Search Results for author: Swalpa Kumar Roy

Found 27 papers, 18 papers with code

Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?

1 code implementation24 Jun 2024 Pallabi Dutta, Soham Bose, Swalpa Kumar Roy, Sushmita Mitra

The advancement of developing efficient medical image segmentation has evolved from initial dependence on Convolutional Neural Networks (CNNs) to the present investigation of hybrid models that combine CNNs with Vision Transformers.

Image Segmentation Medical Image Segmentation +2

Multi-dimension Transformer with Attention-based Filtering for Medical Image Segmentation

no code implementations20 May 2024 Wentao Wang, Xi Xiao, Mingjie Liu, Qing Tian, Xuanyao Huang, Qizhen Lan, Swalpa Kumar Roy, Tianyang Wang

MDT-AF incorporates an attention-based feature filtering mechanism into the patch embedding blocks and employs a coarse-to-fine process to mitigate the impact of low signal-to-noise ratio.

Image Segmentation Medical Image Segmentation +2

Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs

1 code implementation30 Apr 2024 Soham Mitra, Atri Sukul, Swalpa Kumar Roy, Pravendra Singh, Vinay Verma

Our proposed approach involves altering the normalization function within the activation layer utilized in ScoreCAM, resulting in significantly improved results compared to previous efforts.

Decision Making Fairness

GLFNET: Global-Local (frequency) Filter Networks for efficient medical image segmentation

no code implementations1 Mar 2024 Athanasios Tragakis, Qianying Liu, Chaitanya Kaul, Swalpa Kumar Roy, Hang Dai, Fani Deligianni, Roderick Murray-Smith, Daniele Faccio

We propose a novel transformer-style architecture called Global-Local Filter Network (GLFNet) for medical image segmentation and demonstrate its state-of-the-art performance.

Image Segmentation Medical Image Segmentation +1

A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement

1 code implementation6 Dec 2023 Risab Biswas, Swalpa Kumar Roy, Umapada Pal

Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results.

Binarization Decoder +1

DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization

no code implementations6 Dec 2023 Risab Biswas, Swalpa Kumar Roy, Ning Wang, Umapada Pal, Guang-Bin Huang

Instead of using a simple vision transformer block to extract information from the image patches, the proposed architecture uses two transformer blocks for greater coverage of the extracted feature space on a global and local scale.

Binarization Decoder

Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping

1 code implementation9 Aug 2023 Ali Jamali, Swalpa Kumar Roy, Danfeng Hong, Peter M Atkinson, Pedram Ghamisi

Results illustrated the superiority of the developed SGU-MLP classification algorithm over several CNN and CNN-ViT-based models, including HybridSN, ResNet, iFormer, EfficientFormer and CoAtNet.

Image Classification

Neighborhood Attention Makes the Encoder of ResUNet Stronger for Accurate Road Extraction

1 code implementation8 Jun 2023 Ali Jamali, Swalpa Kumar Roy, Jonathan Li, Pedram Ghamisi

In the domain of remote sensing image interpretation, road extraction from high-resolution aerial imagery has already been a hot research topic.

Segmentation Semantic Segmentation

Effective Document Image Enhancement Using tokens-to-token Transformer Network

1 code implementation Preprint 2023 Risab Biswas, Swalpa Kumar Roy, Umapada Pal

Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokeniza-tion technique to capture this local information from an image for achieving more effective results.

Binarization Image Enhancement

Local Window Attention Transformer for Polarimetric SAR Image Classification

1 code implementation IEEE Geoscience and Remote Sensing Letters 2023 Ali Jamali, Swalpa Kumar Roy, Avik Bhattacharya, Pedram Ghamisi

The PolSARFormer outperformed the Swin Transformer and FNet by the margin of 5. 86% and 17. 63%, in terms of average accuracy in the San Francisco data benchmark.

Classification Earth Observation +1

OCFormer: One-Class Transformer Network for Image Classification

no code implementations25 Apr 2022 Prerana Mukherjee, Chandan Kumar Roy, Swalpa Kumar Roy

We propose a novel deep learning framework based on Vision Transformers (ViT) for one-class classification.

Classification Image Classification +2

Multimodal Fusion Transformer for Remote Sensing Image Classification

2 code implementations31 Mar 2022 Swalpa Kumar Roy, Ankur Deria, Danfeng Hong, Behnood Rasti, Antonio Plaza, Jocelyn Chanussot

Vision transformers (ViTs) have been trending in image classification tasks due to their promising performance when compared to convolutional neural networks (CNNs).

Classification Image Classification +2

Deep Hyperspectral Unmixing using Transformer Network

1 code implementation31 Mar 2022 Preetam Ghosh, Swalpa Kumar Roy, Bikram Koirala, Behnood Rasti, Paul Scheunders

In this article, we harness the power of transformers to conquer the task of hyperspectral unmixing and propose a novel deep unmixing model with transformers.

Decoder Hyperspectral Image Classification +1

Attention Mechanism Meets with Hybrid Dense Network for Hyperspectral Image Classification

no code implementations4 Jan 2022 Muhammad Ahmad, Adil Mehmood Khan, Manuel Mazzara, Salvatore Distefano, Swalpa Kumar Roy, Xin Wu

The resulting \textit{attention-fused hybrid network} (AfNet) is based on three attention-fused parallel hybrid sub-nets with different kernels in each block repeatedly using high-level features to enhance the final ground-truth maps.

Hyperspectral Image Classification

Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification

1 code implementation1 Feb 2021 Swalpa Kumar Roy, Juan M. Haut, Mercedes E. Paoletti, Shiv Ram Dubey, and Antonio Plaza

A different classifier from the generator and the discriminator is used in the 3D-HyperGAMO model, which is trained using both original and generated samples to {determine} the classes of newly generated samples to which they actually belong.

Classification General Classification +2

diffGrad: An Optimization Method for Convolutional Neural Networks

1 code implementation12 Sep 2019 Shiv Ram Dubey, Soumendu Chakraborty, Swalpa Kumar Roy, Snehasis Mukherjee, Satish Kumar Singh, Bidyut Baran Chaudhuri

In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i. e., diffGrad).

Image Categorization

Local Jet Pattern: A Robust Descriptor for Texture Classification

no code implementations26 Nov 2017 Swalpa Kumar Roy, Bhabatosh Chanda, Bidyut. B. Chaudhuri, Dipak Kumar Ghosh, Shiv Ram Dubey

In this approach, a jet space representation of a texture image is derived from a set of derivatives of Gaussian (DtGs) filter responses up to second order, so called local jet vectors (LJV), which also satisfy the Scale Space properties.

Classification General Classification +1

Fractal image compression using upper bound on scaling parameter

1 code implementation14 Nov 2017 Swalpa Kumar Roy, Siddharth Kumar, Bhabatosh Chanda, Bidyut. B. Chaudhuri, Soumitro Banerjee

This paper presents a novel approach to calculate the affine parameters of fractal encoding, in order to reduce its computational complexity.

Image Compression

Cannot find the paper you are looking for? You can Submit a new open access paper.