Enregistré dans:
Détails bibliographiques
Auteur principal: Huang, Feiyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.00095
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910787545595904
author Huang, Feiyang
author_facet Huang, Feiyang
contents In the field of image captioning, the phenomenon where missing or nonexistent objects are used to explain an image is referred to as object bias (or hallucination). To mitigate this issue, we propose a target-aware prompting strategy. This method first extracts object labels and their spatial information from the image using an object detector. Then, an attribute predictor further refines the semantic features of the objects. These refined features are subsequently integrated and fed into the decoder, enhancing the model's understanding of the image context. Experimental results on the COCO and nocaps datasets demonstrate that OPCap effectively mitigates hallucination and significantly improves the quality of generated captions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00095
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OPCap:Object-aware Prompting Captioning
Huang, Feiyang
Computer Vision and Pattern Recognition
In the field of image captioning, the phenomenon where missing or nonexistent objects are used to explain an image is referred to as object bias (or hallucination). To mitigate this issue, we propose a target-aware prompting strategy. This method first extracts object labels and their spatial information from the image using an object detector. Then, an attribute predictor further refines the semantic features of the objects. These refined features are subsequently integrated and fed into the decoder, enhancing the model's understanding of the image context. Experimental results on the COCO and nocaps datasets demonstrate that OPCap effectively mitigates hallucination and significantly improves the quality of generated captions.
title OPCap:Object-aware Prompting Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00095