Research Area:  Machine Learning

Abstract:

Recently it has shown that the policy-gradient methods for reinforcement learning have been utilized to train deep end-to-end systems on natural language processing tasks. What-s more, with the complexity of understanding image content and diverse ways of describing image content in natural language, image captioning has been a challenging problem to deal with. To the best of our knowledge, most state-of-the-art methods follow a pattern of sequential model, such as recurrent neural networks (RNN). However, in this paper, we propose a novel architecture for image captioning with deep reinforcement learning to optimize image captioning tasks. We utilize two networks called "policy network" and "value network" to collaboratively generate the captions of images. The experiments are conducted on Microsoft COCO dataset, and the experimental results have verified the effectiveness of the proposed method.

Keywords:  
Image Captioning
Deep Reinforcement Learning
Machine Learning
Deep Learning

Author(s) Name:  Haichao Shi , Peng Li , Bo Wang , Zhenyu Wang

Publisher name:  ACM

DOI:  10.1145/3240876.3240900

Volume Information:  Article No.: 45,Pages 1–5

Paper Link:   https://dl.acm.org/doi/abs/10.1145/3240876.3240900