Single Pixel Reconstruction for One-stage Instance Segmentation

Abstract

Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a two-stage object detector with the Region Proposal Network (RPN). Although producing good segmentation results, the efficiency of these two-stage approaches is far from satisfactory, restricting their applicability in practice. In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors. The added SPR branch reconstructs the pixel-level mask from every single pixel in the convolution feature map directly. Using the same ResNet-50 backbone, SPRNet achieves comparable mask AP to Mask R-CNN at a higher inference speed, and gains all-round improvements on box AP at every scale comparing with RetinaNet.

References in corpus (5)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DSSD : Deconvolutional Single Shot Detector
• Learning to Segment Object Candidates
• Beyond Skip Connections: Top-Down Modulation for Object Detection

Cited by in corpus (4)

• Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
• Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
• Visual Perception and Modelling in Unstructured Orchard for Apple Harvesting Robots
• SAIS: Single-stage Anchor-free Instance Segmentation