Learning Structured Inference Neural Networks With Label Relations

Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2960-2968

Abstract


Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels that depict high level abstraction or a set of labels that reveal attributes. Such categorization at different concept layers can be modeled with label graphs encoding label information. In this paper, we exploit this rich information with a state-of-art deep learning framework, and propose a generic structured model that leverages diverse label relations to improve image classification performance. Our approach employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. We evaluate our method on benchmark image datasets, and empirical results illustrate the efficacy of our model.

Related Material


[pdf]
[bibtex]
@InProceedings{Hu_2016_CVPR,
author = {Hu, Hexiang and Zhou, Guang-Tong and Deng, Zhiwei and Liao, Zicheng and Mori, Greg},
title = {Learning Structured Inference Neural Networks With Label Relations},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}