logo
banner

Journals & Publications

Journals Publications Papers

Papers

A Discriminative Graph Inferring Framework towards Weakly Supervised Image Parsing
Mar 29, 2017Author:
PrintText Size A A

Title: A Discriminative Graph Inferring Framework towards Weakly Supervised Image Parsing  

Authors: Yu, L; Bao, BK; Xu, CS 

Author Full Names: Yu, Lei; Bao, Bing-Kun; Xu, Changsheng 

Source: MULTIMEDIA SYSTEMS, 23 (1):5-18; SI 10.1007/s00530-015-0458-5 FEB 2017  

Language: English 

Abstract: In this paper, we focus on the task of assigning labels to the over-segmented image patches in a weakly supervised manner, in which the training images contain the labels but do not have the labels' locations in the images. We propose a unified discriminative graph inferring framework by simultaneously inferring patch labels and learning the patch appearance models. On one hand, graph inferring reasons the patch labels by a graph propagation procedure. The graph is constructed by connecting the nearest neighbors which share the same image label, and multiple correlations among patches and image labels are imposed as constraints to the inferring. On the other hand, for each label, the patches which do not contain the target label are adopted as negative samples to learn the appearance model. In this way, the predicted labels will be more accurate in the propagation. Graph inferring and the learned patch appearance models are finally embedded to complement each other in one unified formulation. Experiments on three public datasets demonstrate the effectiveness of our method in comparison with other baselines. 

ISSN: 0942-4962  

eISSN: 1432-1882  

IDS Number: EK2LP  

Unique ID: WOS:000393759100002 

 

*Click Here to View Full Record