Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach

TL;DR

This paper introduces a semi-supervised learning framework for image captioning that effectively utilizes unpaired images and captions through adversarial training, reducing the need for extensive labeled datasets.

Contribution

A novel adversarial semi-supervised approach that leverages unpaired data for image captioning, improving performance with limited paired samples.

Findings

Outperforms strong baselines with scarce paired data

Effective use of unpaired images and captions via GANs

Constructed scarcely-paired COCO dataset for evaluation

Abstract

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences separately may be immensely easier. In this paper, we develop a novel data-efficient semi-supervised framework for training an image captioning model. We leverage massive unpaired image and caption data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption. To evaluate, we construct scarcely-paired COCO dataset, a modified version of MS COCO caption dataset. The empirical results show the effectiveness of our method compared to several strong baselines, especially when the amount of the paired samples are scarce.