MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks

1 code implementation • 3 Nov 2020 • Ashish Kumar, Karan Sehgal, Prerna Garg, Vidhya Kamakshi, Narayanan C Krishnan

The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on the foreground object as a whole.

Classification General Classification +1