( 참고 : 패스트 캠퍼스 , 한번에 끝내는 컴퓨터비전 초격차 패키지 )
Instance Segmentation - Mask RCNN
1. Mask RCNN
(Mask R-CNN, He et al., ICCV 2017)
RCNN family
- RCNN, Fast RCNN, Faster RCNN : Object Detection
- Mask RCNN : Instance Segmentation
Summary
- Extend Faster RCNN to pixel-level instage segmentation
- RoI Align
\(\mathcal{L}=\mathcal{L}_{\text {cls }}+\mathcal{L}_{\text {box }}+\mathcal{L}_{\text {mask }}\).
- \(\mathcal{L}_{\text {cls }}\) & \(\mathcal{L}_{\text {box }}\) : same as Faster RCNN
- \(\mathcal{L}_{\text {mask }}=-\frac{1}{m^{2}} \sum_{1 \leq i, j \leq m}\left[y_{i j} \log \hat{y}_{i j}^{k}+\left(1-y_{i j}\right) \log \left(1-\hat{y}_{i j}^{k}\right)\right]\).
2. Summary of RCNN family
( https://lilianweng.github.io/posts/2017-12-31-object-recognition-part-3/ )
