AP-Loss for Accurate One-Stage Object Detection
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework t...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 11 vom: 01. Nov., Seite 3782-3798
|
|---|
| 1. Verfasser: |
Chen, Kean
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Lin, Weiyao,
Li, Jianguo,
See, John,
Wang, Ji,
Zou, Junni |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|