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. Our code and trained models will be available at http://vis.xyz/pub/transfiner.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Instance Segmentation BDD100K val Mask Transfiner AP 23.6 # 1
Instance Segmentation COCO 2017 val Mask Transfiner (R50-FPN) mask AP* 43.1 # 2
Instance Segmentation COCO test-dev Mask Transfiner(ResNet101-FPN) mask AP 42.2 # 52

Methods


No methods listed for this paper. Add relevant methods here