MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval
Youbo Lei, Feifei He, Chen Chen, Yingbin Mo, Sijia Li, Defeng Xie, Haonan Lu
Abstract
Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device deployment. Single- and dual-stream model structures are commonly used in image-text retrieval with the goal of closing the semantic gap between textual and visual modalities. While single-stream models use deep feature fusion to achieve more accurate cross-model alignment, dual-stream models are better at offline indexing and fast inference. We propose a Multi-teacher Cross-modality Alignment Distillation (MCAD) technique to integrate the advantages of single- and dual-stream models. By incorporating the fused single-stream features into the image and text features of the dual-stream model, we formulate new modified teacher similarity distributions and features. Then, we conduct both distribution and feature distillation to boost the capability of the student dual-stream model, achieving high retrieval performance without increasing inference complexity. Extensive experiments demonstrate the remarkable performance and high efficiency of MCAD on image-text retrieval tasks. Furthermore, we implement a lightweight CLIP model on Snapdragon/Dimensity chips with only ~100M running memory and ~8.0ms search latency, achieving the mobile-device application of VLP models.
BibTeX
@inproceedings{lei-etal-2024-mcad,
title = "{MCAD}: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval",
author = "Lei, Youbo and
He, Feifei and
Chen, Chen and
Mo, Yingbin and
Li, Sijia and
Xie, Defeng and
Lu, Haonan",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.96/",
doi = "10.18653/v1/2024.findings-naacl.96",
pages = "1491--1503"
}