Learning Sparse Mixture of Experts for Visual Question Answering
arXiv:1909.09192
Abstract
There has been a rapid progress in the task of Visual Question Answering with improved model architectures. Unfortunately, these models are usually computationally intensive due to their sheer size which poses a serious challenge for deployment. We aim to tackle this issue for the specific task of Visual Question Answering (VQA). A Convolutional Neural Network (CNN) is an integral part of the visual processing pipeline of a VQA model (assuming the CNN is trained along with entire VQA model). In this project, we propose an efficient and modular neural architecture for the VQA task with focus on the CNN module. Our experiments demonstrate that a sparsely activated CNN based VQA model achieves comparable performance to a standard CNN based VQA model architecture.
arXiv commentAccepted in Visual Question Answering and Dialog Workshop, CVPR 2019
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
- Multi-Scale Dense Networks for Resource Efficient Image Classification
- Conditional Computation in Neural Networks for faster models
- Modularity Matters: Learning Invariant Relational Reasoning Tasks