Mask Transfiner for High-Quality Instance Segmentation

Lei Ke, Martin Danelljan, Xia Li, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu
arXiv 2021

Mask Transfiner for High-Quality Instance Segmentation


Two-stage and query-based instance segmentation methods have achieved remarkable results. However, their segmented masks are still very coarse. In this paper, we present Mask Transfiner for high-quality and efficient instance segmentation. Instead of operating on regular dense tensors, our Mask Transfiner decomposes and represents the image regions as a quadtree. Our transformer-based approach only processes detected error-prone tree nodes and self-corrects their errors in parallel. While these sparse pixels only constitute a small proportion of the total number, they are critical to the final mask quality. This allows Mask Transfiner to predict highly accurate instance masks, at a low computational cost. Extensive experiments demonstrate that Mask Transfiner outperforms current instance segmentation methods on three popular benchmarks, significantly improving both two-stage and query-based frameworks by a large margin of +3.0 mask AP on COCO and BDD100K, and +6.6 boundary AP on Cityscapes.





    author    = {Ke, Lei and Danelljan, Martin and Li, Xia and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher},
    journal = {arXiv preprint arXiv:2111.13673},
    title     = {Mask Transfiner for High-Quality Instance Segmentation},
    year      = {2021}