Holistic, Instance-Level Human Parsing

09/11/2017
by   Qizhu Li, et al.
0

Object parsing -- the task of decomposing an object into its semantic parts -- has traditionally been formulated as a category-level segmentation problem. Consequently, when there are multiple objects in an image, current methods cannot count the number of objects in the scene, nor can they determine which part belongs to which object. We address this problem by segmenting the parts of objects at an instance-level, such that each pixel in the image is assigned a part label, as well as the identity of the object it belongs to. Moreover, we show how this approach benefits us in obtaining segmentations at coarser granularities as well. Our proposed network is trained end-to-end given detections, and begins with a category-level segmentation module. Thereafter, a differentiable Conditional Random Field, defined over a variable number of instances for every input image, reasons about the identity of each part by associating it with a human detection. In contrast to other approaches, our method can handle the varying number of people in each image and our holistic network produces state-of-the-art results in instance-level part and human segmentation, together with competitive results in category-level part segmentation, all achieved by a single forward-pass through our neural network.

READ FULL TEXT

page 6

page 10

page 14

page 15

page 16

page 17

page 18

page 19

research
04/07/2017

Pixelwise Instance Segmentation with a Dynamically Instantiated Network

Semantic segmentation and object detection research have recently achiev...
research
09/08/2016

Bottom-up Instance Segmentation using Deep Higher-Order CRFs

Traditional Scene Understanding problems such as Object Detection and Se...
research
03/12/2019

An End-to-End Network for Panoptic Segmentation

Panoptic segmentation, which needs to assign a category label to each pi...
research
07/08/2020

A Multi-Level Approach to Waste Object Segmentation

We address the problem of localizing waste objects from a color image an...
research
02/10/2012

Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

Scene parsing, or semantic segmentation, consists in labeling each pixel...
research
08/18/2016

A Holistic Approach for Data-Driven Object Cutout

Object cutout is a fundamental operation for image editing and manipulat...
research
09/23/2017

Semi-Supervised Hierarchical Semantic Object Parsing

Models based on Convolutional Neural Networks (CNNs) have been proven ve...

Please sign up or login with your details

Forgot password? Click here to reset