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 ...
Publications
2 shownBoosting Adversarial Attacks with Momentum
Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks se...
Frequent Co-Authors
Researcher Info
- h-index
- 2
- Publications
- 2
- Citations
- 2,789
External Links
Identifiers
- ORCID
- 0000-0002-8645-0680
Impact Metrics
h-index
2
h-index: Number of publications with at least h citations each.