Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention
This work addresses the challenge of improving image captioning accuracy by integrating saliency data, offering a domain-specific advancement for computer vision applications.
The authors tackled the problem of incorporating saliency information into image captioning by proposing a model that uses saliency prediction to guide attention during caption generation, achieving superior performance compared to baselines and state-of-the-art methods on large-scale datasets.
Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Even though saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, research is still struggling to incorporate these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are contextual. We show, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to captioning baselines with and without saliency, and to different state of the art approaches combining saliency and captioning.