Nearest Neighbor Normalization Improves Multimodal Retrieval
Neil Chowdhury, Franklin Wang, Sumedh Shenoy, Douwe Kiela, Sarah Schwettmann, Tristan Thrush
Abstract
Multimodal models leverage large-scale pretraining to achieve strong but still imperfect performance on tasks such as image captioning, visual question answering, and cross-modal retrieval. In this paper, we present a simple and efficient method for correcting errors in trained contrastive image-text retrieval models with no additional training, called Nearest Neighbor Normalization (NNN). We show an improvement on retrieval metrics in both text retrieval and image retrieval for all of the contrastive models that we tested (CLIP, BLIP, ALBEF, SigLIP, BEiT) and for both of the datasets that we used (MS-COCO and Flickr30k). NNN requires a reference database, but does not require any training on this database, and can even increase the retrieval accuracy of a model after finetuning.
BibTeX
@inproceedings{chowdhury-etal-2024-nearest,
title = "Nearest Neighbor Normalization Improves Multimodal Retrieval",
author = "Chowdhury, Neil and
Wang, Franklin and
Shenoy, Sumedh and
Kiela, Douwe and
Schwettmann, Sarah and
Thrush, Tristan",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1257/",
doi = "10.18653/v1/2024.emnlp-main.1257",
pages = "22571--22582"
}