Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections
This work addresses a domain-specific problem for archivists and document management companies, but it is incremental as it applies existing deep learning methods to a new use case.
The paper tackled near-duplicate image detection in scanned photo collections to reduce manual annotation time, and the proposed transductive learning approach outperformed baseline methods on UKBench and a private dataset.
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.