利用适配器中的归一化层结合渐进学习与自适应蒸馏实现跨域少样本学习
Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning
AI总结：
针对跨域少样本学习中批量统计偏移和样本统计带噪问题，提出含两种适配器的ProLAD框架，结合渐进训练与自适应蒸馏，在标准基准上性能超越现有最优方法。
摘要：
跨域少样本学习是一项极具挑战性的任务，模型必须在基类上完成训练，随后在仅提供少量样本的情况下，对来自不同域的新类别进行测试。现有方法主要聚焦于使用适配器的参数高效方案，但往往忽略了两个关键问题：批量统计量偏移，以及由域差异变化引发的带噪样本统计量。本文提出了一种全新的通用框架ProLAD（渐进学习与自适应蒸馏），该框架利用适配器中的归一化层实现跨域少样本学习，主要有两方面贡献。第一，我们的方法采用两个独立的适配器：一个不含归一化层，对相似域的适配效果更优；另一个嵌入了归一化层，旨在利用目标域的批量统计量，因此对差异较大的域适配效果显著。第二，为解决统计量带噪的问题，我们采用了两种策略：对两个适配器进行渐进式训练，以及基于仅含无归一化层适配器的模型所提取特征，设计自适应蒸馏技术。通过这种自适应蒸馏，我们的方法可起到调制器的作用，根据每个域的情况控制主适配器完成适配。在标准跨域少样本学习基准上的评估结果表明，我们的技术性能优于现有的最优方法。
英文摘要：
Cross-domain few-shot learning presents a formidable challenge, as models must be trained on base classes and then tested on novel classes from various domains with only a few samples at hand. While prior approaches have primarily focused on parameter-efficient methods of using adapters, they often overlook two critical issues: shifts in batch statistics and noisy sample statistics arising from domain discrepancy variations. In this paper, we introduce a novel generic framework that leverages normalization layer in adapters with Progressive Learning and Adaptive Distillation (ProLAD), marking two principal contributions. First, our methodology utilizes two separate adapters: one devoid of a normalization layer, which is more effective for similar domains, and another embedded with a normalization layer, designed to leverage the batch statistics of the target domain, thus proving effective for dissimilar domains. Second, to address the pitfalls of noisy statistics, we deploy two strategies: a progressive training of the two adapters and an adaptive distillation technique derived from features determined by the model solely with the adapter devoid of a normalization layer. Through this adaptive distillation, our approach functions as a modulator, controlling the primary adapter for adaptation, based on each domain. Evaluations on standard cross-domain few-shot learning benchmarks confirm that our technique outperforms existing state-of-the-art methodologies.
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。
