Review Networks for Caption Generation
This work addresses caption generation for applications like image and code understanding, but it is incremental as it extends existing encoder-decoder frameworks.
The authors tackled the problem of improving encoder-decoder models for caption generation by proposing a review network that performs multiple attention steps on encoder hidden states, resulting in enhanced performance on image and source code captioning tasks.
We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoder- decoder model: in this paper, we consider RNN decoders with both CNN and RNN encoders. The review network performs a number of review steps with attention mechanism on the encoder hidden states, and outputs a thought vector after each review step; the thought vectors are used as the input of the attention mechanism in the decoder. We show that conventional encoder-decoders are a special case of our framework. Empirically, we show that our framework improves over state-of- the-art encoder-decoder systems on the tasks of image captioning and source code captioning.