Fusion Models for Improved Visual Captioning
This work addresses the issue of error-prone visual captioning for applications like accessibility tools, though it is incremental as it builds on existing fusion techniques and models.
The authors tackled the problem of limited generalization in visual captioning models by proposing a multimodal fusion framework that integrates pretrained language models like BERT to correct errors in generated captions, showing improvements on benchmark datasets such as Flickr8k, Flickr30k, and MSCOCO.
Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This limitation hinders the generalization capabilities of these models while also rendering them liable to making mistakes. Language models can, however, be trained on vast amounts of freely available unlabelled data and have recently emerged as successful language encoders and coherent text generators. Meanwhile, several unimodal and multimodal fusion techniques have been proven to work well for natural language generation and automatic speech recognition. Building on these recent developments, and with the aim of improving the quality of generated captions, the contribution of our work in this paper is two-fold: First, we propose a generic multimodal model fusion framework for caption generation as well as emendation where we utilize different fusion strategies to integrate a pretrained Auxiliary Language Model (AuxLM) within the traditional encoder-decoder visual captioning frameworks. Next, we employ the same fusion strategies to integrate a pretrained Masked Language Model (MLM), namely BERT, with a visual captioning model, viz. Show, Attend, and Tell, for emending both syntactic and semantic errors in captions. Our caption emendation experiments on three benchmark image captioning datasets, viz. Flickr8k, Flickr30k, and MSCOCO, show improvements over the baseline, indicating the usefulness of our proposed multimodal fusion strategies. Further, we perform a preliminary qualitative analysis on the emended captions and identify error categories based on the type of corrections.