Fusion Models for Improved Visual Captioning

Abstract: 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. LLMs 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 LLM (AuxLM) within the traditional encoder-decoder visual captioning frameworks. Next, we employ the same fusion strategies to integrate a pretrained Masked LLM (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.