Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech
This addresses the challenge of ambiguous image captioning for applications requiring varied and precise descriptions, though it is incremental as it builds on existing methods like beam search and VAE/GAN approaches.
The paper tackles the problem of generating multiple diverse and accurate captions for images by using part-of-speech summaries to guide caption generation, achieving high accuracy, faster computation than beam search, and high diversity as measured by metrics like novel sentences and mBleu-4 scores.
Image captioning is an ambiguous problem, with many suitable captions for an image. To address ambiguity, beam search is the de facto method for sampling multiple captions. However, beam search is computationally expensive and known to produce generic captions. To address this concern, some variational auto-encoder (VAE) and generative adversarial net (GAN) based methods have been proposed. Though diverse, GAN and VAE are less accurate. In this paper, we first predict a meaningful summary of the image, then generate the caption based on that summary. We use part-of-speech as summaries, since our summary should drive caption generation. We achieve the trifecta: (1) High accuracy for the diverse captions as evaluated by standard captioning metrics and user studies; (2) Faster computation of diverse captions compared to beam search and diverse beam search; and (3) High diversity as evaluated by counting novel sentences, distinct n-grams and mutual overlap (i.e., mBleu-4) scores.