Methods > Computer Vision > Object Detection Models

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.

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

Latest Papers

PAPER DATE
RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
| Cheng-Yang FuMykhailo ShvetsAlexander C. Berg
2019-01-10

Tasks

TASK PAPERS SHARE
Object Detection 1 100.00%

Categories