Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction

*Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han*; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 30-38

**Abstract**

We tackle image question answering (ImageQA) problem by learning a convolutional neural network (CNN) with a dynamic parameter layer whose weights are determined adaptively based on questions. For the adaptive parameter prediction, we employ a separate parameter prediction network, which consists of gated recurrent unit (GRU) taking a question as its input and a fully-connected layer generating a set of candidate weights as its output. However, it is challenging to construct a parameter prediction network for a large number of parameters in the fully-connected dynamic parameter layer of the CNN. We reduce the complexity of this problem by incorporating a hashing technique, where the candidate weights given by the parameter prediction network are selected using a predefined hash function to determine individual weights in the dynamic parameter layer. The proposed network---joint network with the CNN for ImageQA and the parameter prediction network---is trained end-to-end through back-propagation, where its weights are initialized using a pre-trained CNN and GRU. The proposed algorithm illustrates the state-of-the-art performance on all available public ImageQA benchmarks.

**Related Material**

[pdf]
[

bibtex]

@InProceedings{Noh_2016_CVPR,

author = {Noh, Hyeonwoo and Hongsuck Seo, Paul and Han, Bohyung},

title = {Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction},

booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},

month = {June},

year = {2016}

}