Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks

DOI10.1109/TIP.2016.2548241zbMATH Open1408.94857arXiv1509.03877WikidataQ39004608 ScholiaQ39004608MaRDI QIDQ4616507

Author name not available (Why is that?)

Publication date: 4 February 2019

Published in: (Search for Journal in Brave)

Abstract: Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the dependencies among different image regions. However, such dependencies are very important for generating explicit image representation. In contrast, recurrent neural networks (RNNs) are well known for their ability of encoding contextual information among sequential data, and they only require a limited number of network parameters. General RNNs can hardly be directly applied on non-sequential data. Thus, we proposed the hierarchical RNNs (HRNNs). In HRNNs, each RNN layer focuses on modeling spatial dependencies among image regions from the same scale but different locations. While the cross RNN scale connections target on modeling scale dependencies among regions from the same location but different scales. Specifically, we propose two recurrent neural network models: 1) hierarchical simple recurrent network (HSRN), which is fast and has low computational cost; and 2) hierarchical long-short term memory recurrent network (HLSTM), which performs better than HSRN with the price of more computational cost. In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs). C-HRNNs not only make use of the representation power of CNNs, but also efficiently encodes spatial and scale dependencies among different image regions. On four of the most challenging object/scene image classification benchmarks, our C-HRNNs achieve state-of-the-art results on Places 205, SUN 397, MIT indoor, and competitive results on ILSVRC 2012.

Full work available at URL: https://arxiv.org/abs/1509.03877

Mathematics Subject Classification ID

No records found.

This page was built for publication: Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4616507)