Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge

TL;DR

This paper discusses a deep recurrent model for image captioning, trained on COCO dataset, achieving high accuracy and fluency, and winning the 2015 MSCOCO challenge with open-source code.

Contribution

It introduces a generative deep recurrent architecture for image captioning, combining vision and language advances, and provides insights from the 2015 MSCOCO challenge.

Findings

Model achieves high accuracy in image captioning.

The approach produces fluent and relevant descriptions.

The team won the 2015 MSCOCO challenge and released open-source code.

Abstract

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. Our model is often quite accurate, which we verify both qualitatively and quantitatively. Finally, given the recent surge of interest in this task, a competition was organized in 2015 using the newly released COCO dataset. We describe and analyze the various improvements we applied to our own baseline and show the resulting performance in the competition, which we won ex-aequo with a team from Microsoft Research, and provide an open source implementation in TensorFlow.