Image Captioning based on Deep Reinforcement Learning
This addresses the challenging problem of generating diverse and accurate natural language descriptions for images, which is incremental as it builds on existing sequential models like RNNs.
The paper tackles image captioning by proposing a novel architecture using deep reinforcement learning with policy and value networks, achieving verified effectiveness on the Microsoft COCO dataset.
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.