Memory-Free Generative Replay For Class-Incremental Learning

By Xiaomeng Xin, Yiran Zhong, Yunzhong Hou, Jinjun Wang, Liang Zheng. 2021

10 citations recorded by the source corpus.

Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume that old knowledge is well preserved if the classifier produces similar output on new images. In this paper, we find that their effectiveness largely depends on the nature of old classes: they work well on classes that are easily distinguishable between each other but may fail on more fine-grained ones, e.g., boy and girl. In spirit, such methods project new data onto the feature space spanned by the weight vectors in the fully connected layer, corresponding to old classes. The resulting projections would be similar on fine-grained old classes, and as a consequence the new classifier will gradually lose the discriminative ability on these classes. To address this issue, we propose a memory-free generative replay strategy to preserve the fine-grained old classes characteristics by generating representative old images directly from the old classifier and combined with new data for new classifier training. To solve the homogenization problem of the generated samples, we also propose a diversity loss that maximizes Kullback Leibler (KL) divergence between generated samples. Our method is best complemented by prior regularization-based methods proved to be effective for easily distinguishable old classes. We validate the above design and insights on CUB-200-2011, Caltech-101, CIFAR-100 and Tiny ImageNet and show that our strategy outperforms existing memory-free methods with a clear margin. Code is available at https://github.com/xmengxin/MFGR

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jingshan Tang
2. Jieren Deng
3. Yuanhao Yu
4. Li Gu
5. Huan Liu
6. Jianhua Hu
7. Haojian Zhang
8. Zhixiang Chi

In Computer Vision and Pattern Recognition

1. Jingshan Tang
2. Jieren Deng
3. Yuanhao Yu
4. Li Gu
5. Huan Liu
6. Jianhua Hu
7. Jun Chen
8. Haojian Zhang

Citations in the corpus

• Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay (2022, background): “Recently, [26,30,29] have integrated the idea of generative reply into addressing class-incremental learning problem using Deep-Inversion.”
• Incremental Prototype Prompt-tuning with Pre-trained Representation for Class Incremental Learning (2022, methodology): “Recently, the most successful class incremental approaches fight against catastrophic forgetting by replaying the seen data [30, 19, 39] or distilling the previous model [16, 9, 6].”