The Equalization Losses : Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications. Due to the extremely small ratio of instances, tail categories often show inferior accuracy. In this paper, we find such performance bottleneck is mainly caused by the imbalanced gradients, which can be categorized into two parts: (...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 11 vom: 24. Nov., Seite 13876-13892
|
|---|
| 1. Verfasser: |
Tan, Jingru
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Bo,
Lu, Xin,
Yao, Yongqiang,
Yu, Fengwei,
He, Tong,
Ouyang, Wanli |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|