Novel mAP: 0.61Known mAP: 21.09All mAP: 2.18
Papers with Code · CC BY-SA 4.0
Novel Object Detection
Novel Object Detection is a challenging task introduced by Fomenko et.al. in their paper "Learning to Discover and Detect Objects". The goal in this task is to measure mAP performance on known as well as novel classes, where the known classes correspond to the 80 COCO classes, and the novel classes are the remaining 1123 classes from LVIS dataset. Thus, during training the model can only be trained with annotations from COCO dataset, but during evaluation/inference it is expected to BOTH classify and detect objects belonging to ALL the classes in the LVIS dataset.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
데이터셋
1개논문
Novel mAP: 17.42Known mAP: 42.08All mAP: 19.33
Novel mAP: 5.42Known mAP: 25.00All mAP: 6.92
Novel mAP: 0.49Known mAP: 20.57All mAP: 2.03
Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
Novel mAP: 0.27Known mAP: 17.85All mAP: 1.62
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.