October 28, 2019
TensorMask: A Foundation for Dense Object Segmentation
International Conference on Computer Vision (ICCV)
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. In this work, we investigate the paradigm of dense sliding-window instance segmentation, which is surprisingly under-explored.
By: Xinlei Chen, Ross Girshick, Kaiming He, Piotr Dollar
Facebook AI Research