1 code implementation • 20 Apr 2024 • Shyam Varahagiri, Aryaman Sinha, Shiv Ram Dubey, Satish Kumar Singh
Furthermore, to have high classification performance, there should be a strong interaction between the HSI token and the class (CLS) token.
no code implementations • 27 Jan 2024 • Ayush Dubey, Shiv Ram Dubey, Satish Kumar Singh, Wei-Ta Chu
Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image.
no code implementations • 27 Jan 2024 • Trinetra Devkatte, Shiv Ram Dubey, Satish Kumar Singh, Abdenour Hadid
Facial super-resolution/hallucination is an important area of research that seeks to enhance low-resolution facial images for a variety of applications.
no code implementations • 4 Dec 2023 • Neeraj Baghel, Shiv Ram Dubey, Satish Kumar Singh
Motivated from the success of transformers in language and vision applications, we propose a SRTransGAN for image super-resolution using transformer based GAN.
no code implementations • 20 Oct 2023 • Neeraj Baghel, Shiv Ram Dubey, Satish Kumar Singh
The results of the proposed model is improved on an average for $4\times$ super-resolution by 21. 66% in PNSR score and 11. 59% in SSIM score, as compared to the best competitive models.
no code implementations • 17 Feb 2023 • Shiv Ram Dubey, Satish Kumar Singh
This paper presents a comprehensive survey on the developments and advancements in GANs utilizing the Transformer networks for computer vision applications.
1 code implementation • 12 Oct 2022 • Shiv Ram Dubey, Satish Kumar Singh, Bidyut Baran Chaudhuri
In this paper, we propose a novel AdaNorm based SGD optimizers by correcting the norm of gradient in each iteration based on the adaptive training history of gradient norm.
no code implementations • 22 Feb 2022 • Suvidha Tripathi, Satish Kumar Singh, Lee Hwee Kuan
BoVW is used as a feature selector to select most discriminative features among the CNN features.
no code implementations • 22 Feb 2022 • Suvidha Tripathi, Satish Kumar Singh
For polygon like annotation or segmentation, we have used Active Contours whose vertices or snake points move towards the boundary of the object of interest to find the region of minimum energy.
no code implementations • 22 Feb 2022 • Suvidha Tripathi, Satish Kumar Singh
The use of Deep Learning (DL) based methods in medical histopathology images have been one of the most sought after solutions to classify, segment, and detect diseased biopsy samples.
no code implementations • 21 Feb 2022 • Suvidha Tripathi, Satish Kumar Singh
To further strengthen the viability of our architectural approach, we tested our proposed methodology with state of the art deep learning architectures AlexNet, VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 as backbone networks.
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
In this paper a novel hand crafted cascaded asymmetric local pattern (CALP) is proposed for retrieval and recognition facial image.
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
Distinctive information captured by the kernel with limited number of pixel achieves satisfactory recognition and retrieval accuracies on facial images taken under constrained environment (controlled variations in light, pose, expressions, and background).
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
Accuracy of these descriptors depends on the precision of mapping the relationship that exists in the local neighborhood of a facial image into microstructures.
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
The proposed local directional gradient pattern (LDGP) is a 1D local micropattern computed by encoding the relationships between the higher order derivatives of the reference pixel in four distinct directions.
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
The major problem in increasing the local neighbourhood is that, it also increases the feature length of the descriptor.
no code implementations • 3 Jan 2022 • Soumendu Chakraborty, Satish Kumar Singh, Pavan Chakraborty
RTLNP exploits relationships amongst the pixels in local neighborhood of the reference pixel at different angular and radial widths.
no code implementations • 25 Nov 2021 • Vishal Kumar, Albert Mundu, Satish Kumar Singh
We use this post-processing algorithm to add and refine the geometric relationships between object pairs to a prior model.
1 code implementation • 29 Sep 2021 • Shiv Ram Dubey, Satish Kumar Singh, Bidyut Baran Chaudhuri
The most popular and common non-linearity layers are activation functions (AFs), such as Logistic Sigmoid, Tanh, ReLU, ELU, Swish and Mish.
1 code implementation • 26 Sep 2021 • Shiv Ram Dubey, Satish Kumar Singh, Wei-Ta Chu
We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head.
1 code implementation • 26 Sep 2021 • Shiv Ram Dubey, S. H. Shabbeer Basha, Satish Kumar Singh, Bidyut Baran Chaudhuri
Overall, we observe very promising performance improvement of existing optimizers with the proposed AdaInject approach.
no code implementations • 24 Aug 2021 • Dipti Mishra, Satish Kumar Singh, Rajat Kumar Singh
In this work, we propose a two-stage autoencoder based compressor-decompressor framework for compressing malaria RBC cell image patches.
no code implementations • 4 Aug 2021 • Anamika Jain, Satish Kumar Singh, Krishna Pratap Singh
Publicly available dataset MCYT, BHSig260 (contains the image of two regional languages Bengali and Hindi) has been used in this paper to test the effectiveness of the proposed method.
no code implementations • 13 Jul 2021 • Suranjan Goswami, IEEE Student Member, Satish Kumar Singh, Senior Member, Bidyut B. Chaudhuri, Life Fellow, IEEE
As a part of this work, we also present a new and unique database for obtaining the region of interest in thermal images based on an existing thermal visual paired database, containing the Region of Interest on 5 different classes of data.
no code implementations • 5 Jun 2021 • Suvidha Tripathi, Satish Kumar Singh, Hwee Kuan Lee
However, due to patch-based analysis, most of the current methods fail to exploit the underlying spatial relationship among the patches.
no code implementations • 11 Apr 2021 • Dipti Mishra, Satish Kumar Singh, Rajat Kumar Singh
We propose a learning-based compression scheme that envelopes a standard codec between pre and post-processing deep CNNs.
no code implementations • 2 Feb 2021 • Nayaneesh Kumar Mishra, Satish Kumar Singh
A video, instead of an image, as an input can be more useful to solve the challenges of face recognition in real world conditions.
no code implementations • 2 Feb 2021 • Nayaneesh Kumar Mishra, Satish Kumar Singh
In this work, we used video as input to the 3D CNN architectures for capturing both spatial and time domain information from the video for face recognition in real world environment.
no code implementations • 18 Jan 2021 • Suranjan Goswami, Satish Kumar Singh
While thermal optical registered datasets are becoming widely available, most of these works are based on image pairs which are pre-registered.
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).