1 code implementation • 20 Feb 2024 • Yanan Zhao, Yuelong Li, Haichuan Zhang, Vishal Monga, Yonina C. Eldar
Through extensive experimental studies, we verify that our approach achieves competitive performance with state-of-the-art unrolled layer-specific learning and significantly improves over the traditional HQS algorithm.
1 code implementation • 28 Aug 2023 • Amirsaeed Yazdani, Xuelu Li, Vishal Monga
We propose "Maturity-Aware Distribution Breakdown-based Active Learning'' (MADBAL), an AL method that benefits from a hierarchical approach to define a multiview data distribution, which takes into account the different "sample" definitions jointly, hence able to select the most impactful segmentation pixels with comprehensive understanding.
1 code implementation • CVPRW 2023 • Marcos V. Conde, Manuel Kolmet, Tim Seizinger, Tom E. Bishop, Radu Timofte, Xiangyu Kong, Dafeng Zhang, Jinlong Wu, Fan Wang, Juewen Peng, Zhiyu Pan, Chengxin Liu, Xianrui Luo, Huiqiang Sun, Liao Shen, Zhiguo Cao, Ke Xian, Chaowei Liu, Zigeng Chen, Xingyi Yang, Songhua Liu, Yongcheng Jing, Michael Bi Mi, Xinchao Wang, Zhihao Yang, Wenyi Lian, Siyuan Lai, Haichuan Zhang, Trung Hoang, Amirsaeed Yazdani, Vishal Monga, Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön, Yuxuan Zhao, Baoliang Chen, Yiqing Xu, JiXiang Niu
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
no code implementations • 28 Mar 2022 • Yung-Chen Sun, Isaac D. Gerg, Vishal Monga
IDUS is an unsupervised learning framework that can be divided into four main steps: 1) A deep network estimates class assignments.
no code implementations • 17 Mar 2022 • Li Yu, Kareem Metwaly, James Z. Wang, Vishal Monga
Detecting and evaluating surface coating defects is important for marine vessel maintenance.
1 code implementation • CVPR 2022 • Kareem Metwaly, Aerin Kim, Elliot Branson, Vishal Monga
Collectively, the Global-Local-Intrinsic blocks comprehend the scene's global context while attending to the characteristics of the local object of interest.
1 code implementation • 16 Nov 2021 • Kareem Metwaly, Aerin Kim, Elliot Branson, Vishal Monga
We have also created an API for the dataset to ease the usage of CAR.
no code implementations • 15 Aug 2021 • Yuelong Li, Or Bar-Shira, Vishal Monga, Yonina C. Eldar
In this chapter, we review biomedical applications and breakthroughs via leveraging algorithm unrolling, an important technique that bridges between traditional iterative algorithms and modern deep learning techniques.
no code implementations • 30 Jul 2021 • Yung-Chen Sun, Isaac D. Gerg, Vishal Monga
Our results show that the performance of our proposed method is considerably better than current state-of-the-art methods in SAS image segmentation.
1 code implementation • 5 May 2021 • Amirsaeed Yazdani, Tiantong Guo, Vishal Monga
While our proposed method applies to both one-to-one and any-to-any relighting problems, for each case we introduce problem-specific components that enrich the model performance: 1) For one-to-one relighting we incorporate normal vectors of the surfaces in the scene to adjust gloss and shadows accordingly in the image.
Ranked #1 on Image Relighting on VIDIT’20 validation set
no code implementations • 30 Apr 2021 • Amirsaeed Yazdani, Sumit Agrawal, Kerrick Johnstonbaugh, Sri-Rajasekhar Kothapalli, Vishal Monga
The network trained on this novel dataset accurately locates targets in experimental PA data that is clinically relevant with respect to the localization of vessels, needles, or brachytherapy seeds.
no code implementations • 21 Apr 2021 • Amirsaeed Yazdani, Yung-Chen Sun, Nicholas B. Stephens, Timothy Ryan, Vishal Monga
It is common in anthropology and paleontology to address questions about extant and extinct species through the quantification of osteological features observable in micro-computed tomographic (micro-CT) scans.
no code implementations • 18 Mar 2021 • Isaac D. Gerg, Vishal Monga
To improve convergence, a hand-crafted weighting function to remove "bad" areas of the image is sometimes applied to the image-under-test before the optimization procedure.
no code implementations • 29 Oct 2020 • Isaac Gerg, Vishal Monga
In this letter, we demonstrate the potential of machine learning, specifically deep learning, to address the autofocus problem.
no code implementations • 26 Oct 2020 • Isaac D. Gerg, Vishal Monga
Deep learning has been recently shown to improve performance in the domain of synthetic aperture sonar (SAS) image classification.
no code implementations • 7 May 2020 • Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu, Radu Timofte, Jing Liu, Haiyan Wu, Yuan Xie, Yanyun Qu, Lizhuang Ma, Ziling Huang, Qili Deng, Ju-Chin Chao, Tsung-Shan Yang, Peng-Wen Chen, Po-Min Hsu, Tzu-Yi Liao, Chung-En Sun, Pei-Yuan Wu, Jeonghyeok Do, Jongmin Park, Munchurl Kim, Kareem Metwaly, Xuelu Li, Tiantong Guo, Vishal Monga, Mingzhao Yu, Venkateswararao Cherukuri, Shiue-Yuan Chuang, Tsung-Nan Lin, David Lee, Jerome Chang, Zhan-Han Wang, Yu-Bang Chang, Chang-Hong Lin, Yu Dong, Hong-Yu Zhou, Xiangzhen Kong, Sourya Dipta Das, Saikat Dutta, Xuan Zhao, Bing Ouyang, Dennis Estrada, Meiqi Wang, Tianqi Su, Siyi Chen, Bangyong Sun, Vincent Whannou de Dravo, Zhe Yu, Pratik Narang, Aryan Mehra, Navaneeth Raghunath, Murari Mandal
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
no code implementations • 4 Apr 2020 • Xuelu Li, Vishal Monga
Given that images from distinct classes in fine-grained classification share significant features of interest, we present a new deep network architecture that explicitly models shared features and removes their effect to achieve enhanced classification results.
1 code implementation • 22 Dec 2019 • Vishal Monga, Yuelong Li, Yonina C. Eldar
In this article, we review algorithm unrolling for signal and image processing.
no code implementations • 10 Sep 2019 • Venkateswararao Cherukuri, Tiantong Guo, Steve. J. Schiff, Vishal Monga
Sharpness is emphasized by the variance of the Laplacian which we show can be implemented by a fixed feedback layer at the output of the network.
no code implementations • 22 Apr 2019 • Tiantong Guo, Hojjat S. Mousavi, Vishal Monga
As the first contribution, we show that DCT can be integrated into the network structure as a Convolutional DCT (CDCT) layer.
no code implementations • 1 Apr 2019 • Yuelong Li, Mohammad Tofighi, Vishal Monga
We study the problem of image alignment for panoramic stitching.
no code implementations • 9 Feb 2019 • Yuelong Li, Mohammad Tofighi, Junyi Geng, Vishal Monga, Yonina C. Eldar
We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID).
no code implementations • 9 Feb 2019 • Yuelong Li, Mohammad Tofighi, Vishal Monga, Yonina C. Eldar
We first present an iterative algorithm that may be considered a generalization of the traditional total-variation regularization method on the gradient domain, and subsequently unroll the half-quadratic splitting algorithm to construct a neural network.
no code implementations • 21 Jan 2019 • Mohammad Tofighi, Tiantong Guo, Jairam K. P. Vanamala, Vishal Monga
Using a set of canonical cell nuclei shapes, prepared with the help of a domain expert, we develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN).
1 code implementation • 4 Oct 2018 • Tiep Vu, Lam Nguyen, Vishal Monga
Using low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e. g. bomb or mine, has been successfully demonstrated recently.
no code implementations • 10 Sep 2018 • Venkateswararao Cherukuri, Tiantong Guo, Steven J. Schiff, Vishal Monga
High resolution magnetic resonance (MR) images are desired for accurate diagnostics.
no code implementations • 8 Feb 2018 • Hojjat S. Mousavi, Tiantong Guo, Vishal Monga
Single image super-resolution (SR) via deep learning has recently gained significant attention in the literature.
no code implementations • 6 Feb 2018 • Tiantong Guo, Hojjat S. Mousavi, Vishal Monga
Deep learning methods, in particular trained Convolutional Neural Networks (CNNs) have recently been shown to produce compelling state-of-the-art results for single image Super-Resolution (SR).
no code implementations • 16 Jan 2018 • Tiep Vu, Lam Nguyen, Tiantong Guo, Vishal Monga
The classification problem has been firstly, and partially, addressed by sparse representation-based classification (SRC) method which can extract noise from signals and exploit the cross-channel information.
no code implementations • 8 Jan 2018 • John McKay, Isaac Gerg, Vishal Monga
There are many real-world classification problems wherein the issue of data imbalance (the case when a data set contains substantially more samples for one/many classes than the rest) is unavoidable.
no code implementations • 5 Dec 2017 • Mohammad Tofighi, Yuelong Li, Vishal Monga
Blind image deblurring is a particularly challenging inverse problem where the blur kernel is unknown and must be estimated en route to recover the deblurred image.
no code implementations • 7 Jul 2017 • John McKay, Raghu G. Raj, Vishal Monga
The resulting algorithm, fast stochastic HB-MAP (fsHBMAP), takes dramatically fewer operations while retaining high reconstruction quality.
no code implementations • 29 Jun 2017 • John McKay, Isaac Gerg, Vishal Monga, Raghu Raj
Finding mines in Sonar imagery is a significant problem with a great deal of relevance for seafaring military and commercial endeavors.
no code implementations • 26 Jun 2017 • John McKay, Vishal Monga, Raghu G. Raj
Sonar imaging has seen vast improvements over the last few decades due in part to advances in synthetic aperture Sonar (SAS).
no code implementations • 26 Jun 2017 • John McKay, Anne Gelb, Vishal Monga, Raghu Raj
Recent progress in synthetic aperture sonar (SAS) technology and processing has led to significant advances in underwater imaging, outperforming previously common approaches in both accuracy and efficiency.
no code implementations • 8 Dec 2016 • Yuelong Li, Chul Lee, Vishal Monga
For HDR video, a stiff practical challenge presents itself in the form of accurate correspondence estimation of objects between video frames.
2 code implementations • 27 Oct 2016 • Tiep Vu, Vishal Monga
Our dictionary learning framework is hence characterized by both a shared dictionary and particular (class-specific) dictionaries.
no code implementations • 4 Oct 2016 • Hojjat S. Mousavi, Vishal Monga
Sparsity constrained single image super-resolution (SR) has been of much recent interest.
no code implementations • 12 Sep 2016 • Tiep H. Vu, Hojjat S. Mousavi, Vishal Monga
Spike and Slab priors have been of much recent interest in signal processing as a means of inducing sparsity in Bayesian inference.
2 code implementations • 31 Jan 2016 • Tiep H. Vu, Vishal Monga
Despite the fact that different objects possess distinct class-specific features, they also usually share common patterns.
no code implementations • 13 Jan 2016 • John McKay, Vishal Monga, Raghu Raj
We develop a new localized block-based dictionary design that can enable geometric, i. e. pose robustness.
no code implementations • 1 Jan 2016 • John McKay, Raghu Raj, Vishal Monga, Jason Isaacs
Advancements in Sonar image capture have enabled researchers to apply sophisticated object identification algorithms in order to locate targets of interest in images such as mines.
2 code implementations • 16 Jun 2015 • Tiep Huu Vu, Hojjat Seyed Mousavi, Vishal Monga, Arvind UK Rao, Ganesh Rao
In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures.
no code implementations • 16 Feb 2015 • Hojjat S. Mousavi, Vishal Monga, Trac. D. Tran
Essentially, ICR solves a sequence of convex optimization problems such that sequence of solutions converges to a sub-optimal solution of the original hard optimization problem.
no code implementations • 3 Feb 2015 • Tiep H. Vu, Hojjat S. Mousavi, Vishal Monga, UK Arvind Rao, Ganesh Rao
In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structure.
no code implementations • 30 Jan 2015 • Hojjat Seyed Mousavi, Umamahesh Srinivas, Vishal Monga, Yuanming Suo, Minh Dao, Trac. D. Tran
Promising results have been achieved in image classification problems by exploiting the discriminative power of sparse representations for classification (SRC).
no code implementations • 8 Jun 2014 • Yuanming Suo, Minh Dao, Umamahesh Srinivas, Vishal Monga, Trac. D. Tran
Sparsity driven signal processing has gained tremendous popularity in the last decade.
no code implementations • 8 Nov 2011 • Yi Chen, Umamahesh Srinivas, Thong T. Do, Vishal Monga, Trac. D. Tran
We propose a probabilistic graphical model framework to explicitly mine the conditional dependencies between these distinct sparse local features.