M2m: Imbalanced Classification via Major-to-minor Translation

Cited 0 time in webofscience Cited 54 time in scopus
  • Hit : 252
  • Download : 0
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples (e.g., images) from more-frequent classes. This simple approach enables a classifier to learn more generalizable features of minority classes, by transferring and leveraging the diversity of the majority information. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods. The performance of our method even surpasses those of previous state-of-the-art methods for the imbalanced classification.
Publisher
IEEE Computer Society
Issue Date
2020-06-16
Language
English
Citation

IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020

ISSN
1063-6919
DOI
10.1109/CVPR42600.2020.01391
URI
http://hdl.handle.net/10203/278207
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0