基于双原型自增强与精炼的无样本在线类增量持续学习
Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement
AI总结：
针对无样本在线类增量持续学习中无样本重放导致的灾难性遗忘、无法全量重训的问题，提出含双类原型与自增强精炼策略的DSR方法，在保证隐私与低内存的同时提升了任务性能。
摘要：
本文研究了一个全新且实用但颇具挑战性的问题，名为无样本在线类增量持续学习（Non-exemplar Online Class-incremental continual Learning, NO-CL），该问题旨在不缓存数据样本的前提下保持基类的可区分性，同时在单次遍历（即在线）的数据流中持续高效地学习新类。该任务的挑战主要有两方面：（1）由于没有过往样本可用于重放，基类和新类都会遭受严重的灾难性遗忘。（2）由于在线数据只能被观测一次，无法对整个模型进行完全重训练，例如通过原型对齐或特征蒸馏来重新校准决策边界。针对NO-CL问题，本文提出了一种新颖的双原型自增强与精炼方法（Dual-prototype Self-augment and Refinement method, DSR），该方法包含两种策略：1）双类原型：利用原始原型和高维原型来借助预训练信息，获得鲁棒的准正交表示，而非使用样本缓冲区，以此兼顾隐私保护与内存占用降低。2）自增强与精炼：我们不更新整个网络，而是通过一个双层优化问题，基于自增强的原始原型，交替优化高维原型与额外的投影模块。大量实验证明了所提出的DSR在NO-CL任务中的有效性与优越性。
英文摘要：
This paper investigates a new, practical, but challenging problem named Non-exemplar Online Class-incremental continual Learning (NO-CL), which aims to preserve the discernibility of base classes without buffering data examples and efficiently learn novel classes continuously in a single-pass (i.e., online) data stream. The challenges of this task are mainly two-fold: (1) Both base and novel classes suffer from severe catastrophic forgetting as no previous samples are available for replay. (2) As the online data can only be observed once, there is no way to fully re-train the whole model, e.g., re-calibrate the decision boundaries via prototype alignment or feature distillation. In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for NO-CL problem, which consists of two strategies: 1) Dual class prototypes: vanilla and high-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction. 2) Self-augment and refinement: Instead of updating the whole network, we optimize high-dimensional prototypes alternatively with the extra projection module based on self-augment vanilla prototypes, through a bi-level optimization problem. Extensive experiments demonstrate the effectiveness and superiority of the proposed DSR in NO-CL.
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。
