Attention on Attention: Architectures for Visual Question Answering (VQA)

03/21/2018

∙

by   Jasdeep Singh, et al.

∙

0

∙

share

Visual Question Answering (VQA) is an increasingly popular topic in deep learning research, requiring coordination of natural language processing and computer vision modules into a single architecture. We build upon the model which placed first in the VQA Challenge by developing thirteen new attention mechanisms and introducing a simplified classifier. We performed 300 GPU hours of extensive hyperparameter and architecture searches and were able to achieve an evaluation score of 64.78 single model's validation score of 63.15