一种面向遥感领域持续自监督学习的可塑性感知方法
A Plasticity-Aware Method for Continual Self-Supervised Learning in Remote Sensing
AI总结：
针对现有遥感持续自监督学习方法因侧重防灾难性遗忘而降低学习可塑性的问题，提出一种带解耦机制的知识蒸馏CSSL方法，划分任务共有与特有特征以兼顾记忆稳定与新特征学习，在两类增量场景下性能均优于主流框架CaSSLe。
摘要：
持续自监督学习（CSSL）方法因能够从连续的无标签数据流中顺序学习新任务，在遥感（RS）领域受到越来越多的关注。现有的CSSL方法在学习新任务时，重点在于防止灾难性遗忘。为此，大多数方法采用正则化策略来保留先前任务的知识，这会降低模型适应新任务数据的能力（即学习可塑性），进而可能导致性能下降。为解决这一问题，本文提出了一种新型CSSL方法，旨在实现任务顺序学习的同时保持高学习可塑性。为此，该方法采用了集成了解耦机制的知识蒸馏策略。解耦的实现方式为：首先将特征维度划分为任务共有部分和任务特有部分，随后强制任务共有特征保持关联以确保记忆稳定性，同时强制任务特有特征去关联以促进新特征的学习。实验结果表明，与广泛使用的CSSL框架CaSSLe相比，该方法具备有效性：在任务增量场景下，平均准确率提升最高达1.12%，不妥协度提升最高达2.33%；在类别增量场景下，平均准确率提升最高达1.24%，不妥协度提升最高达2.01%。
英文摘要：
Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while learning new tasks, focus on preventing catastrophic forgetting. To this end, most of them use regularization strategies to retain knowledge of previous tasks. This reduces the model's ability to adapt to the data of new tasks (i.e., learning plasticity), which can degrade performance. To address this problem, in this paper, we propose a novel CSSL method that aims to learn tasks sequentially, while achieving high learning plasticity. To this end, the proposed method uses a knowledge distillation strategy with an integrated decoupling mechanism. The decoupling is achieved by first dividing the feature dimensions into task-common and task-specific parts. Then, the task-common features are forced to be correlated to ensure memory stability while the task-specific features are forced to be de-correlated facilitating the learning of new features. Experimental results show the effectiveness of the proposed method compared to CaSSLe, which is a widely used CSSL framework, with improvements of up to 1.12% in average accuracy and 2.33% in intransigence in a task-incremental scenario, and 1.24% in average accuracy and 2.01% in intransigence in a class-incremental scenario.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
