Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content

Published: 19 Mar 2024, Last Modified: 17 May 2024Tiny Papers @ ICLR 2024 PresentEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Image-captioning, Multimodal learning, Computer vision
TL;DR: Image Captioning models effectively generate captions from masked visual content.
Abstract: This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to generate captions from masked images, closely resembling the original content. Notably, even in the presence of masks, the model adeptly crafts descriptive textual information that goes beyond what is observable in the original image-generated captions. While the decoding performance of the IC model experiences a decline with an increase in the masked region's area, the model still performs well when important regions of the image are not masked at high coverage.
Submission Number: 146