RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6857-6865
Abstract
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner. Through fusing more detailed information stage by stage, RefineMask is able to refine high-quality masks consistently. RefineMask succeeds in segmenting hard cases such as bent parts of objects that are oversmoothed by most previous methods and outputs accurate boundaries. Without bells and whistles, RefineMask yields significant gains of 2.6, 3.4, 3.8 AP over Mask R-CNN on COCO, LVIS, and Cityscapes benchmarks respectively at a small amount of additional computational cost. Furthermore, our single-model result outperforms the winner of the LVIS Challenge 2020 by 1.3 points on the LVIS test-dev set and establishes a new state-of-the-art. Code will be available at https://github.com/zhanggang001/RefineMask.Keywords
Funding Information
- National Key Research and Development Program of China
- National Natural Science Foundation of China
This publication has 16 references indexed in Scilit:
- LVIS: A Dataset for Large Vocabulary Instance Segmentation2019
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features2018
- Mask R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade2017
- Boundary-Aware Instance Segmentation2017
- Learning to Refine Object Segments2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation2016
- ImageNet: A large-scale hierarchical image database2009