Recursive Weight Sharing for Parameter-Efficient Deep Convolutional Networks: Application to Skin Lesion Classification

Read full text Summarise with VIRAT
Authors: Ali Belkhiri, My Abdelouahed Sabri, Abdellah Aarab
Cited by: 0
References: 20

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Modern deep convolutional neural networks achieve remarkable performance but require substantial computational resources due to their large parameter counts, limiting their suitability for resource-constrained environments. We propose Tiny Recursive ResNet-50, a parameter-efficient architecture that reduces model complexity through recursive feature refinement with weight sharing across reasoning cycles. The proposed design combines lightweight bottleneck blocks, iterative latent state accumulation, and deep supervision to enhance representation quality without increasing parameter count. Extensive experiments are conducted on melanoma classification using the HAM10000 dataset as the primary training and evaluation benchmark. Results demonstrate that the proposed recursive architecture maintains competitive accuracy while reducing parameters by approximately 49%, confirming its efficiency under constrained settings. To assess robustness under limited data and acquisition variability, we additionally validate on the PH2 dataset (200 images). Due to the small dataset size and class imbalance, evaluation is performed using 5-fold stratified cross-validation, and performance metrics are reported as mean ± standard deviation. This validation confirms that recursive refinement with moderate cycle depth improves stability and generalization in small-data regimes.

Fields of Study & Subjects

Advanced Neural Network Applications Cutaneous Melanoma Detection and Management Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Applied System Innovation
Volume
9
Issue
4
Pages
69–69
Publication date
25 March 2026
Language
EN