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

TL;DR

This paper introduces a transductive learning method utilizing deep neural networks and Vision Transformers to improve near-duplicate image detection in scanned photo collections, reducing manual annotation effort.

Contribution

It proposes a novel transductive learning approach that fine-tunes pre-trained models on unlabeled target data for near-duplicate detection, outperforming baseline methods.

Findings

Outperforms baseline methods on UKBench dataset

Effective in reducing manual annotation time

Leverages self-supervised fine-tuning on unlabeled data

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.