Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction

Citations Over TimeTop 1% of 2016 papers

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 Papers

• → Comparative Evaluation of CNN Architectures for Image Caption Generation(2020)36 cited
• → A verifiable multi-secret image sharing scheme using XOR operation and hash function(2020)34 cited
• → Estimation of crowd density in surveillance scenes based on deep convolutional neural network(2017)29 cited
• → Scene Recognition from Image Using Convolutional Neural Network(2020)20 cited
• → CNNA: A study of Convolutional Neural Networks with Attention(2021)2 cited