Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
-
Updated
Jun 1, 2024 - Python
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
Building models that can predict whether an area is at risk of a wildfire or not on satellite images.
Attribution methods that explain image classification models, implemented in PyTorch, and support batch input and GPU.
Unofficial PyTorch implementation of Score-CAM with additional functions
The official code of Relevance-CAM
Wanna know what your model sees? Here's a package for applying EigenCAM on the new YOLO V8 model
Computer vision visualization such as Grad-CAM, etc.
An awesome list of papers and tools about the class activation map (CAM) technology.
[SIGMOD 2022] Python code for "Dimension-wise Class Activation Map for Multivariate Time Series Classification"
PyTorch implementation of "Learning Deep Features for Discriminative Localization"
Time Series package for fastai v2
Class Activation Map | Stanford Cars | PyTorch
Through data, classification model was builded whether predicts if there is any crack or not on concrete with Class Activation Map.
Classification model was builded whether lemons have good quality, bad quality or have empty background with Class Activation Map.
Code for our paper "Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism", by I. Gkartzonika, N. Gkalelis, V. Mezaris, presented and included in the Proceedings of the ECCV 2022 Workshop on Vision with Biased or Scarce Data (VBSD), Oct. 2022.
Code for the paper : "Weakly supervised segmentation with cross-modality equivariant constraints", available at https://arxiv.org/pdf/2104.02488.pdf
Simple tf-keras code CAM (Class Activation Mapping)
Implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation (Fong, et. al., 2018)
Explainable text classification
Add a description, image, and links to the class-activation-map topic page so that developers can more easily learn about it.
To associate your repository with the class-activation-map topic, visit your repo's landing page and select "manage topics."