no code implementations • 1 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.
1 code implementation • 16 Dec 2023 • Wentao Wang, Xuanyao Huang, Tianyang Wang, Swalpa Kumar Roy
This paper explores the image synthesis capabilities of GPT-4, a leading multi-modal large language model.
no code implementations • 6 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.
1 code implementation • 6 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.
1 code implementation • bioRxiv 2023 • Yilun Zhang, Wentao Wang, Jiahui Guan, Deepak Kumar Jain, Tianyang Wang, Swalpa Kumar Roy
Drug-target interactions (DTIs) is essential for advancing pharmaceuticals.
1 code implementation • 9 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.
1 code implementation • 8 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.
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.
Ranked #1 on Binarization on H-DIBCO 2012
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.
no code implementations • 25 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.
1 code implementation • 31 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.
2 code implementations • 31 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).
no code implementations • 4 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.
1 code implementation • 1 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.
2 code implementations • 15 Jan 2021 • Muhammad Ahmad, Sidrah Shabbir, Swalpa Kumar Roy, Danfeng Hong, Xin Wu, Jing Yao, Adil Mehmood Khan, Manuel Mazzara, Salvatore Distefano, Jocelyn Chanussot
Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.
1 code implementation • 24 Dec 2020 • Swalpa Kumar Roy, Suvojit Manna, Tiecheng Song, Lorenzo Bruzzone
Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands.
Ranked #1 on Hyperspectral Image Classification on Kennedy Space Center (Overall Accuracy metric)
1 code implementation • 12 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).
1 code implementation • 18 Feb 2019 • Swalpa Kumar Roy, Gopal Krishna, Shiv Ram Dubey, Bidyut. B. Chaudhuri
This letter proposes a Hybrid Spectral Convolutional Neural Network (HybridSN) for HSI classification.
Ranked #1 on Hyperspectral Image Classification on Salinas Scene
2 code implementations • 1 Jan 2019 • Swalpa Kumar Roy, Suvojit Manna, Shiv Ram Dubey, Bidyut Baran Chaudhuri
The proposed LiSHT is non-parametric and tackles the dying gradient problem.
1 code implementation • 10 Jan 2018 • Swalpa Kumar Roy, Nilavra Bhattacharya, Bhabatosh Chanda, Bidyut. B. Chaudhuri, Dipak Kumar Ghosh
In this paper we propose a novel texture descriptor called Fractal Weighted Local Binary Pattern (FWLBP).
no code implementations • 26 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.
1 code implementation • 14 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.