Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
This addresses the image question answering problem for AI systems by providing an incremental improvement in adapting model parameters to questions.
The authors tackled image question answering by introducing a CNN with a dynamic parameter layer whose weights are adaptively predicted based on questions, using a parameter prediction network with a hashing technique to reduce complexity. The method achieved state-of-the-art performance on all available public ImageQA benchmarks.
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.