Pixelwise Instance Segmentation with a Dynamically Instantiated Network

04/07/2017
by   Anurag Arnab, et al.
0

Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose an Instance Segmentation system that produces a segmentation map where each pixel is assigned an object class and instance identity label. Most approaches adapt object detectors to produce segments instead of boxes. In contrast, our method is based on an initial semantic segmentation module, which feeds into an instance subnetwork. This subnetwork uses the initial category-level segmentation, along with cues from the output of an object detector, within an end-to-end CRF to predict instances. This part of our model is dynamically instantiated to produce a variable number of instances per image. Our end-to-end approach requires no post-processing and considers the image holistically, instead of processing independent proposals. Therefore, unlike some related work, a pixel cannot belong to multiple instances. Furthermore, far more precise segmentations are achieved, as shown by our state-of-the-art results (particularly at high IoU thresholds) on the Pascal VOC and Cityscapes datasets.

READ FULL TEXT

page 2

page 12

page 13

page 14

page 15

page 16

page 17

page 19

research
09/08/2016

Bottom-up Instance Segmentation using Deep Higher-Order CRFs

Traditional Scene Understanding problems such as Object Detection and Se...
research
09/09/2015

Proposal-free Network for Instance-level Object Segmentation

Instance-level object segmentation is an important yet under-explored ta...
research
09/11/2017

Holistic, Instance-Level Human Parsing

Object parsing -- the task of decomposing an object into its semantic pa...
research
07/07/2014

Simultaneous Detection and Segmentation

We aim to detect all instances of a category in an image and, for each i...
research
09/23/2017

Semi-Supervised Hierarchical Semantic Object Parsing

Models based on Convolutional Neural Networks (CNNs) have been proven ve...
research
11/24/2016

Deep Watershed Transform for Instance Segmentation

Most contemporary approaches to instance segmentation use complex pipeli...
research
03/12/2019

An End-to-End Network for Panoptic Segmentation

Panoptic segmentation, which needs to assign a category label to each pi...

Please sign up or login with your details

Forgot password? Click here to reset