用双原型动态选择适配器，缓解预训练模型增量学习中的遗忘问题。
Dual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning
- 为每个任务设计适配器，通过中心聚类损失提升特征可分性。
- 测试时根据原始原型选适配器，增强原型区分混淆类别能力。
- 在多个数据集上优于现有方法1%-5%，VTAB提升约3%。
类别增量学习（CIL）旨在学习新类别同时保留旧知识。尽管基于预训练模型（PTM）的方法表现优异，但直接对增量任务流微调PTM常导致灾难性遗忘。本文提出带任务自适应的双原型网络（DPTA），为每个增量任务构建适配器模块以微调PTM，其中中心适应损失促使表示更集中且类别可分。双原型网络改进预测过程：原始原型推断测试样本可能的任务索引，从而选择合适适配器；增强原型则用于区分易混淆类别，确定最终结果。在多个基准上的实验表明，DPTA持续优于近期方法1%-5%。尤其在VTAB数据集上，相比最先进方法提升约3%。代码已开源于https://github.com/Yorkxzm/DPTA。
原文摘要 · Abstract (English)
Class-incremental learning (CIL) aims to learn new classes while retaining previous knowledge. Although pre-trained model (PTM) based approaches show strong performance, directly fine-tuning PTMs on incremental task streams often causes renewed catastrophic forgetting. This paper proposes a Dual-Prototype Network with Task-wise Adaptation (DPTA) for PTM-based CIL. For each incremental learning task, an adapter module is built to fine-tune the PTM, where the center-adapt loss forces the representation to be more centrally clustered and class separable. The dual prototype network improves the prediction process by enabling test-time adapter selection, where the raw prototypes deduce several possible task indexes of test samples to select suitable adapter modules for PTM, and the augmented prototypes that could separate confusable classes are utilized to determine the final result. Experiments on multiple benchmarks show that DPTA consistently surpasses recent methods by 1\% - 5\%. Notably, on the VTAB dataset, it achieves approximately 3\% improvement over state-of-the-art methods. The code is open-sourced in https://github.com/Yorkxzm/DPTA}
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。