基于视觉-语言模型的小样本类别增量学习
Few Shot Class Incremental Learning using Vision-Language models
AI总结：
针对现实中新类别训练数据有限且需增量学习同时保留基础类别性能的问题，提出融合语言与子空间正则化器的FSCIL框架，利用视觉-语言模型语义，在三个基准上取得SOTA性能。
摘要：
深度学习的最新进展已在各类有监督计算机视觉任务中展现出可与人类能力媲美的卓越性能。然而，模型训练前需拥有涵盖所有类别的海量训练数据这一普遍假设，往往与现实场景不符——真实场景中新类别通常只有有限的可用数据。如何将仅含少量样本的新类别无缝融入训练数据，同时要求模型既能灵活适配这些新增类别，又不损害其在基础类别上的性能，成为一大挑战。为应对这一需求，研究界在小样本类别增量学习（few-shot class incremental learning, FSCIL）领域提出了多种解决方案。\n本研究提出了一种创新的FSCIL框架，该框架采用语言正则化器与子空间正则化器。在基础训练阶段，语言正则化器有助于融入从视觉-语言（Vision-Language）模型中提取的语义信息。子空间正则化器则在增量训练阶段，帮助模型掌握基础类别固有的图像与文本语义之间的细微关联。我们提出的框架不仅能让模型在数据有限的情况下适配新类别，还能确保保留其在基础类别上的性能。为验证我们方法的有效性，我们在三个不同的FSCIL基准上开展了全面实验，实验中该框架取得了当前最优（state-of-the-art）性能。
英文摘要：
Recent advancements in deep learning have demonstrated remarkable performance comparable to human capabilities across various supervised computer vision tasks. However, the prevalent assumption of having an extensive pool of training data encompassing all classes prior to model training often diverges from real-world scenarios, where limited data availability for novel classes is the norm. The challenge emerges in seamlessly integrating new classes with few samples into the training data, demanding the model to adeptly accommodate these additions without compromising its performance on base classes. To address this exigency, the research community has introduced several solutions under the realm of few-shot class incremental learning (FSCIL). In this study, we introduce an innovative FSCIL framework that utilizes language regularizer and subspace regularizer. During base training, the language regularizer helps incorporate semantic information extracted from a Vision-Language model. The subspace regularizer helps in facilitating the model's acquisition of nuanced connections between image and text semantics inherent to base classes during incremental training. Our proposed framework not only empowers the model to embrace novel classes with limited data, but also ensures the preservation of performance on base classes. To substantiate the efficacy of our approach, we conduct comprehensive experiments on three distinct FSCIL benchmarks, where our framework attains state-of-the-art performance.
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。
