Frontiers

Label tree semantic losses for rich multi-class medical image segmentation

Rich and accurate medical image segmentation is poised to underpin the next generation of AI-defined clinical practice by delineating critical anatomy for pre-operative planning, guiding real-time ...
Frontiers

Dual contextual learning for semi-supervised medical image classification

Semi-supervised learning (SSL) has emerged as a promising paradigm for medical image classification, addressing the critical challenge of limited labeled data in healthcare where expert annotation is ...
GitHub

AvinashSappati/CNN-RNN-Multi-Image-Classification

A full-stack Deep Learning application that detects multiple objects in a single image using a hybrid CNN-RNN architecture. This repository bridges the gap between complex machine learning ...
GitHub

DisasterClassifier - CNN + Convex SVM + Quantum Hybrid

DisasterClassifier/ ├── data/ │ ├── raw/ # Original zip / download files │ ├── processed/ # Train/val/test splits (ImageFolder format ...
Scientific Research Publishing

A Multi-CNN-GAN Framework for Effective Image Dehazing ()

1 Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh. 2 Department of Computer Science and Engineering, Green University of Bangladesh, Narayanganj, Bangladesh ...
IEEE

Image-Based Malware Classification Using CNN with Benign Class Augmentation

Abstract: Malware remains one of the most serious cybersecurity threats in modern times, as its main goal is to compromise the confidentiality, integrity, and availability of digital systems. Classic ...
IEEE

Multi-Class Waste Image Classification Using CNN Architectures

Abstract: Effective waste sorting has become a progressively critical issue globally, forming the basis towards realizing automated recycling systems and fostering environmental sustainability. Recent ...