Distance to Center of Mass Encoding for Instance Segmentation

Abstract

The instance segmentation can be considered an extension of the object detection problem where bounding boxes are replaced by object contours. Strictly speaking the problem requires to identify each pixel instance and class independently of the artifice used for this mean. The advantage of instance segmentation over the usual object detection lies in the precise delineation of objects improving object localization. Additionally, object contours allow the evaluation of partial occlusion with basic image processing algorithms. This work approaches the instance segmentation problem as an annotation problem and presents a novel technique to encode and decode ground truth annotations. We propose a mathematical representation of instances that any deep semantic segmentation model can learn and generalize. Each individual instance is represented by a center of mass and a field of vectors pointing to it. This encoding technique has been denominated Distance to Center of Mass Encoding (DCME).

References in corpus (8)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Semantic Instance Segmentation with a Discriminative Loss Function
• Proposal-free Network for Instance-level Object Segmentation
• Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
• Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
• Monocular Object Instance Segmentation and Depth Ordering with CNNs

Cited by in corpus (2)

• Transformer Assisted Convolutional Network for Cell Instance Segmentation
• Bounding Box Embedding for Single Shot Person Instance Segmentation