (OT)-guided prompt learning framework that mitigates forgetting by preserving the structural consistency of feature distributions.<n>Our approach enforces joint constraints on both vision and text representations, ensuring a holistic feature alignment.
  arXiv  Detail & Related papers  (2025-03-11T21:38:34Z)
• Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning [3.708456605408296]
  We propose a method called Feature Realignment through Experts on hyperSpHere in Continual Learning (Fresh-CL)<n>We propose a dynamic extension of ETF through mixture of experts, enabling adaptive projections onto diverse subspaces to enhance feature representation.<n>Experiments on 11 datasets demonstrate a 2% improvement in accuracy compared to the strongest baseline.
  arXiv  Detail & Related papers  (2025-01-04T05:20:53Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning [50.88504784466931]
  Multi-task dense prediction involves semantic segmentation, depth estimation, and surface normal estimation. Existing solutions typically rely on learning global image representations for global cross-task image matching. Our proposal involves modeling region-wise representations using Gaussian Distributions.
  arXiv  Detail & Related papers  (2024-03-15T12:41:30Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning [60.501201259732625]
  We introduce task-adaptive saliency for EFCIL and propose a new framework, which we call Task-Adaptive Saliency Supervision (TASS) Our experiments demonstrate that our method can better preserve saliency maps across tasks and achieve state-of-the-art results on the CIFAR-100, Tiny-ImageNet, and ImageNet-Subset EFCIL benchmarks.
  arXiv  Detail & Related papers  (2022-12-16T02:43:52Z)
• Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach [14.674494335647841]
  We propose a two-stage training paradigm for CL that intertwines task-agnostic and task-specific learning. We show that our training paradigm can be easily added to memory- or regularization-based approaches.
  arXiv  Detail & Related papers  (2022-07-13T15:16:51Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation [165.61511788237485]
  Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. We propose a dynamic task-oriented disentangling network (DTDN) to learn disentangled representations in an end-to-end fashion for UDA.
  arXiv  Detail & Related papers  (2020-07-27T01:21:18Z)

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.