Matting Enhanced Mask R-CNN
Lufan Ma, Bin Dong, Jiangpeng Yan, Xiu Li · 2021
We propose a novel and effective method for high-quality instance segmentation. Top-performing "detect-then-segment" approaches (e.g., Mask R-CNN) rely on region-of-interest (ROI) cropping operations to obtain the final masks, but their performance is restricted by blurry boundary and average loss weight. Here, we develop a unique perspective of image segmentation as an image matting problem. Our method, termed MMask R-CNN, enjoys two advantages: 1) Present a novel matting enhanced mask head to generate trimap-based mat-ting features as auxiliary priors, which enhance accurate estimation of alpha values for boundary pixels. 2) Explicitly represents the classification uncertainty with confidence indicator alpha matte, and design a Uncertainty-Aware Binary Cross-Entropy Loss to assign larger weights to pixels with higher uncertainty. We evaluate the proposed method through extensive experiments on the COCO dataset. The experimental results show that our method outperforms well-tuned Mask R-CNN baseline by 2.3% AP.