PofoliaShared via Pofolia

arXiv (Cornell University)· 2018· Preprint

YOLOv3: An Incremental Improvement

Joseph Redmon, Ali Farhadi

Short summary

YOLOv3 achieves 28.2 mAP at 320x320 resolution in 22ms, matching SSD accuracy while being three times faster, and outperforms RetinaNet on the mAP@50 metric (57.9 vs 57.5) by being 3.8x faster (51ms vs 198ms).

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 open

Field: Computer Vision and Pattern Recognition

Computer Vision and Pattern RecognitionComputer Science