1 code implementation • 1 Dec 2023 • Niranjan Rajesh, Debayan Gupta
In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution.
1 code implementation • 12 Jul 2023 • Chanda Grover Kamra, Indra Deep Mastan, Debayan Gupta
However, the ground semantics of objects in the style transfer output is lost due to style spill-over on salient and background objects (content mismatch) or over-stylization.
1 code implementation • 24 Apr 2023 • Bhavesh Neekhra, Kshitij Kapoor, Debayan Gupta
Our experimental results show that synthetic population can realistically simulate the population for various administrative units of India, producing real-scale, detailed data at the desired level of zoom -- from cities, to districts, to states, eventually combining to form a country-scale synthetic population.
no code implementations • 11 Mar 2023 • Chanda G Kamra, Indra Deep Mastan, Debayan Gupta
Sem-CS first segments the content image into salient and non-salient objects and then transfers artistic style based on a given style text description.
no code implementations • 14 Nov 2022 • Chanda Grover, Indra Deep Mastan, Debayan Gupta
However, it showed negative transfer performance on standard datasets, e. g., BirdsNAP, RESISC45, and MNIST.
1 code implementation • 6 Feb 2022 • Arup Mondal, Harpreet Virk, Debayan Gupta
This makes it prone to gradient tampering and privacy leakage by a malicious aggregator.
1 code implementation • 19 Jan 2022 • Yash More, Prashanthi Ramachandran, Priyam Panda, Arup Mondal, Harpreet Virk, Debayan Gupta
Federated learning enables multiple data owners to jointly train a machine learning model without revealing their private datasets.
no code implementations • 28 Jan 2021 • Prashanthi Ramachandran, Shivam Agarwal, Arup Mondal, Aastha Shah, Debayan Gupta
In recent times, ReLU has been found to converge much faster and be more computationally efficient as compared to non-linear functions like sigmoid or tanh.
no code implementations • 21 Jan 2021 • Pratyush Kumar, Aishwarya Das, Debayan Gupta
In this paper, we propose a detailed experimental setup to determine the feasibility of using neural networks to solve the three body problem up to a certain number of time steps.