How does Mask R-CNN extend Faster R-CNN for instance segmentation?
hardAnswer
- Add a parallel FCN mask-prediction head to each RoI, predicting a small binary mask (28×28 typically) per class.
- Replaces RoIPool with RoIAlign (bilinear interpolation instead of quantization) — critical for precise mask localization.
- Preserves the classification / box head.
- Standard instance-segmentation baseline; adopted broadly for pose estimation, keypoints, panoptic segmentation.
Check yourself — multiple choice
- Same as U-Net
- Faster R-CNN + per-RoI mask FCN head + RoIAlign → instance segmentation
- No mask head
- Removes classification
Mask R-CNN: Faster R-CNN + mask FCN + RoIAlign → instance seg.
#segmentation#computer-vision#detection
Practise Deep Learning
214 interview questions in this topic.