无需记忆缓冲区即可实现增量学习与未知样本检测。
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
- 推理时使用后验异常检测方法替代内存缓冲区。
- 在多个数据集上性能媲美甚至优于带缓冲区的方法。
- 适合注重隐私和可扩展性的开放世界场景应用。
类增量学习（CIL）在开放世界场景中面临严峻挑战，模型需在不遗忘旧类的前提下持续学习新类，并正确识别来自未知类的输入，避免误分类。现有方法通过任务增量学习框架训练多头模型，并利用分布外（OOD）检测器预测任务身份来应对这些问题。然而，这些方法通常依赖于包含历史数据的记忆缓冲区，带来隐私泄露、可扩展性差及训练时间增加等隐患。本文深入分析了后验OOD检测方法的潜力，发现其在推理阶段适当应用时，可有效替代基于缓冲区的检测机制。实验表明，该无缓冲方法在CIFAR-10、CIFAR-100和Tiny ImageNet上的类增量学习性能及未知样本拒绝能力均达到或超过传统缓冲方法，为高效、隐私友好的开放世界CIL系统设计提供了新思路。
原文摘要 · Abstract (English)
Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle inputs from unknown classes that a closed-set model would misclassify. Recent works address both issues by (i)~training multi-head models using the task-incremental learning framework, and (ii) predicting the task identity employing out-of-distribution (OOD) detectors. While effective, the latter mainly relies on joint training with a memory buffer of past data, raising concerns around privacy, scalability, and increased training time. In this paper, we present an in-depth analysis of post-hoc OOD detection methods and investigate their potential to eliminate the need for a memory buffer. We uncover that these methods, when applied appropriately at inference time, can serve as a strong substitute for buffer-based OOD detection. We show that this buffer-free approach achieves comparable or superior performance to buffer-based methods both in terms of class-incremental learning and the rejection of unknown samples. Experimental results on CIFAR-10, CIFAR-100 and Tiny ImageNet datasets support our findings, offering new insights into the design of efficient and privacy-preserving CIL systems for open-world settings.
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。