390 papers with code • 9 benchmarks • 32 datasets
Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.
Within this family, we show that the architecture of the mask-head plays a surprisingly important role in generalization to classes for which we do not observe masks during training.
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #4 on Image Classification on iNaturalist
To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors.
Ranked #46 on Instance Segmentation on COCO test-dev
In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.
Ranked #4 on Panoptic Segmentation on KITTI Panoptic Segmentation
The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.