MaskPlus: Improving Mask Generation for Instance Segmentation
arXiv:1907.06713
Abstract
Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts -- a detection component and a mask generation branch, and mostly focus on the improvement of the detection part. In this paper, we present an approach that extends Mask R-CNN with five novel optimization techniques for improving the mask generation branch and reducing the conflicts between the mask branch and the detection component in training. These five techniques are independent to each other and can be flexibly utilized in building various instance segmentation architectures for increasing the overall accuracy. We demonstrate the effectiveness of our approach with tests on the COCO dataset.
References in corpus (10)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Semantic Instance Segmentation with a Discriminative Loss Function
- Cascade R-CNN: Delving into High Quality Object Detection
- Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
- Semantic Instance Segmentation via Deep Metric Learning
- Gland Instance Segmentation Using Deep Multichannel Neural Networks
- Proposal-free Network for Instance-level Object Segmentation
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images