Single Pixel Reconstruction for One-stage Instance Segmentation

04/16/2019
by   Jinghan Yao, et al.
0

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 to RetinaNet.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

research
03/26/2020

Mask Encoding for Single Shot Instance Segmentation

To date, instance segmentation is dominated by twostage methods, as pion...
research
05/01/2023

Event Camera as Region Proposal Network

The human eye consists of two types of photoreceptors, rods and cones. R...
research
11/15/2019

CenterMask : Real-Time Anchor-Free Instance Segmentation

We propose a simple yet efficient anchor-free instance segmentation, cal...
research
12/04/2019

EmbedMask: Embedding Coupling for One-stage Instance Segmentation

Current instance segmentation methods can be categorized into segmentati...
research
06/18/2021

A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation

Boundary-based instance segmentation has drawn much attention since of i...
research
12/02/2020

Learning Universal Shape Dictionary for Realtime Instance Segmentation

We present a novel explicit shape representation for instance segmentati...
research
03/13/2020

PointINS: Point-based Instance Segmentation

A single-point feature has shown its effectiveness in object detection. ...

Please sign up or login with your details

Forgot password? Click here to reset