1 code implementation • 31 Mar 2024 • Jakaria Rabbi, Johannes Kiechle, Christian Beaulieu, Nilanjan Ray, Dana Cobzas
This research provides valuable insights into the relationship between neurological disorder and hippocampal shape changes in different age groups of MS populations using a Graph VAE with Supervised Contrastive loss.
1 code implementation • 24 Oct 2023 • Rudraksh Kapil, Seyed Mojtaba Marvasti-Zadeh, Nadir Erbilgin, Nilanjan Ray
Accurate detection of individual tree crowns from remote sensing data poses a significant challenge due to the dense nature of forest canopy and the presence of diverse environmental variations, e. g., overlapping canopies, occlusions, and varying lighting conditions.
no code implementations • 3 Aug 2023 • Amir Akbarnejad, Nilanjan Ray, Penny J. Barnes, Gilbert Bigras
In a quest to answer this question, we built a large-scale dataset (185538 images) with reliable measurements for Ki67, ER, PR, and HER2 statuses.
no code implementations • 25 Jul 2023 • Seyed Mojtaba Marvasti-Zadeh, Nilanjan Ray, Nadir Erbilgin
Extensive experiments demonstrate the superior performance of our approach over state-of-the-art SSOD methods.
1 code implementation • 22 Jun 2023 • Ganesh Tata, Katyani Singh, Eric Van Oeveren, Nilanjan Ray
In this work, we propose two sample selection algorithms to train an OCR preprocessor with less than 10% of the original system's OCR engine queries, resulting in more than 60% reduction of the total training time without significant loss of accuracy.
1 code implementation • 23 May 2023 • Abhineet Singh, Ila Jasra, Omar Mouhammed, Nidheesh Dadheech, Nilanjan Ray, James Shapiro
This paper presents advancements in automated early-stage prediction of the success of reprogramming human induced pluripotent stem cells (iPSCs) as a potential source for regenerative cell therapies. The minuscule success rate of iPSC-reprogramming of around $ 0. 01% $ to $ 0. 1% $ makes it labor-intensive, time-consuming, and exorbitantly expensive to generate a stable iPSC line.
no code implementations • 6 Mar 2023 • Fateme Bahri, Nilanjan Ray
In this work, we propose a weakly supervised framework that can perform background subtraction without requiring per-pixel ground-truth labels.
no code implementations • 23 Nov 2022 • Seyed Mojtaba Marvasti-Zadeh, Devin Goodsman, Nilanjan Ray, Nadir Erbilgin
Visual explanation of ``black-box'' models allows researchers in explainable artificial intelligence (XAI) to interpret the model's decisions in a human-understandable manner.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 7 Oct 2022 • Seyed Mojtaba Marvasti-Zadeh, Devin Goodsman, Nilanjan Ray, Nadir Erbilgin
This paper provides a comprehensive review of past and current advances in the early detection of bark beetle-induced tree mortality from three primary perspectives: bark beetle & host interactions, RS, and ML/DL.
no code implementations • 28 Aug 2022 • Ameneh Sheikhjafari, Deepa Krishnaswamy, Michelle Noga, Nilanjan Ray, Kumaradevan Punithakumar
Finally, it is suitable for cardiac data processing, since the nature of this parameterization is to define the deformation field in terms of the radial and rotational components.
1 code implementation • 16 Aug 2022 • Preetam Anbukarasu, Shailesh Nanisetty, Ganesh Tata, Nilanjan Ray
Further, a hybrid pipeline consisting of the upsampler and classifier, followed by a peak detection algorithm was developed.
1 code implementation • 15 Jul 2022 • Rudraksh Kapil, Seyed Mojtaba Marvasti-Zadeh, Devin Goodsman, Nilanjan Ray, Nadir Erbilgin
Bark beetle outbreaks can dramatically impact forest ecosystems and services around the world.
no code implementations • 10 Jul 2022 • Seyed Mojtaba Marvasti-Zadeh, Mohammad N. S. Jahromi, Javad Khaghani, Devin Goodsman, Nilanjan Ray, Nadir Erbilgin
In nature, the collective behavior of animals, such as flying birds is dominated by the interactions between individuals of the same species.
1 code implementation • 10 Feb 2022 • Fateme Bahri, Nilanjan Ray
One of the challenges for background subtraction methods is dynamic background, which constitute stochastic movements in some parts of the background.
1 code implementation • 1 Feb 2022 • Soumyadeep Pal, Matthew Tennant, Nilanjan Ray
We present a postprocessing layer for deformable image registration to make a registration field more diffeomorphic by encouraging Jacobians of the transformation to be positive.
no code implementations • 1 Feb 2022 • Ameneh Sheikhjafari, Michelle Noga, Kumaradevan Punithakumar, Nilanjan Ray
The moving image is warped successively at each resolution and finally aligned to the fixed image; this procedure is recursive in a way that at each resolution, a fully convolutional network (FCN) models a progressive change of deformation for the current warped image.
1 code implementation • NeurIPS 2023 • Amir Akbarnejad, Gilbert Bigras, Nilanjan Ray
Using our method we find out that on 5 datasets, only a subset of those theoretical assumptions are sufficient.
1 code implementation • CVPR 2022 • Sara Elkerdawy, Mostafa Elhoushi, Hong Zhang, Nilanjan Ray
On CIFAR, we reach similar accuracy to SOTA methods with 15% and 24% higher FLOPs reduction.
1 code implementation • 17 May 2021 • Ayantha Randika, Nilanjan Ray, Xiao Xiao, Allegra Latimer
Unlike the previous OCR agnostic preprocessing techniques, the proposed approach approximates the gradient of a particular OCR engine to train a preprocessor module.
Optical Character Recognition Optical Character Recognition (OCR)
1 code implementation • MIDL 2019 • Logan Gilmour, Nilanjan Ray
For very large images, this makes training untenable, as the memory and computation required for activation maps scales quadratically with the side length of an image.
1 code implementation • 27 Jul 2020 • Abhishek Nan, Matthew Tennant, Uriel Rubin, Nilanjan Ray
Autograd-based software packages have recently renewed interest in image registration using homography and other geometric models by gradient descent and optimization, e. g., AirLab and DRMIME.
1 code implementation • 11 Jul 2020 • Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray
LayerPrune presents a set of layer pruning methods based on different criteria that achieve higher latency reduction than filter pruning methods on similar accuracy.
4 code implementations • 20 Mar 2020 • Jakaria Rabbi, Nilanjan Ray, Matthias Schubert, Subir Chowdhury, Dennis Chao
Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance.
1 code implementation • MIDL 2019 • Abhishek Nan, Matthew Tennant, Uriel Rubin, Nilanjan Ray
In this work, we present a novel unsupervised image registration algorithm.
1 code implementation • 24 Oct 2019 • Abhineet Singh, Marcin Pietrasik, Gabriell Natha, Nehla Ghouaiel, Ken Brizel, Nilanjan Ray
Automatic detection of animals that have strayed into human inhabited areas has important security and road safety applications.
1 code implementation • 13 May 2019 • Sara Elkerdawy, Hong Zhang, Nilanjan Ray
This is achieved by removing the least important features with a novel joint end-to-end filter pruning.
no code implementations • 23 Jan 2019 • Sara Elkerdawy, Nilanjan Ray, Hong Zhang
In addition, we achieve 95. 5% and 93. 19% on CompCars on both train-test splits, 70-30 and 50-50, outperforming the other methods by 4. 5% and 8% respectively.
Ranked #1 on Fine-Grained Image Classification on BoxCars116K
2 code implementations • 14 Jan 2019 • Abhineet Singh, Hayden Kalke, Mark Loewen, Nilanjan Ray
This paper deals with the problem of computing surface ice concentration for two different types of ice from digital images of river surface.
1 code implementation • MIDL 2019 • Nhat M. Nguyen, Nilanjan Ray
Differentiable programming is able to combine different functions or programs in a processing pipeline with the goal of applying end-to-end learning or optimization.
no code implementations • 7 Oct 2018 • Yao Xue, Gilbert Bigras, Judith Hugh, Nilanjan Ray
Thanks to the SC/CS recovery algorithm (L1 optimization) that can recover sparse cell locations from the output of CNN.
no code implementations • 3 Aug 2018 • Fateme Bahri, Moein Shakeri, Nilanjan Ray
In this paper, we propose an extension of a state-of-the-art batch MOD method (ILISD) to an online/incremental MOD using unsupervised and generative neural networks, which use illumination invariant image representations.
no code implementations • ICLR 2018 • Nhat M. Nguyen, Nilanjan Ray
Most existing GANs architectures that generate images use transposed convolution or resize-convolution as their upsampling algorithm from lower to higher resolution feature maps in the generator.
3 code implementations • 10 Aug 2017 • Yao Xue, Nilanjan Ray
In this paper, we seek a different route and propose a convolutional neural network (CNN)-based cell detection method that uses encoding of the output pixel space.
no code implementations • 15 Mar 2017 • Homa Foroughi, Moein Shakeri, Nilanjan Ray, Hong Zhang
Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under illumination and pose variations.
no code implementations • 5 Dec 2016 • Homa Foroughi, Nilanjan Ray, Hong Zhang
To address these issues, we propose a joint projection and low-rank dictionary learning method using dual graph constraints (JP-LRDL).
no code implementations • 27 Nov 2016 • Sayan Ghosal, Nilanjan Ray
Next, we minimize this UB-SSD by adjusting both the parameters of the FCNN and the parameters of the deformable model in coordinate descent.
no code implementations • 16 Nov 2016 • Mennatullah Siam, Sepehr Valipour, Martin Jagersand, Nilanjan Ray
This architecture is tested for both binary and semantic video segmentation tasks.
no code implementations • 1 Jun 2016 • Sepehr Valipour, Mennatullah Siam, Martin Jagersand, Nilanjan Ray
Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data.
no code implementations • 24 Mar 2016 • Homa Foroughi, Nilanjan Ray, Hong Zhang
To address this issue, we propose a joint projection and dictionary learning using low-rank regularization and graph constraints (JPDL-LR).