Distincive Image Captioning via CLIP Guided Group Optimization. (arXiv:2208.04254v2 [cs.CV] UPDATED)

Image captioning models are usually trained according to human annotated
ground-truth captions, which could generate accurate but generic captions. In
this paper, we focus on generating the distinctive captions that can
distinguish the target image from other similar images. To evaluate the
distinctiveness of captions, we introduce a series of metrics that use
large-scale vision-language pre-training model CLIP to quantify the
distinctiveness. To further improve the distinctiveness of captioning models,
we propose a simple and effective training strategy which trains …

arxiv captioning clip cv image optimization