PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond

05/05/2021
by   Enze Xie, et al.
0

Reducing the complexity of the pipeline of instance segmentation is crucial for real-world applications. This work addresses this issue by introducing an anchor-box free and single-shot instance segmentation framework, termed PolarMask, which reformulates the instance segmentation problem as predicting the contours of objects in the polar coordinate, with several appealing benefits. (1) The polar representation unifies instance segmentation (masks) and object detection (bounding boxes) into a single framework, reducing the design and computational complexity. (2) Two modules are carefully designed (i.e. soft polar centerness and polar IoU loss) to sample high-quality center examples and optimize polar contour regression, making the performance of PolarMask does not depend on the bounding box prediction results and thus becomes more efficient in training. (3) PolarMask is fully convolutional and can be easily embedded into most off-the-shelf detection methods. To further improve the accuracy of the framework, a Refined Feature Pyramid is introduced to further improve the feature representation at different scales, termed PolarMask++. Extensive experiments demonstrate the effectiveness of both PolarMask and PolarMask++, which achieve competitive results on instance segmentation in the challenging COCO dataset with single-model and single-scale training and testing, as well as new state-of-the-art results on rotate text detection and cell segmentation. We hope the proposed polar representation can provide a new perspective for designing algorithms to solve single-shot instance segmentation. The codes and models are available at: github.com/xieenze/PolarMask.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 10

page 11

page 13

research
09/29/2019

PolarMask: Single Shot Instance Segmentation with Polar Representation

In this paper, we introduce an anchor-box free and single shot instance ...
research
03/31/2020

EOLO: Embedded Object Segmentation only Look Once

In this paper, we introduce an anchor-free and single-shot instance segm...
research
08/28/2020

Fast Single-shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images

Object detection and instance segmentation in remote sensing images is a...
research
11/30/2022

Growing Instance Mask on Leaf

Contour-based instance segmentation methods include one-stage and multi-...
research
02/08/2022

SCR: Smooth Contour Regression with Geometric Priors

While object detection methods traditionally make use of pixel-level mas...
research
10/27/2021

SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation

Video object segmentation (VOS) is an essential part of autonomous vehic...
research
07/05/2022

Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation

In this work, we propose PolarBEV for vision-based uneven BEV representa...

Please sign up or login with your details

Forgot password? Click here to reset