IEEE

Fast Transfer Learning Method Using Random Layer Freezing and Feature Refinement Strategy

Abstract: Recently, Moore-Penrose inverse (MPI)-based parameter fine-tuning of fully connected (FC) layers in pretrained deep convolutional neural networks (DCNNs) has emerged within the inductive ...
GitHub

Dropping the D: RGB-D SLAM Without the Depth Sensor

A real-time monocular SLAM system that achieves RGB-D accuracy without requiring a depth sensor. https://arxiv.org/abs/2510.06216 The system removes keypoints on ...
GitHub

QuratulainSofDev/Lightweight-and-Effective-Deep-learning-model-for-osteoprosis-classification

📋 Project Overview This project presents a novel CBAM-guided channel pruning framework for efficient osteoporosis classification using knee X-ray images. The methodology achieves 55.9% parameter ...
IEEE

An Interpretable Quantum Adjoint Convolutional Layer for Image Classification

Abstract: The interpretability of quantum machine learning (QML) refers to the capability to provide clear and understandable explanations for the predictions and decision-making processes of QML ...