Skip to content

Semantic Drift Compensation for Class-Incremental Learning (CVPR2020)

Notifications You must be signed in to change notification settings

yulu0724/SDC-IL

Repository files navigation

SDC-IL

Title: Semantic Drift Compensation for Class-Incremental Learning.

The paper will be published at the conference of 2020 Computer Vision and Pattern Recognition (CVPR20). An pre-print version is available. Poster is linked.

Authors

Lu Yu, Bartłomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost van de Weijer

Requirments

All training and test are done in Pytorch framework.

Pytorch vesion: 0.4.1

Python version: 2.7

Code with higher pytorch version will come soon...

Illustration

figure

Datasets

We evaluate our system in several datasets, including CUB-200-2011, Flowers-102, Caltech-101, CIFAR100, ImageNet-Subset(the first 100 classes of full ImageNet). Please download CUB-200-2011 , Flowers-102, Caltech-101, CIFAR100 and ImagNet-Subset.(Note: some datasets do not split the train set and test set in the original folder, the splited datasets can be download from this link according to the original provided train/test text file.)

Losses

The loss functions in the code refer to source repository.

About

Semantic Drift Compensation for Class-Incremental Learning (CVPR2020)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published