RM
Rainbow Memory: Continual Learning with a Memory of Diverse Samples
arxiv (opens new window) | CVPR 2021
0.Abstract

- 本文关注的‘blurry’ task boundary 渐变增量任务(任务间共享类别),过去的类增量持续学习方法中(disjoint),不同任务中的类别互不交叉
- 样本的多样性更为重要(diversity of samples)
- 样本分类不确定性
- 数据增强
1.Introduction
Contributions
- a new diversity-aware sampling method for effectively managing the memory with limited capacity by leveraging classification uncertainty——选取多样性的样本放置在 Memory 之中
- augment the samples in the memory to further enhance the diversity of the samples——Data augmentation 来进行多样化
2.Related Work
3.Method
Diversity-Aware Memory Update
most discriminative:near the classification boundary
most representative:close to the center of the distribution
Diversity Enhancement by Augmentation
那么,如何通过预测概率的变化定义不确定性呢?作者进一步计算预测类别的变化来评估不确定性,具体来说,就是评估多次扰动中,最经常类别的命中次数占总实验次数的比例,形式化如下,其中
即样本经过变换之后,比如遮挡、平移、旋转等等,如果在模型中的输出的结果方差越大,样本越难,则说明此样本越 diverse. (这里作者的解释并不清晰,逻辑关系有点模糊,因为模型经过变换之后在网络中的输出结果不确定,并不能说明这个样本就靠近 decision boundary)
假定样本为

按不确定性指标排序后进行均匀间隔采样
Diversity Enhancement by Augmentation
‘mix’ images in the classes of the new tasks and the exemplars of the old classes in the memory
4.Experiments
5.Conclusion
6.Reference
- 论文分享:Rainbow Memory: Continual Learning with a Memory of Diverse Samples (opens new window)
- CVPR2021 论文详解 Rainbow Memory: Continual Learning with a Memory of Diverse Samples (opens new window)
上次更新: 2025/04/02, 12:03:38