Non-local RoIs for Instance Segmentation
arXiv:1807.05361
Abstract
We introduce the concept of Non-Local RoI (NL-RoI) Block as a generic and flexible module that can be seamlessly adapted into different Mask R-CNN heads for various tasks. Mask R-CNN treats RoIs (Regions of Interest) independently and performs the prediction based on individual object bounding boxes. However, the correlation between objects may provide useful information for detection and segmentation. The proposed NL-RoI Block enables each RoI to refer to all other RoIs' information, and results in a simple, low-cost but effective module. Our experimental results show that generalizations with NL-RoI Blocks can improve the performance of Mask R-CNN for instance segmentation on the Robust Vision Challenge benchmarks.
Robust Vision Challenge 2018
References in corpus (9)
- YOLOv3: An Incremental Improvement
- Deep Residual Learning for Image Recognition
- DSSD : Deconvolutional Single Shot Detector
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Feature Pyramid Networks for Object Detection
- YOLO9000: Better, Faster, Stronger
- Non-local Neural Networks