INSTITUTIONAL DIGITAL REPOSITORY

Browsing by Author "Kamakshi, V."

Browsing by Author "Kamakshi, V."

Sort by: Order: Results:

  • Explainable supervised domain adaptation 
    Kamakshi, V.; Krishnan, N.C. (2022-12-09)
    Domain adaptation techniques have contributed to the success of deep learning. Leveraging knowledge from an auxiliary source domain for learning in labeled data-scarce target domain is fundamental to domain adaptation. ...
  • MAIRE - A model-agnostic interpretable rule extraction procedure for explaining classifiers 
    Sharma, R.; Reddy, N.; Kamakshi, V.; Krishnan, N.C.; Jain, S. (2022-09-03)
    The paper introduces a novel framework for extracting model-agnostic human interpretable rules to explain a classifier’s output. The human interpretable rule is defined as an axis-aligned hyper-cuboid containing the instance ...
  • PACE: posthoc Architecture-Agnostic concept extractor for explaining CNNs 
    Kamakshi, V.; Gupta, U.; Krishnan, N. C. (2021-11-22)
    Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them. There is a growing interest in explaining the working of these deep models to ...