Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

HADA: A graph-based amalgamation framework in image-text retrieval

Nguyen, Manh-Duy orcid logoORCID: 0000-0001-6878-7039, Nguyen, Thanh Binh orcid logoORCID: 0000-0001-5249-9702 and Gurrin, Cathal orcid logoORCID: 0000-0003-2903-3968 (2023) HADA: A graph-based amalgamation framework in image-text retrieval. In: European Conference on Information Retrieval (ECIR 2023), 2-6 Apr 2023, Dublin, Ireland. ISBN 978-3-031-28243-0

Abstract
Many models have been proposed for vision and language tasks, especially the image-text retrieval task. State-of-the-art (SOTA) models in this challenge contain hundreds of millions of parameters. They also were pretrained on large external datasets that have been proven to significantly improve overall performance. However, it is not easy to propose a new model with a novel architecture and intensively train it on a massive dataset with many GPUs to surpass many SOTA models already available to use on the Internet. In this paper, we propose a compact graph-based framework named HADA, which can combine pretrained models to produce a better result rather than starting from scratch. Firstly, we created a graph structure in which the nodes were the features extracted from the pretrained models and the edges connecting them. The graph structure was employed to capture and fuse the information from every pretrained model. Then a graph neural network was applied to update the connection between the nodes to get the representative embedding vector for an image and text. Finally, we employed cosine similarity to match images with their relevant texts and vice versa to ensure a low inference time. Our experiments show that, although HADA contained a tiny number of trainable parameters, it could increase baseline performance by more than 3.6% in terms of evaluation metrics on the Flickr30k dataset. Additionally, the proposed model did not train on any external dataset and only required a single GPU to train due to the small number of parameters required. The source code is available at https://github.com/m2man/HADA.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Image-text retrieval; Graph neural network; Fusion model
Subjects:Computer Science > Artificial intelligence
Computer Science > Information retrieval
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Kamps, Jaap, Goeuriot, Lorraine, Crestani, Fabio, Maistro, Maria, Joho, Hideo, Davis, Brian, Gurrin, Cathal, Kruschwitz, Udo and Caputo, Annalina, (eds.) Advances in Information Retrieval. Lecture Notes in Computer Science 13980. Springer. ISBN 978-3-031-28243-0
Publisher:Springer
Official URL:https://doi.org/10.1007/978-3-031-28244-7_45
Copyright Information:© 2023 The Authors
Funders:Science Foundation Ireland grant number SFI/12/RC/2289, Science Foundation Ireland grant number SFI/13/RC/2106, Science Foundation Ireland grant number 18/CRT/6223
ID Code:28883
Deposited On:08 Aug 2023 10:00 by Manh Duy Nguyen . Last Modified 08 Aug 2023 10:29
Documents

Full text available as:

[thumbnail of 978-3-031-28244-7_45.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial 4.0
951kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record