ECCV22-FOSTER
ECCV22-FOSTER copied to clipboard
G-U-N
The official implementation for ECCV22 paper: "FOSTER: Feature Boosting and Compression for Class-Incremental Learning" in PyTorch.
Hi. Thank you for your great work! While I am trying to reproduce your work for further research, I found following imagenet-100 configs yield inferior results for imagenet-1000. Can you...
作者您好，打扰您了。 请问能否方便提供一下[performance.png](https://github.com/G-U-N/ECCV22-FOSTER/blob/master/imgs/performance.png)这个图中的每个方法每个阶段的具体数据，也就是您论文中的图3.谢谢！
Is "Bound" joint-training 100 classes？Why Bound has different results ?  thank you！
Hello, Can you please provide the config file of training ImageNet1k? Thanks!
Mentioned in the paper:Through this scaling strategy, the absolute value of logits for old categories is reduced, and the absolute value of logits for new ones is enlarged, thus forcing...
