A Probabilistic Associative Model for Segmenting Weakly Supervised Images

Weakly supervised image segmentation is an important yet challenging task in image processing and pattern recognition fields. It is defined as: in the training stage, semantic labels are only at the image-level, without regard to their specific object/scene location within the image. Given a test im...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 23; no. 9; pp. 4150 - 4159
Main Authors: Zhang, Luming, Yang, Yi, Gao, Yue, Yu, Yi, Wang, Changbo, Li, Xuelong
Format: Journal Article
Language:English
Published: United States IEEE 01.09.2014
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Bayesian analysis
Computational modeling
Context
Image processing
Image segmentation
Labels
Manifolds
Mathematical models
Networks
Optimization
Semantics
Vectors
associations
segmentation
Probabilistic model
weakly-supervised
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Weakly supervised image segmentation is an important yet challenging task in image processing and pattern recognition fields. It is defined as: in the training stage, semantic labels are only at the image-level, without regard to their specific object/scene location within the image. Given a test image, the goal is to predict the semantics of every pixel/superpixel. In this paper, we propose a new weakly supervised image segmentation model, focusing on learning the semantic associations between superpixel sets (graphlets in this paper). In particular, we first extract graphlets from each image, where a graphlet is a small-sized graph measures the potential of multiple spatially neighboring superpixels (i.e., the probability of these superpixels sharing a common semantic label, such as the sky or the sea). To compare different-sized graphlets and to incorporate image-level labels, a manifold embedding algorithm is designed to transform all graphlets into equal-length feature vectors. Finally, we present a hierarchical Bayesian network to capture the semantic associations between postembedding graphlets, based on which the semantics of each superpixel is inferred accordingly. Experimental results demonstrate that: 1) our approach performs competitively compared with the state-of-the-art approaches on three public data sets and 2) considerable performance enhancement is achieved when using our approach on segmentation-based photo cropping and image categorization.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2014.2344433