P.K. Biswas
Indian Institute of Technology Kharagpur
19 Papers
39 Citations
P.K. Biswas is an academic researcher from Indian Institute of Technology Kharagpur. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 19 publications. Previous affiliations of P.K. Biswas include University of Calcutta & Indira Gandhi National Open University.
Chat about Author
Papers
Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising
Sutanu Bera,P.K. Biswas +1 more
TL;DR: A novel convolutional module as the first attempt to utilize neighborhood similarity of CT images for denoising tasks and a novel discriminator function for CT denoizing tasks to mitigate problems with three novel accretions are proposed.
85
Component labeling in pyramid architecture
TL;DR: A new pyramid algorithm for labeling connected components of an image is presented that uses explicit node to node connections in a pyramid architecture for data transfer operations and does not assume any complex pyramid machine with random access read (RAR) or random access write (RAW) capabilities.
10
Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network
Aupendu Kar,P.K. Biswas +1 more
- 01 Jun 2021
TL;DR: In this paper, a Bayesian approach for estimating uncertainty associated with output and applying it in a deep image super-resolution model to address the problem of out-of-distribution samples is proposed.
•Journal Article
Learning Strategies and Academic Performance: A Study of the Successful Distance Learners of PGDDE programme of IGNOU
TL;DR: In this article, a structured questionnaire was developed to collect data in relation to the objectives of the study and a questionnaire was administered on 16 learners in face-to-face situation and was later sent to 134 learners by post.
6
•Posted Content
Faster Unsupervised Semantic Inpainting: A GAN Based Approach
TL;DR: This paper proposes to improve the inference speed and visual quality of contemporary baseline of Generative Adversarial Networks (GAN) based unsupervised semantic inpainting with consideration to temporal cues with better initialization of the core iterative optimization involved in the framework.
5