Name
Abstract | ||
|---|---|---|
Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of this issue. We found that a neural network tends to first under-fit the minor classes by classifying most of their data into the major classes in early training... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICCV48922.2021.00016 | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Keywords | DocType | ISBN |
Training,Deep learning,Knowledge engineering,Computer vision,Neural networks,Fitting,Training data | Conference | 978-1-6654-2812-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Han-Jia Ye | 1 | 47 | 12.03 |
| De-Chuan Zhan | 2 | 394 | 32.57 |
| Wei-Lun Chao | 3 | 391 | 19.32 |