0

Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception

DCE enhances image captions by integrating attributes and relationships from pretrained visual specialists, improving visual understanding and reasoning tasks.

Year
2024
Venue
arXiv 2024
Authors
9
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2412.14233v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods either distill the caption from the LMM models or construct the captions from the internet images or by human. We propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named DCE, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. We will release the source code and the pipeline so that other visual specialists are easily combined into the pipeline. The complete source code of DCE pipeline and datasets will be available at \url{https://github.com/syp2ysy/DCE}.

Authors

9