no code implementations • 22 Sep 2023 • Abhishek Singh Sambyal, Usma Niyaz, Narayanan C. Krishnan, Deepti R. Bathula
We considered fully supervised training, which is the prevailing approach in the community, as well as rotation-based self-supervised method with and without transfer learning, across various datasets and architecture sizes.
no code implementations • 8 Sep 2023 • Aroof Aimen, Arsh Verma, Makarand Tapaswi, Narayanan C. Krishnan
Real-world application of chest X-ray abnormality classification requires dealing with several challenges: (i) limited training data; (ii) training and evaluation sets that are derived from different domains; and (iii) classes that appear during training may have partial overlap with classes of interest during evaluation.
no code implementations • 21 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.
1 code implementation • 2 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.
no code implementations • 15 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.
no code implementations • 20 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.
1 code implementation • 31 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Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers).
1 code implementation • 11 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.
no code implementations • 21 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.
1 code implementation • 12 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.
no code implementations • 3 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.
no code implementations • 28 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.
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.
1 code implementation • 31 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.