Publications

2025

1. arXiv

   State-of-the-Art Transformer Models for Image Super-Resolution: Techniques, Challenges, and Applications

   Debasish Dutta, Deepjyoti Chetia, Neeharika Sonowal, and 1 more author

   arXiv preprint arXiv:2501.07855, 2025

    https://doi.org/10.48550/arXiv.2501.07855
   ArXiv preprint
   

   Abs arXiv Bib PDF

   

   Image Super-Resolution (SR) aims to recover a high-resolution image from its low-resolution counterpart, which has been affected by a specific degradation process. This is achieved by enhancing detail and visual quality. Recent advancements in transformer-based methods have remolded image super-resolution by enabling high-quality reconstructions surpassing previous deep-learning approaches like CNN and GAN-based. This effectively addresses the limitations of previous methods, such as limited receptive fields, poor global context capture, and challenges in high-frequency detail recovery. Additionally, the paper reviews recent trends and advancements in transformer-based SR models, exploring various innovative techniques and architectures that combine transformers with traditional networks to balance global and local contexts. These neoteric methods are critically analyzed, revealing promising yet unexplored gaps and potential directions for future research. Several visualizations of models and techniques are included to foster a holistic understanding of recent trends. This work seeks to offer a structured roadmap for researchers at the forefront of deep learning, specifically exploring the impact of transformers on super-resolution techniques.

   @article{dutta2025srtrans,
     title = {State-of-the-Art Transformer Models for Image Super-Resolution: Techniques, Challenges, and Applications},
     author = {Dutta, Debasish and Chetia, Deepjyoti and Sonowal, Neeharika and Kalita, Sanjib Kr},
     journal = {arXiv preprint arXiv:2501.07855},
     year = {2025},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     dimensions = {true},
     keywords = {arxiv, Single Image Super-Resolution (SR); Transformers; Vision Transformers (ViTs); Image Degradation and Enhancement; Self-Attention Mechanisms},
     doi = {https://doi.org/10.48550/arXiv.2501.07855},
     url = {https://arxiv.org/abs/2501.07855},
   }

2. arXiv

   Image Segmentation with transformers: An Overview, Challenges and Future

   Deepjyoti Chetia, Debasish Dutta, and Sanjib Kr Kalita

   arXiv preprint arXiv:2501.09372, 2025

    https://doi.org/10.48550/arXiv.2501.09372
   ArXiv preprint
   

   Abs arXiv Bib PDF

   

   Image segmentation, a key task in computer vision, has traditionally relied on convolutional neural networks (CNNs), yet these models struggle with capturing complex spatial dependencies, objects with varying scales, need for manually crafted architecture components and contextual information. This paper explores the shortcomings of CNN-based models and the shift towards transformer architectures -to overcome those limitations. This work reviews state-of-the-art transformer-based segmentation models, addressing segmentation-specific challenges and their solutions. The paper discusses current challenges in transformer-based segmentation and outlines promising future trends, such as lightweight architectures and enhanced data efficiency. This survey serves as a guide for understanding the impact of transformers in advancing segmentation capabilities and overcoming the limitations of traditional models.

   @article{chetia2025segtrans,
     title = {Image Segmentation with transformers: An Overview, Challenges and Future},
     author = {Chetia, Deepjyoti and Dutta, Debasish and Kalita, Sanjib Kr},
     journal = {arXiv preprint arXiv:2501.09372},
     year = {2025},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     dimensions = {true},
     keywords = {arxiv, Image Segmentation, Transformer, Vision Transformers (ViTs), Self-Attention Mechanism, Deep Learning},
     doi = {https://doi.org/10.48550/arXiv.2501.09372},
     url = {https://arxiv.org/abs/2501.09372},
   }

3. arXiv

   Developing a Modular Compiler for a Subset of a C-like Language

   Debasish Dutta, Neeharika Sonowal, and Irani Hazarika

   2025

    https://doi.org/10.48550/arXiv.2501.04503
   ArXiv preprint
   

   Abs arXiv Bib PDF Code

   

   The paper introduces the development of a modular compiler for a subset of a C-like language, which addresses the challenges in constructing a compiler for high-level languages. This modular approach will allow developers to modify a language by adding or removing subsets as required, resulting in a minimal and memory-efficient compiler. The development process is divided into small, incremental steps, where each step yields a fully functioning compiler for an expanding subset of the language. The paper outlines the iterative developmental phase of the compiler, emphasizing progressive enhancements in capabilities and functionality. Adherence to industry best practices of modular design, code reusability, and documentation has enabled the resulting compiler’s functional efficiency, maintainability, and extensibility. The compiler proved to be effective not only in managing the language structure but also in developing optimized code, which demonstrates its practical usability. This was also further assessed using the compiler on a tiny memory-deficient single-board computer, again showing the compiler’s efficiency and suitability for resource-constrained devices.

   @article{dutta2025compiler,
     title = {Developing a Modular Compiler for a Subset of a C-like Language},
     author = {Dutta, Debasish and Sonowal, Neeharika and Hazarika, Irani},
     year = {2025},
     archiveprefix = {arXiv},
     primaryclass = {cs.PL},
     dimensions = {true},
     keywords = {arxiv, Programming Languages (cs.PL); Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC); Performance (cs.PF)},
     doi = {https://doi.org/10.48550/arXiv.2501.04503},
     url = {https://arxiv.org/abs/2501.04503},
   }

2024

1. IEEE

   Recent Advancements in Microscopy Image Enhancement using Deep Learning: A Survey

   Debasish Dutta, Neeharika Sonowal, Risheraj Barauh, and 2 more authors

   In 2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI), 2024

    10.1109/CVMI61877.2024.10782829
   IEEE Explore
   

   Abs Bib HTML PDF

   

   Microscopy image enhancement plays a pivotal role in understanding the details of biological cells and materials at microscopic scales. In recent years, there has been a significant rise in the advancement of microscopy image enhancement, specifically with the help of deep learning methods. This survey paper aims to provide a snapshot of this rapidly growing state-of-the-art method, focusing on its evolution, applications, challenges, and future directions. The core discussions take place around the key domains of microscopy image enhancement of super-resolution, reconstruction, and denoising, with each domain explored in terms of its current trends and their practical utility of deep learning.

   @inproceedings{ddcvmi2024,
     author = {Dutta, Debasish and Sonowal, Neeharika and Barauh, Risheraj and Chetia, Deepjyoti and Kalita, Sanjib Kr},
     booktitle = {2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)},
     title = {Recent Advancements in Microscopy Image Enhancement using Deep Learning: A Survey},
     year = {2024},
     volume = {},
     number = {},
     pages = {1-7},
     ieee = {10782829},
     dimensions = {true},
     keywords = {Surveys;Deep learning;Evolution (biology);Microscopy;Biological system modeling;Noise reduction;Superresolution;Spatial resolution;Image enhancement;Image reconstruction;microscopy;deep learning;image restoration;image enhancement;super-resolution;deconvolution},
     doi = {10.1109/CVMI61877.2024.10782829},
   }

2. Springer

   Identification of Traditional Medicinal Plant Leaves Using an effective Deep Learning model and Self-Curated Dataset

   Deepjyoti Chetia, Sanjib Kr Kalita, Prof Partha Pratim Baruah, and 2 more authors

   In , 2024

    https://doi.org/10.1007/978-3-031-83793-7_22
   ArXiv preprint
   

   Abs arXiv Bib PDF

   

   Medicinal plants have been a key component in producing traditional and modern medicines, especially in the field of Ayurveda, an ancient Indian medical system. Producing these medicines and collecting and extracting the right plant is a crucial step due to the visually similar nature of some plants. The extraction of these plants from nonmedicinal plants requires human expert intervention. To solve the issue of accurate plant identification and reduce the need for a human expert in the collection process; employing computer vision methods will be efficient and beneficial. In this paper, we have proposed a model that solves such issues. The proposed model is a custom convolutional neural network (CNN) architecture with 6 convolution layers, max-pooling layers, and dense layers. The model was tested on three different datasets named Indian Medicinal Leaves Image Dataset,MED117 Medicinal Plant Leaf Dataset, and the self-curated dataset by the authors. The proposed model achieved respective accuracies of 99.5%, 98.4%, and 99.7% using various optimizers including Adam, RMSprop, and SGD with momentum.

   @inproceedings{chetia2025med,
     title = {Identification of Traditional Medicinal Plant Leaves Using an effective Deep Learning model and Self-Curated Dataset},
     author = {Chetia, Deepjyoti and Kalita, Sanjib Kr and Baruah, Prof Partha Pratim and Dutta, Debasish and Akhter, Tanaz},
     journal = {International Conference on Advanced Network Technologies and Intelligent Computing},
     year = {2024},
     pages = {342--356},
     archiveprefix = {arXiv},
     dimensions = {true},
     keywords = {arxiv, Medicinal plant identification · Medicinal plant leaf dataset deep learning · Convolutional Neural Network(CNN)},
     doi = {https://doi.org/10.1007/978-3-031-83793-7_22},
     url = {https://arxiv.org/abs/2501.09363},
   }