36 citations · 105 across the 22 of their papers we have counts for
9 papers · 1 filter
Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks
Abhishek Singh Sambyal, Narayanan C. Krishnan, Deepti R. Bathula
In safety-critical applications like medical diagnosis, certainty associated with a model's prediction is just as important as its accuracy. Consequently, uncertainty estimation an…
Efficient Algorithms For Fair Clustering with a New Fairness Notion
Shivam Gupta, Ganesh Ghalme, Narayanan C. Krishnan +1
We revisit the problem of fair clustering, first introduced by Chierichetti et al., that requires each protected attribute to have approximately equal representation in every clust…
PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs
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. There is a growing interest in explaining…
Deep Geospatial Interpolation Networks
Sumit Kumar Varshney, Jeetu Kumar, Aditya Tiwari +3
Interpolation in Spatio-temporal data has applications in various domains such as climate, transportation, and mining. Spatio-Temporal interpolation is highly challenging due to th…
Evaluation of Saliency-based Explainability Method
Sam Zabdiel Sunder Samuel, Vidhya Kamakshi, Namrata Lodhi +1
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…
Task Attended Meta-Learning for Few-Shot Learning
Aroof Aimen, Sahil Sidheekh, Narayanan C. Krishnan
Meta-learning (ML) has emerged as a promising direction in learning models under constrained resource settings like few-shot learning. The popular approaches for ML either learn a…
On Characterizing GAN Convergence Through Proximal Duality Gap
Sahil Sidheekh, Aroof Aimen, Narayanan C. Krishnan
Despite the accomplishments of Generative Adversarial Networks (GANs) in modeling data distributions, training them remains a challenging task. A contributing factor to this diffic…
Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition
Ravi Bhatt, Anuj Rai, Narayanan C. Krishnan +1
Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers). In a real-life…
Stress Testing of Meta-learning Approaches for Few-shot Learning
Aroof Aimen, Sahil Sidheekh, Vineet Madan +1
Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generaliz…