Prerocessing the images before classification as well as visualizations aiming at understanding how the final model performs classification
-
Updated
Sep 23, 2022 - Jupyter Notebook
Prerocessing the images before classification as well as visualizations aiming at understanding how the final model performs classification
Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet
This study tries to compare the detection of lung diseases using xray scans from three different datasets using three different neural network architectures using Pytorch and perform an ablation study by changing learning rates. The dimensional understanding is visualised using t-SNE and Grad-CAM for visualisation of diseases in x-ray scans.
Fork of the Mario Kart 64 Gym Environment. Includes training scripts for RL algorithms and Grad-CAM visualization
image classification using deep learning
Gradient Frequency Attention: Tell Neural Networks where speaker information is.
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.
Develop and train image classification models using advanced deep learning techniques to identify diseases specific to apples.
Exploring the Application of Attention Mechanisms in Conjunction with Baseline Models on the COVID-19-CT Dataset
Collecting fish image data, after training classifiers grad-cam is applied for the prediction interpretation
Detection and localization of COVID-19 on chest X-rays
Using LIME and Grad-CAM techniques to explain the results achieved by various image transfer learning techniques
Image classification using deep learning models with activation map visualisation and TensorRT support
Master's thesis - Austral University - Pneumonia detection on X-ray chest exams
KL severity grading using SE-ResNet and SE-DenseNet architectures trained with Cross Entropy loss and Focal Loss. The hyperparameters of focal loss have been fine-tuned as well. Further, Grad-CAM has been implemented for visualization purposes.
PyTorch MobileNetV2 Stanford Cars Dataset Classification (0.85 Accuracy)
Have you ever asked yourself, which regions of the input image were considered more by the model? If so, Grad-CAM has exciting answers for you!
Generate explanations for the ResNet50 classification using Grad-CAM and LIME (XAI Method)
Gradient Class Activation Map (with pytorch): Visualize the model's prediction to help understand CNN and ViT models better
Repository of the course project of CMU 16-824 Visual Learning and Recognition
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."