arXiv Open Access 2025

Lightweight Deep Models for Dermatological Disease Detection: A Study on Instance Selection and Channel Optimization

Ian Mateos Gonzalez Estefani Jaramilla Nava Abraham Sánchez Morales Jesús García-Ramírez Ricardo Ramos-Aguilar

Lihat Sumber

Abstrak

The identification of dermatological disease is an important problem in Mexico according with different studies. Several works in literature use the datasets of different repositories without applying a study of the data behavior, especially in medical images domain. In this work, we propose a methodology to preprocess dermaMNIST dataset in order to improve its quality for the classification stage, where we use lightweight convolutional neural networks. In our results, we reduce the number of instances for the neural network training obtaining a similar performance of models as ResNet.

Topik & Kata Kunci

eess.IV cs.AI cs.CV

Penulis (5)

Ian Mateos Gonzalez

Estefani Jaramilla Nava

Abraham Sánchez Morales

Jesús García-Ramírez

Ricardo Ramos-Aguilar

Format Sitasi

APA MLA BibTeX

Gonzalez, I.M., Nava, E.J., Morales, A.S., García-Ramírez, J., Ramos-Aguilar, R. (2025). Lightweight Deep Models for Dermatological Disease Detection: A Study on Instance Selection and Channel Optimization. https://arxiv.org/abs/2504.01208

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓