Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
This addresses the labor-intensive challenge of collecting large paired datasets for image captioning, benefiting researchers and practitioners in computer vision and NLP by reducing data requirements.
The paper tackles the problem of training image captioning models with very scarce supervised data by proposing a novel semi-supervised framework that leverages unpaired images and captions using adversarial learning to associate them. The method shows effectiveness on a modified COCO dataset, outperforming strong baselines when paired samples are limited.
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.