Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Soeun, Kim, Si-Woo, Kim, Taewhan, Kim, Dong-Jin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2409.18046
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910621448011776
author Lee, Soeun
Kim, Si-Woo
Kim, Taewhan
Kim, Dong-Jin
author_facet Lee, Soeun
Kim, Si-Woo
Kim, Taewhan
Kim, Dong-Jin
contents Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between using text data during training and employing images during inference. To address this issue, we propose a novel approach called Image-like Retrieval, which aligns text features with visually relevant features to mitigate the modality gap. Our method further enhances the accuracy of generated captions by designing a Fusion Module that integrates retrieved captions with input features. Additionally, we introduce a Frequency-based Entity Filtering technique that significantly improves caption quality. We integrate these methods into a unified framework, which we refer to as IFCap ($\textbf{I}$mage-like Retrieval and $\textbf{F}$requency-based Entity Filtering for Zero-shot $\textbf{Cap}$tioning). Through extensive experimentation, our straightforward yet powerful approach has demonstrated its efficacy, outperforming the state-of-the-art methods by a significant margin in both image captioning and video captioning compared to zero-shot captioning based on text-only training.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18046
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
Lee, Soeun
Kim, Si-Woo
Kim, Taewhan
Kim, Dong-Jin
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between using text data during training and employing images during inference. To address this issue, we propose a novel approach called Image-like Retrieval, which aligns text features with visually relevant features to mitigate the modality gap. Our method further enhances the accuracy of generated captions by designing a Fusion Module that integrates retrieved captions with input features. Additionally, we introduce a Frequency-based Entity Filtering technique that significantly improves caption quality. We integrate these methods into a unified framework, which we refer to as IFCap ($\textbf{I}$mage-like Retrieval and $\textbf{F}$requency-based Entity Filtering for Zero-shot $\textbf{Cap}$tioning). Through extensive experimentation, our straightforward yet powerful approach has demonstrated its efficacy, outperforming the state-of-the-art methods by a significant margin in both image captioning and video captioning compared to zero-shot captioning based on text-only training.
title IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2409.18046