Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

CVPR 2016  ·  Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han ·

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.

PDF Abstract CVPR 2016 PDF CVPR 2016 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Retrieval with Multi-Modal Query Fashion200k Param Hashing Recall@1 12.2 # 5
Recall@10 40 # 5
Recall@50 61.7 # 5

Methods