Momojit Biswas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Momojit Biswas has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Dilip Kumar Prasad
UiT The Arctic University of Norway, Tromsø, Norway
2 shared publications - Himanshu Buckchash
Institute Digitalisation and Informatics, Department of Science and Technology, IMC Krems University of Applied Sciences, 3500 Krems an der Donau, Austria
2 shared publications - Ram Sarkar
Computer Science and Engineering Department, Jadavpur University, Kolkata, India
2 shared publications - Arup Sau
Department of Computer Science and Engineering, Jadavpur University
1 shared publication - Chirag Jain
TCS Research, Pune, India
1 shared publication - João Paulo Papa
São Paulo State University (UNESP)
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Automating Metadata Extraction from Software Engineering Contracts Using a RAG Framework
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessAutomating Metadata Extraction from Software Engineering Contracts Using a RAG Framework
- 10 July 2024
- Published by Elsevier in Computational Materials Science
- Vol. 244
Metallographic image segmentation using feature pyramid based recurrent residual U-Net
- 10 July 2024
- Published by Elsevier in Computational Materials Science
- Vol. 244
Metallographic image segmentation using feature pyramid based recurrent residual U-Net
- Open Access
- 11 May 2024
- Published by Elsevier in Neurocomputing
- Vol. 593
pNNCLR: Stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problems
- 11 May 2024
- Published by Elsevier in Neurocomputing
- Vol. 593
Open AccesspNNCLR: Stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problems
- Open Access
pNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems
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.
Open AccesspNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems
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.
- 30 March 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 219, 106776
A fuzzy distance-based ensemble of deep models for cervical cancer detection
- 30 March 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 219, 106776
A fuzzy distance-based ensemble of deep models for cervical cancer detection