Semantic Part Segmentation using Compositional Model combining Shape and Appearance

12/18/2014
by   Jianyu Wang, et al.
0

In this paper, we study the problem of semantic part segmentation for animals. This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have similar appearance and highly varying shapes. To tackle these challenges, we build a mixture of compositional models to represent the object boundary and the boundaries of semantic parts. And we incorporate edge, appearance, and semantic part cues into the compositional model. Given part-level segmentation annotation, we develop a novel algorithm to learn a mixture of compositional models under various poses and viewpoints for certain animal classes. Furthermore, a linear complexity algorithm is offered for efficient inference of the compositional model using dynamic programming. We evaluate our method for horse and cow using a newly annotated dataset on Pascal VOC 2010 which has pixelwise part labels. Experimental results demonstrate the effectiveness of our method.

READ FULL TEXT

page 1

page 8

page 9

research
05/26/2021

Unsupervised Part Segmentation through Disentangling Appearance and Shape

We study the problem of unsupervised discovery and segmentation of objec...
research
06/09/2014

Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency

This paper addresses the problem of semantic part parsing (segmentation)...
research
03/28/2017

Objects as context for detecting their semantic parts

We present a semantic part detection approach that effectively leverages...
research
11/29/2021

3D Compositional Zero-shot Learning with DeCompositional Consensus

Parts represent a basic unit of geometric and semantic similarity across...
research
10/31/2022

gCoRF: Generative Compositional Radiance Fields

3D generative models of objects enable photorealistic image synthesis wi...
research
04/24/2015

Situational Object Boundary Detection

Intuitively, the appearance of true object boundaries varies from image ...
research
12/20/2022

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

Large-scale models combining text and images have made incredible progre...

Please sign up or login with your details

Forgot password? Click here to reset