/MVTec_GradCAM

Grad-CAM implementation on MVTec dataset re-casted as a supervised learning problem.

Primary LanguageJupyter Notebook

MVTec_GradCAM

Grad-CAM[1] implementation on MVTec anomaly AD dataset[2] re-casted into a supervised learning based classification task.

Code for training a ResNet101 model using Transfer Learning is also provided in this repo, as the trained model is loaded onto the Grad-CAM explanation algorithm.

[1]. Selvaraju, Ramprasaath R., et al. "Grad-cam: Visual explanations from deep networks via gradient-based localization." Proceedings of the IEEE international conference on computer vision. 2017.

[2]. MVTec AD dataset - Bergmann, Paul, et al. "MVTec AD--A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.