Inductive Self-Supervised Dimensionality Reduction for Image Retrieval

Deryk Willyan Biotto, Guilherme Henrique Jardim, Vinicius Atsushi Sato Kawai, Bionda Rozin, Denis Salvadeo, Daniel Pedronette

2025

Abstract

The exponential growth of multimidia data creates a pressing need for approaches that are capable of efficiently handling Content-Based Image Retrieval (CBIR) in large and continuosly evolving datasets. Dimensionality reduction techniques, such as t-SNE and UMAP, have been widely used to transform high-dimensional features into more discriminative, low-dimensional representations. These transformations improve the effectiveness of retrieval systems by not only preserving but also enhancing the underlying structure of the data. However, their transductive nature requires access to the entire dataset during the reduction process, limiting their use in dynamic environments where data is constantly added. In this paper, we propose ISSDiR, a self-supervised, inductive dimensionality reduction method that generalizes to unseen data, offering a practical solution for continuously expanding datasets. Our approach integrates neural networks-based feature extraction with clustering-based pseudo-labels and introduces a hybrid loss function that combines cross-entropy and constrastive loss, weighted by cluster distances. Extensive experiments demonstrate the competitive performance of the proposed method in multiple datasets. This indicates its potential to contribute to the field of image retrieval by introducing a novel inductive approach specifically designed for dimensionality reduction in retrieval tasks.

Paper Citation

in Harvard Style

Biotto D., Jardim G., Kawai V., Rozin B., Salvadeo D. and Pedronette D. (2025). Inductive Self-Supervised Dimensionality Reduction for Image Retrieval. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 383-391. DOI: 10.5220/0013158600003912

in Bibtex Style

@conference{visapp25,
author={Deryk Biotto and Guilherme Jardim and Vinicius Kawai and Bionda Rozin and Denis Salvadeo and Daniel Pedronette},
title={Inductive Self-Supervised Dimensionality Reduction for Image Retrieval},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={383-391},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013158600003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Inductive Self-Supervised Dimensionality Reduction for Image Retrieval
SN - 978-989-758-728-3
AU - Biotto D.
AU - Jardim G.
AU - Kawai V.
AU - Rozin B.
AU - Salvadeo D.
AU - Pedronette D.
PY - 2025
SP - 383
EP - 391
DO - 10.5220/0013158600003912
PB - SciTePress