Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3864-3872
DOI: 10.1609/aaai.v38i4.28178 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zhiyue Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).
Abstract (Originalsprache)
Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the CLIP's cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. However, not only does a modality gap exist between CLIP text and image features, but a discrepancy also arises between training and inference due to the unavailability of real-world images, which hinders the cross-modal alignment in text-only captioning. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space. Furthermore, textual information is gathered to represent image features, resulting in the image features with various semantics and the bridged modality gap. To unify training and inference, synthetic image features would serve as the training prefix for the language decoder, while real images are used for inference. Additionally, salient objects in images are detected as assistance to enhance the learning of modality alignment. Experimental results demonstrate that our method obtains the state-of-the-art performance on benchmark datasets.
Zitieren
APA
Liu, Z., Liu, J., & Ma, F. (2024). Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3864-3872. https://doi.org/10.1609/aaai.v38i4.28178
Vancouver
Liu Z, Liu J, Ma F. Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3864-3872. doi:10.1609/aaai.v38i4.28178
BibTeX
@article{Liu2024,
author = {Liu, Zhiyue and Liu, Jinyuan and Ma, Fanrong},
title = {Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {3864--3872},
doi = {10.1609/aaai.v38i4.28178}
}
EUVIMED