PolarMask: Single Shot Instance Segmentation with Polar Representation

Abstract

In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on challenging COCO dataset. For the first time, we demonstrate a much simpler and flexible instance segmentation framework achieving competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation tasks. Code is available at: github.com/xieenze/PolarMask.

Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition 2020

References in corpus (5)

• FCOS: Fully Convolutional One-Stage Object Detection
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• TensorMask: A Foundation for Dense Object Segmentation

Cited by in corpus (19)

• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
• SOLO: Segmenting Objects by Locations
• EmbedMask: Embedding Coupling for One-stage Instance Segmentation
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
• SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
• Dense RepPoints: Representing Visual Objects with Dense Point Sets
• Learning Dynamic Alignment via Meta-filter for Few-shot Learning
• Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• IoU-aware Single-stage Object Detector for Accurate Localization
• MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• CenterMask: single shot instance segmentation with point representation
• TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
• Real-Time Panoptic Segmentation from Dense Detections
• SAIS: Single-stage Anchor-free Instance Segmentation
• Human-centric Relation Segmentation: Dataset and Solution
• S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
• Fast Single-shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images