Deconfounded Image Captioning: A Causal Retrospect

Cited by: 9|Bibtex|Views75
Other Links: arxiv.org

Abstract:

The dataset bias in vision-language tasks is becoming one of the main problems that hinder the progress of our community. However, recent studies lack a principled analysis of the bias. In this paper, we present a novel perspective: Deconfounded Image Captioning (DIC), to find out the cause of the bias in image captioning, then retrospe...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments