no code implementations • 7 Aug 2023 • Akshit Achara, Ram Krishna Pandey
Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task.
no code implementations • 30 May 2023 • Ram Krishna Pandey, Akshit Achara
The objective of this work is to show that by incorporating domain knowledge along with deep learning architectures, we can achieve similar performance with less data.
no code implementations • 10 Sep 2022 • Ram Krishna Pandey, Akshit Achara
Detecting, measuring and quantifying cracks for distress analysis in challenging background scenarios is a difficult task as there is no clear boundary that separates cracks from the background.
no code implementations • 12 Feb 2019 • Ram Krishna Pandey, Souvik Karmakar, A. G. Ramakrishnan, Nabagata Saha
These modifications help the network learn additional information from the gradient and Laplacian of the images.
1 code implementation • 6 Dec 2018 • Ram Krishna Pandey, K Vignesh, A. G. Ramakrishnan, Chandrahasa B
This gives rise to the problem of binary document image super-resolution (BDISR).
no code implementations • 25 Aug 2018 • Ram Krishna Pandey, Nabagata Saha, Samarjit Karmakar, A. G. Ramakrishnan
With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques.
no code implementations • 16 Jul 2018 • Ram Krishna Pandey, Samarjit Karmakar, A. G. Ramakrishnan
In this work, we have investigated various style transfer approaches and (i) examined how the stylized reconstruction changes with the change of loss function and (ii) provided a computationally efficient solution for the same.
no code implementations • 23 May 2018 • Ram Krishna Pandey, Aswin Vasan, A. G. Ramakrishnan
We propose a computationally efficient architecture that learns to segment lesions from CT images of the liver.
no code implementations • 23 May 2018 • Ram Krishna Pandey, A. G. Ramakrishnan
We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images.
no code implementations • 30 Jan 2017 • Ram Krishna Pandey, A. G. Ramakrishnan
The problem involves quality improvement before passing it to a properly trained OCR to get accurate recognition of the text.