IEEE GRSL: Integrating spatial details with long-range contexts for semantic segmentation of very high resolution remote sensing images
-
Updated
Jun 6, 2024 - Python
IEEE GRSL: Integrating spatial details with long-range contexts for semantic segmentation of very high resolution remote sensing images
Official implementation of "MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation" in MMSegmentation Framework.
Complete code for the proposed CNN-Transformer model for natural language understanding.
A deep learning approach for classifying crop types based on agricultural data.
A hybrid CNN–Transformer framework for precise industrial surface defect detection and segmentation, integrating Vision Transformer (ViT) with convolutional modules to effectively capture both local texture details and global contextual features.
Official implementation of "MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation" in MMSegmentation Framework.
A state-of-the-art hybrid deep learning ensemble that combines the strengths of Convolutional Neural Networks (CNNs) and Transformers for intelligent plant disease detection and real world agricultural applications.
ECG-TransNet implementation focused on the MIT-BIH Arrhythmia & AFDB datasets. Features a hybrid 1D-CNN & Transformer architecture for high-accuracy beat classification (AAMI standards). Includes specialized preprocessing for noise reduction, R-peak detection, and SHAP-based explainability for clinical validation of arrhythmia predictions.
Custom Video Processing Model
CNN-Transformer and ConvKAN based framework for obfuscated malware detection and classification using the MalImg dataset.
Unofficial PyTorch reimplementation of LHNet-S/B — lightweight hybrid CNN–Transformer real-time semantic segmentation with multi-scale sliding-window attention (Neurocomputing 2026).
End-to-end yoga pose classification web app using DenseNet121 and Flask, featuring a modular architecture, trained deep learning model, and deployment-ready UI for real-world inference
To associate your repository with the cnn-transformer topic, visit your repo's landing page and select "manage topics."