Search Results for author: Narayanan C. Krishnan

Found 12 papers, 5 papers with code

Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks

no code implementations21 Oct 2021 Abhishek Singh Sambyal, Narayanan C. Krishnan, Deepti R. Bathula

The proposed method was evaluated on a benchmark medical imaging dataset with image reconstruction as the self-supervised task and segmentation as the image analysis task.

Data Augmentation Decision Making Under Uncertainty +4

Efficient Algorithms For Fair Clustering with a New Fairness Notion

1 code implementation2 Sep 2021 Shivam Gupta, Ganesh Ghalme, Narayanan C. Krishnan, Shweta Jain

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 cluster; i. e., a balance property.


Deep Geospatial Interpolation Networks

no code implementations15 Aug 2021 Sumit Kumar Varshney, Jeetu Kumar, Aditya Tiwari, Rishabh Singh, Venkata M. V. Gunturi, Narayanan C. Krishnan

Spatio-Temporal interpolation is highly challenging due to the complex spatial and temporal relationships.

Task Attended Meta-Learning for Few-Shot Learning

no code implementations20 Jun 2021 Aroof Aimen, Sahil Sidheekh, Narayanan C. Krishnan

The popular approaches for ML either learn a generalizable initial model or a generic parametric optimizer through episodic training.

Few-Shot Learning

Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition

1 code implementation31 May 2021 Ravi Bhatt, Anuj Rai, Narayanan C. Krishnan, Sukalpa Chanda

Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers).

Zero-Shot Learning

On Characterizing GAN Convergence Through Proximal Duality Gap

1 code implementation11 May 2021 Sahil Sidheekh, Aroof Aimen, Narayanan C. Krishnan

Finally, we validate experimentally the usefulness of proximal duality gap for monitoring and influencing GAN training.

Stress Testing of Meta-learning Approaches for Few-shot Learning

no code implementations21 Jan 2021 Aroof Aimen, Sahil Sidheekh, Vineet Madan, Narayanan C. Krishnan

Our results show a quick degradation in the performance of initialization strategies for ML (MAML, TAML, and MetaSGD), while surprisingly, approaches that use an optimization strategy (MetaLSTM) perform significantly better.

Few-Shot Learning

On Duality Gap as a Measure for Monitoring GAN Training

1 code implementation12 Dec 2020 Sahil Sidheekh, Aroof Aimen, Vineet Madan, Narayanan C. Krishnan

Further, we show that our estimate, with its ability to identify model convergence/divergence, is a potential performance measure that can be used to tune the hyperparameters of a GAN.

Wheat Crop Yield Prediction Using Deep LSTM Model

no code implementations3 Nov 2020 Sagarika Sharma, Sujit Rai, Narayanan C. Krishnan

An in-season early crop yield forecast before harvest can benefit the farmers to improve the production and enable various agencies to devise plans accordingly.

Crop Yield Prediction Dimensionality Reduction

Implicit Discriminator in Variational Autoencoder

no code implementations28 Sep 2019 Prateek Munjal, Akanksha Paul, Narayanan C. Krishnan

In this work we introduce a novel hybrid architecture, Implicit Discriminator in Variational Autoencoder (IDVAE), that combines a VAE and a GAN, which does not need an explicit discriminator network.

Semantically Aligned Bias Reducing Zero Shot Learning

no code implementations CVPR 2019 Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal

It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes.

Zero-Shot Learning

Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet)

1 code implementation31 Jul 2018 Jatin Garg, Skand Vishwanath Peri, Himanshu Tolani, Narayanan C. Krishnan

Further, recognizing the identity in the image by knowledge transfer using a combination of shared and modality specific representations, resulted in an unprecedented performance of 85% rank-1 accuracy for caricatures and 95% rank-1 accuracy for visual images.

Caricature Face Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.