SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification

no code implementations • 15 May 2023 • Mauricio Mendez-Ruiz, Jorge Gonzalez-Zapata, Ivan Reyes-Amezcua, Daniel Flores-Araiza, Francisco Lopez-Tiro, Andres Mendez-Vazquez, Gilberto Ochoa-Ruiz

Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data.

Few-Shot Image Classification Few-Shot Learning +1

Guided Deep Metric Learning

no code implementations • 4 Jun 2022 • Jorge Gonzalez-Zapata, Ivan Reyes-Amezcua, Daniel Flores-Araiza, Mauricio Mendez-Ruiz, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning.

Few-Shot Learning Knowledge Distillation +1

On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification

no code implementations • 2 May 2022 • Mauricio Mendez-Ruiz, Francisco Lopez-Tiro, Jonathan El-Beze, Vincent Estrade, Gilberto Ochoa-Ruiz1, Jacques Hubert, Andres Mendez-Vazquez, Christian Daul

Deep learning has shown great promise in diverse areas of computer vision, such as image classification, object detection and semantic segmentation, among many others.

Domain Adaptation Few-Shot Learning +4

Finding Significant Features for Few-Shot Learning using Dimensionality Reduction

no code implementations • 6 Jul 2021 • Mauricio Mendez-Ruiz, Ivan Garcia Jorge Gonzalez-Zapata, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez

This module helps to improve the accuracy performance by allowing the similarity function, given by the metric learning method, to have more discriminative features for the classification.

Dimensionality Reduction Few-Shot Learning +1