申请试用
HOT
登录
注册
 
Andreas Neural Module Networks

Andreas Neural Module Networks

Reboot
/
发布于
/
1745
人观看
Visual question answering is fundamentally compositional in nature—a question like where is the dog? shares sub-structure with questions like what color is the dog? and where is the cat? This paper seeks to simultaneously exploit the representational capacity of deep networks and the compositional linguistic structure of questions. We describe a procedure for constructing and learning neural module networks, which compose collections of jointly-trained neural “modules” into deep networks for question answering. Our approach decomposes questions into their linguistic sub-structures, and uses these structures to dynamically instantiate modular networks (with reusable components for recognizing dogs, classifying colors, etc.). The resulting compound networks are jointly trained. We evaluate our approach on two challenging datasets for visual question answering, achieving state-of-the-art results on both the VQA natural image dataset and a new dataset of complex questions about abstract shapes.
0 点赞
0 收藏
0下载
相关文档
确认
3秒后跳转登录页面
去登陆