RetinaMask

2000년 도입 · 논문 1편에서 사용

RetinaMask is a one-stage object detection method that improves upon RetinaNet by adding the task of instance mask prediction during training, as well as an adaptive loss that improves robustness to parameter choice during training, and including more difficult examples in training.

출처: RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

소개 논문: RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free