Incremental Learning with Unlabeled Data in the Wild

Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 29-32

Abstract


We propose to leverage a continuous and large stream of unlabeled data in the wild to alleviate catastrophic forget- ting in class-incremental learning. Our experimental results on CIFAR and ImageNet datasets demonstrate the superiority of the proposed methods over prior methods: compared to the state-of-the-art method, our proposed method shows up to 14.9% higher accuracy and 45.9% less forgetting.

Related Material


[pdf]
[bibtex]
@InProceedings{Lee_2019_CVPR_Workshops,
author = {Lee, Kibok and Lee, Kimin and Shin, Jinwoo and Lee, Honglak},
title = {Incremental Learning with Unlabeled Data in the Wild},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}