paper-with-me

Comic2k

홈페이지 · 논문 29편

Comic2k is a dataset used for cross-domain object detection which contains 2k comic images with image and instance-level annotations. Image Source: https://naoto0804.github.io/cross_domain_detection/

Images

벤치마크

Weakly Supervised Object Detection on Comic2k 결과 40개
Body Detection on Comic2k 결과 5개
Object Detection on Comic2k 결과 5개
Domain Adaptation on Comic2k 결과 2개