Saurabh Desai

Project Associate

Artificial Intelligence

Computer Vision

Machine Learning

Interpretability and Deep Learning

I work as project associate interested in working in computer vision and deep learning research. I am also interested in explanability of AI which can increase the reliability in use of neural networks and open up the black box.

Jan 13, 2021

Ablation-CAM: Making AI trustworthy

Saurabh Desai , Harish G. Ramaswamy

As machine learning is set to change every aspect of our life, a key dilemma plagues the minds of researchers and its users- Can we trust machines to make key life decisions for us? Can we rely solely on the machine to drive us safely to the destination without knowing the basis of its function or shall we allow a machine to operate us instead of a doctor?

neural network , black box , deep learning , visualization

4 min read

Project Associate

blogs

Ablation-CAM: Making AI trustworthy

publications

Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization