IEEE Transactions on Pattern Analysis and Machine Intelligence· 2018Q1
Focal Loss for Dense Object Detection
- 9,656citations
- Q1SCImago
- 2018year
Short summary
A novel Focal Loss function significantly improves one-stage object detectors by down-weighting easy examples and focusing training on hard ones, enabling RetinaNet to match one-stage speed with two-stage accuracy.
AI-generated from the title and abstract; the full text is not read.
TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app
The rest is in the Pofolia app
Takeaways, key points and questions to the paper; new summaries every day for your field. Free.
Sign in on the web to openField: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science