ReReLRP——利用 LRP 记忆和识别任务
ReReLRP -- Remembering and Recognizing Tasks with LRP
AI总结：
针对持续学习中的灾难性遗忘，本文提出 ReReLRP，利用 LRP 在无回放条件下跨任务保留信息，增强隐私、可解释性、部署灵活性和存储效率，并在多数据集上达到可比性能。
摘要：
深度神经网络已经革新了众多研究领域和应用。尽管取得了广泛成功，一个被称为灾难性遗忘的根本局限仍然存在：模型在接受新任务训练后，无法保持执行先前所学任务的能力。在某些持续学习场景中，这一局限尤为突出，因为模型必须将来自新领域的知识与其现有能力整合起来。缓解该问题的传统方法通常依赖记忆回放机制，存储原始数据样本、原型或激活模式。这些方法虽然有效，但往往会带来显著的计算开销，引发隐私问题，并需要使用专用架构。在本工作中，我们提出 ReReLRP（Remembering and Recognizing with LRP，利用 LRP 进行记忆与识别），这是一种利用 Layerwise Relevance Propagation（LRP，分层相关性传播）在任务间保留信息的新颖解决方案。我们的贡献提升了现有无回放方法的隐私性，同时还提供内置可解释性、模型架构与部署的灵活性，以及一种提高记忆存储效率的新机制。我们在多种多样的数据集上验证了该方法，结果表明在选定场景中，其性能可与一种著名的基于回放的方法相媲美。
英文摘要：
Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform previously learned tasks after being trained on new ones. This limitation is particularly acute in certain continual learning scenarios, where models must integrate the knowledge from new domains with their existing capabilities. Traditional approaches to mitigate this problem typically rely on memory replay mechanisms, storing either original data samples, prototypes, or activation patterns. Although effective, these methods often introduce significant computational overhead, raise privacy concerns, and require the use of dedicated architectures. In this work we present ReReLRP (Remembering and Recognizing with LRP), a novel solution that leverages Layerwise Relevance Propagation (LRP) to preserve information across tasks. Our contribution provides increased privacy of existing replay-free methods while additionally offering built-in explainability, flexibility of model architecture and deployment, and a new mechanism to increase memory storage efficiency. We validate our approach on a wide variety of datasets, demonstrating results comparable with a well-known replay-based method in selected scenarios.
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。
