ControlCap: Controllable Region-level Captioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yuzhong, Liu, Yue, Guo, Zonghao, Wu, Weijia, Gong, Chen, Wan, Fang, Ye, Qixiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916154476331008
author Zhao, Yuzhong
Liu, Yue
Guo, Zonghao
Wu, Weijia
Gong, Chen
Wan, Fang
Ye, Qixiang
author_facet Zhao, Yuzhong
Liu, Yue
Guo, Zonghao
Wu, Weijia
Gong, Chen
Wan, Fang
Ye, Qixiang
contents Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the less frequent ones. In this study, we propose a controllable region-level captioning (ControlCap) approach, which introduces control words to a multimodal model to address the caption degeneration issue. In specific, ControlCap leverages a discriminative module to generate control words within the caption space to partition it to multiple sub-spaces. The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue. Furthermore, interactive control words can be given by either a human or an expert model, which enables captioning beyond the training caption space, enhancing the model's generalization ability. Extensive experiments on Visual Genome and RefCOCOg datasets show that ControlCap respectively improves the CIDEr score by 21.6 and 2.2, outperforming the state-of-the-arts by significant margins. Code is available at https://github.com/callsys/ControlCap.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17910
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ControlCap: Controllable Region-level Captioning
Zhao, Yuzhong
Liu, Yue
Guo, Zonghao
Wu, Weijia
Gong, Chen
Wan, Fang
Ye, Qixiang
Computer Vision and Pattern Recognition
Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the less frequent ones. In this study, we propose a controllable region-level captioning (ControlCap) approach, which introduces control words to a multimodal model to address the caption degeneration issue. In specific, ControlCap leverages a discriminative module to generate control words within the caption space to partition it to multiple sub-spaces. The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue. Furthermore, interactive control words can be given by either a human or an expert model, which enables captioning beyond the training caption space, enhancing the model's generalization ability. Extensive experiments on Visual Genome and RefCOCOg datasets show that ControlCap respectively improves the CIDEr score by 21.6 and 2.2, outperforming the state-of-the-arts by significant margins. Code is available at https://github.com/callsys/ControlCap.
title ControlCap: Controllable Region-level Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.17910