Modulated Self-attention Convolutional Network for VQA

10/08/2019
by   Jean-Benoit Delbrouck, et al.
0

As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training. This small contribution aims to suggest new ideas to improve the visual processing of traditional convolutional network for visual question answering (VQA). In this paper, we propose to modulate by a linguistic input a CNN augmented with self-attention. We show encouraging relative improvements for future research in this direction.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset