Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Net, Francesc, Folia, Marc, Casals, Pep, Gomez, Lluis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916454351241216
author Net, Francesc
Folia, Marc
Casals, Pep
Gomez, Lluis
author_facet Net, Francesc
Folia, Marc
Casals, Pep
Gomez, Lluis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19437
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections
Net, Francesc
Folia, Marc
Casals, Pep
Gomez, Lluis
Computer Vision and Pattern Recognition
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.
title Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.19437