Generation of 3D/ 2D attention maps for both classification and segmentation
- Updated
Jul 17, 2025 - Python
Generation of 3D/ 2D attention maps for both classification and segmentation
📦 PyTorch based visualization package for generating layer-wise explanations for CNNs.
Going deeper into Deep CNNs through visualization methods: Saliency maps, optimize a random input image and deep dreaming with Keras
Code for the paper : "Weakly supervised segmentation with cross-modality equivariant constraints", available at https://arxiv.org/pdf/2104.02488.pdf
Deep Learning Breast MRI Segmentation and Classification
First position in Gran Canary Datathon 2021
We will build and train a Deep Convolutional Neural Network (CNN) with Residual Blocks to detect the type of scenery in an image. In addition, we will also use a technique known as Gradient-Weighted Class Activation Mapping (Grad-CAM) to visualize the regions of the inputs and help us explain how our CNN models think and make decision.
PyTorch MobileNetV2 Stanford Cars Dataset Classification (0.85 Accuracy)
Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet
Heat Map 🔥 Generation codes for using PyTorch and CAM Localization Algorithm.
Deep Learning for SAR Ship classification: Focus on Unbalanced Datasets and Inter-Dataset Generalization
Deep learning pipeline for classification of Cataract, Diabetic Retinopathy, Glaucoma and Normal using fundus images
Curso de Redes Neuronales Convolucionales con PyTorch
Intracerebral Hemorrhage Detection on Computed Tomography Images Using a Residual Neural Network
Repository of the course project of CMU 16-824 Visual Learning and Recognition
Generate explanations for the ResNet50 classification using Grad-CAM and LIME (XAI Method)
A complete, straightforward digit classification project built with PyTorch, featuring CNN-based training, evaluation metrics, confusion matrix visualization, and XAI using Grad-CAM.
Detection and localization of COVID-19 on chest X-rays
Develop and train image classification models using advanced deep learning techniques to identify diseases specific to apples.
rad-Cam provides us with a way to look into what particular parts of the image influenced the whole model’s decision for a specifically assigned label. It is particularly useful in analyzing wrongly classified samples.
Add a description, image, and links to the grad-cam-visualization topic page so that developers can more easily learn about it.
To associate your repository with the grad-cam-visualization topic, visit your repo's landing page and select "manage topics."