通过分层语言指导补偿视觉不足以实现长尾类增量学习
Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning
AI总结：
本文提出分层语言指导方法，通过构建语义层次结构缓解长尾类增量学习中的样本稀缺和灾难性遗忘问题，实验表明方法在多个基准上取得最优性能。
摘要：
长尾类增量学习（LT CIL）仍极具挑战性，因为尾类样本稀缺不仅阻碍其学习，还加剧了持续演变和不平衡数据分布下的灾难性遗忘。为解决这些问题，我们利用语言知识的信息性和可扩展性。具体而言，我们分析LT CIL的数据分布，引导大语言模型（LLMs）生成分层语言树，该树按粗粒度到细粒度的层次组织语义信息。在此基础上，我们引入分层自适应语言指导，利用可学习权重融合多尺度语义表示，从而实现对尾类的动态监督调整，减轻数据不平衡的影响。此外，我们引入分层对齐语言指导，利用语言树的结构稳定性来约束优化并强化语义视觉对齐，从而缓解灾难性遗忘。在多个基准上的广泛实验表明，我们的方法在多个基准上取得了最先进的性能。
英文摘要：
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced data distributions. To tackle these issues, we exploit the informativeness and scalability of language knowledge. Specifically, we analyze the LT CIL data distribution to guide large language models (LLMs) in generating a stratified language tree that hierarchically organizes semantic information from coarse to fine grained granularity. Building upon this structure, we introduce stratified adaptive language guidance, which leverages learnable weights to merge multi-scale semantic representations, thereby enabling dynamic supervisory adjustment for tail classes and alleviating the impact of data imbalance. Furthermore, we introduce stratified alignment language guidance, which exploits the structural stability of the language tree to constrain optimization and reinforce semantic visual alignment, thereby alleviating catastrophic forgetting. Extensive experiments on multiple benchmarks demonstrate that our method achieves 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。
