https://github.com/luogen1996/oneteacher
공식 코드Towards End-to-end Semi-supervised Learning for One-stage Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Towards End-to-end Semi-supervised Learning for One-stage Object Detection
CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
End-to-End Semi-Supervised Object Detection with Soft Teacher
Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
ALWOD: Active Learning for Weakly-Supervised Object Detection
Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
SIOD: Single Instance Annotated Per Category Per Image for Object Detection
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
A Simple Semi-Supervised Learning Framework for Object Detection
A Simple Semi-Supervised Learning Framework for Object Detection
Points as Queries: Weakly Semi-supervised Object Detection by Points
A Simple Semi-Supervised Learning Framework for Object Detection
End-to-End Semi-Supervised Object Detection with Soft Teacher
Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.