用CLOOB替换CLIP，提升少样本增量学习性能。
An experimental approach on Few Shot Class Incremental Learning
- 用CLOOB替代CLIP，优化视觉语言模型
- 在多数据集和架构上验证性能提升
- 适合关注少样本学习与模型记忆保持的研究者
少样本类增量学习（FSCIL）是机器学习前沿范式，旨在让模型在仅有少量新类别样本的情况下学习新知识，同时保护已有知识。本文通过大规模数据集、领域偏移和不同网络架构的实验，评估并比较多种方法。我们分析其优势后，提出一种实验方法：将表现优异的零样本学习模型CLIP替换为性能更优的CLOOB模型，以提升FSCIL性能。本报告旨在提供一种改进FSCIL的实验路径，并综述该领域的最新进展，重点探讨缓解灾难性遗忘的策略，以及提升模型对动态任务与数据集的适应能力。
原文摘要 · Abstract (English)
Few-Shot Class-Incremental Learning (FSCIL) represents a cutting-edge paradigm within the broader scope of machine learning, designed to empower models with the ability to assimilate new classes of data with limited examples while safeguarding existing knowledge. The paper will present different solutions which contain extensive experiments across large-scale datasets, domain shifts, and network architectures to evaluate and compare the selected methods. We highlight their advantages and then present an experimental approach with the purpose of improving the most promising one by replacing the visual-language (V-L) model (CLIP) with another V-L model (CLOOB) that seem to outperform it on zero-shot learning tasks. The aim of this report is to present an experimental method for FSCIL that would improve its performance. We also plan to offer an overview followed by an analysis of the recent advancements in FSCIL domain, focusing on various strategies to mitigate catastrophic forgetting and improve the adaptability of models to evolving tasks and datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。