Momojit Biswas

Momojit Biswas

Auto-generated profile, based on publicly available information

Momojit Biswas

Jadavpur University Kolkata India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2022 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
RPRishav Pramanik
Rishav Pramanik
MBMomojit Biswas
Momojit Biswas
SSShibaprasad Sen
Shibaprasad Sen
LJLuis Antonio de Souza Júnior
Luis Antonio de Souza Júnior
JPJoao Papa
Joao Papa
RSRam Sarkar
Ram Sarkar

10 July 2024 in Computational Materials Science
Verified
Journal Article
Closed access
SMSamriddha Majumdar
Samriddha Majumdar
ASArup Sau
Arup Sau
MBMomojit Biswas
Momojit Biswas
RSRam Sarkar
Ram Sarkar


14 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
MBMomojit Biswas
Momojit Biswas
Himanshu BuckchashHimanshu Buckchash
Himanshu Buckchash
Dilip K. PrasadDilip K. Prasad
Dilip K. Prasad
Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set, which holds positive samples for the contrastive loss. In this work, we show that the quality of the support set plays a crucial role in any nearest neighbor based method for SSL. We then provide a refined baseline (pNNCLR) to the nearest neighbor based SSL approach (NNCLR). To this end, we introduce pseudo nearest neighbors (pNN) to control the quality of the support set, wherein, rather than sampling the nearest neighbors, we sample in the vicinity of hard nearest neighbors by varying the magnitude of the resultant vector and employing a stochastic sampling strategy to improve the performance. Additionally, to stabilize the effects of uncertainty in NN-based learning, we employ a smooth-weight-update approach for training the proposed network. Evaluation of the proposed method on multiple public image recognition and medical image recognition datasets shows that it performs up to 8 percent better than the baseline nearest neighbor method, and is comparable to other previously proposed SSL methods.