@InProceedings{FrancescNet2023,
author="Francesc Net
and Marc Folia
and Pep Casals
and Lluis Gomez",
title="Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections",
booktitle="17th International Conference on Document Analysis and Recognition",
year="2023",
volume="14191",
pages="3--17",
optkeywords="Image deduplication",
optkeywords="Near-duplicate images detection",
optkeywords="Transductive Learning",
optkeywords="Photographic Archives",
optkeywords="Deep Learning",
abstract="This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3859), last updated on Wed, 17 Jan 2024 13:29:24 +0100",
opturl="https://link.springer.com/chapter/10.1007/978-3-031-41734-4_1"
}