Published on Sat Apr 17 2021

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

Gang Zhang, Xin Lu, Jingru Tan, Jianmin Li, Zhaoxiang Zhang, Quanquan Li, Xiaolin Hu
0
0
0
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 over-smoothed 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.

Tue Sep 17 2019
Computer Vision
AdaptIS: Adaptive Instance Selection Network
Adaptive Instance Selection network architecture for class-agnostic instance segmentation. Given an input image and a point, it generates a mask for the object located at that point. The network adapts to the input point with a help of AdaIN layers, thus producing different masks.
0
0
0
Sun Aug 15 2021
Computer Vision
SOTR: Segmenting Objects with Transformers
Most recent transformer-based models show impressive performance on vision tasks. Segmenting Objects with TRansformers (SOTR) simplifies the segmentation pipeline. SOTR can effectively extract lower-level feature representations and capture long-range context.
5
21
129
Mon Apr 12 2021
Computer Vision
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
0
0
0
Fri Feb 12 2021
Machine Learning
INSTA-YOLO: Real-Time Instance Segmentation
Insta-YOLO is a novel one-stage end-to-end deep learning model for real-time instance segmentation. Instead of pixel-wise prediction, our model predicts instances as object contours represented by 2D points in Cartesian space.
0
0
0
Fri Jul 17 2020
Computer Vision
Boundary-preserving Mask R-CNN
BMask R-CNN has a boundary-preserving mask head in which object boundary and mask are mutually learned via feature fusion blocks. As a result, the predicted masks are better aligned with object boundaries. Without bells and whistles, BMaskR-CNN outperforms Mask R- CNN.
0
0
0
Mon Jul 15 2019
Computer Vision
MaskPlus: Improving Mask Generation for Instance Segmentation
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. In this paper, we present an approach that extends Mask R- CNN with five novel optimization techniques.
0
0
0