TensorMask: A Foundation for Dense Object Segmentation

ICCV 2019 Xinlei ChenRoss GirshickKaiming HePiotr Dollár

Sliding-window object detectors that generate bounding-box object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Instance Segmentation COCO test-dev TensorMask (ResNet-101-FPN) mask AP 37.3% # 18

Methods used in the Paper