Journal
NEURAL NETWORKS
Volume 105, Issue -, Pages 356-370Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2018.05.009
Keywords
Detrending; Normalization; Internal covariate shift; Convolutional neural networks (CNNs); Recurrent neural networks (RNNs); Convolutional recurrent neural networks (ConvRNNs)
Funding
- National Research Foundation of Korea (NRF) - Korea government (MSIP) [2014R1A2A2A01005491]
- Okinawa Institute of Science and Technology Graduate University, Japan
Ask authors/readers for more resources
Video image recognition has been extensively studied with rapid progress recently. However, most methods focus on short-term rather than long-term (contextual) video recognition. Convolutional recurrent neural networks (ConvRNNs) provide robust spatio-temporal information processing capabilities for contextual video recognition, but require extensive computation that slows down training. Inspired by normalization and detrending methods, in this paper we propose adaptive detrending'' (AD) for temporal normalization in order to accelerate the training of ConvRNNs, especially of convolutional gated recurrent unit (ConvGRU). For each neuron in a recurrent neural network (RNN), AD identifies the trending change within a sequence and subtracts it, removing the internal covariate shift. In experiments testing for contextual video recognition with ConvGRU, results show that (1) ConvGRU clearly outperforms feed-forward neural networks, (2) AD consistently and significantly accelerates training and improves generalization, (3) performance is further improved when AD is coupled with other normalization methods, and most importantly, (4) the more long-term contextual information is required, the more AD outperforms existing methods. (c) 2018 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available