Convolutional Image Captioning

TL;DR

This paper introduces a convolutional approach to image captioning, demonstrating comparable performance to LSTM-based models but with faster training times, and provides analysis supporting convolutional methods for language generation.

Contribution

The paper presents a novel convolutional neural network architecture for image captioning, offering faster training and competitive accuracy compared to traditional LSTM-based models.

Findings

Convolutional image captioning achieves performance on par with LSTM models.

The convolutional approach trains faster per parameter.

Analysis favors convolutional methods for language generation tasks.

Abstract

Image captioning is an important but challenging task, applicable to virtual assistants, editing tools, image indexing, and support of the disabled. Its challenges are due to the variability and ambiguity of possible image descriptions. In recent years significant progress has been made in image captioning, using Recurrent Neural Networks powered by long-short-term-memory (LSTM) units. Despite mitigating the vanishing gradient problem, and despite their compelling ability to memorize dependencies, LSTM units are complex and inherently sequential across time. To address this issue, recent work has shown benefits of convolutional networks for machine translation and conditional image generation. Inspired by their success, in this paper, we develop a convolutional image captioning technique. We demonstrate its efficacy on the challenging MSCOCO dataset and demonstrate performance on par with the baseline, while having a faster training time per number of parameters. We also perform a detailed analysis, providing compelling reasons in favor of convolutional language generation approaches.