no code implementations • 20 May 2022 • Vidhya Kamakshi, Narayanan C Krishnan
Domain adaptation techniques have contributed to the success of deep learning.
no code implementations • 31 Aug 2021 • Vidhya Kamakshi, Uday Gupta, Narayanan C Krishnan
Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them.
no code implementations • 24 Jun 2021 • Sam Zabdiel Sunder Samuel, Vidhya Kamakshi, Namrata Lodhi, Narayanan C Krishnan
A particular class of Explainable AI (XAI) methods provide saliency maps to highlight part of the image a Convolutional Neural Network (CNN) model looks at to classify the image as a way to explain its working.
no code implementations • 3 Nov 2020 • Rajat Sharma, Nikhil Reddy, Vidhya Kamakshi, Narayanan C Krishnan, Shweta Jain
Novel approximations to the coverage and precision measures in terms of the parameters of the hyper-cuboid are defined.
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.