Match!
Vishal M. Patel
Johns Hopkins University
Machine learningPattern recognitionComputer visionComputer scienceConvolutional neural network
280Publications
44H-index
7,411Citations
What is this?
Publications 244
Newest
#1Rajeev Yasarla (Johns Hopkins University)H-Index: 3
#2Vishal M. Patel (Johns Hopkins University)H-Index: 44
Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths. Images captured under such condition suffer from a combination of geometric deformation and space varying blur. We present a deep learning-based solution to the problem of restoring a turbulence-degraded face image where prior information regarding the amount of geometric distortion and blur at each location of the face image is first estimated using two separate netwo...
#1Yashasvi Baweja (Johns Hopkins University)
#2Poojan Oza (Johns Hopkins University)H-Index: 4
Last. Vishal M. Patel (Johns Hopkins University)H-Index: 44
view all 4 authors...
Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a...
#1Ahmed Z. Alsinan (RU: Rutgers University)H-Index: 1
#2Vishal M. Patel (Johns Hopkins University)H-Index: 44
Last. Ilker Hacihaliloglu (RU: Rutgers University)H-Index: 12
view all 3 authors...
PURPOSE Real-time, two (2D) and three-dimensional (3D) ultrasound (US) has been investigated as a potential alternative to fluoroscopy imaging in various surgical and non-surgical orthopedic procedures. However, low signal to noise ratio, imaging artifacts and bone surfaces appearing several millimeters (mm) in thickness have hindered the wide spread adaptation of this safe imaging modality. Limited field of view and manual data collection cause additional problems during US-based orthopedic pro...
Source
#1Pengyu Yuan (UH: University of Houston)H-Index: 2
#2Aryan MobinyH-Index: 5
Last. Hien Van NguyenH-Index: 17
view all 9 authors...
Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a network from scratch to combat this issue poses a significant cost. Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process. In this paper, we propose a tAsk-auGmented actIve meta-LEarning (AGILE) method to efficien...
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas for patients with malignant gliomas in neuro-oncology with the help of conventional and advanced molecular MR images. However, the lack of sufficient annotated MRI data has vastly impeded the development of such automatic methods. Conventional data augmentation approaches, including flipping, scaling, rotation, and distortion are not capable of generating data with diverse i...
#1Thomas M StratH-Index: 1
#2Rama ChellappaH-Index: 98
Last. Vishal M. PatelH-Index: 44
view all 3 authors...
Source
In this paper, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users. We extend the Quickest Change Detection (QCD) framework to the multiple-user case and formulate the Multiple-user Quickest Intruder Detection (MQID) algorithm. Furthermore, we extend the algorithm to the data-efficient scenario where intruder detection is carried out with fewer observation samples. We evaluate the effectiveness of the proposed method on two publicly ...
Jun 14, 2020 in CVPR (Computer Vision and Pattern Recognition)
#1Rajeev Yasarla (Johns Hopkins University)H-Index: 3
#2Vishwanath A. Sindagi (Johns Hopkins University)H-Index: 13
Last. Vishal M. Patel (Johns Hopkins University)H-Index: 44
view all 3 authors...
Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in the sense that they can be trained only on fully labeled data. Due to various challenges in obtaining real world fully-labeled image deraining datasets, existing methods are trained only on synthetically generated data and hence, generalize poorly to real-world images. The use of real-world data in training image derain...
1 Citations
Jun 14, 2020 in CVPR (Computer Vision and Pattern Recognition)
#1Pramuditha Perera (Johns Hopkins University)H-Index: 9
#2Vlad I. Morariu (Adobe Systems)H-Index: 21
Last. Vishal M. Patel (Johns Hopkins University)H-Index: 44
view all 7 authors...
We address the problem of open-set recognition, where the goal is to determine if a given sample belongs to one of the classes used for training a model (known classes). The main challenge in open-set recognition is to disentangle open-set samples that produce high class activations from known-set samples. We propose two techniques to force class activations of open-set samples to be low. First, we train a generative model for all known classes and then augment the input with the representation ...
1 Citations
Due to its excellent performance, U-Net is the most widely used backbone architecture for biomedical image segmentation in the recent years. However, in our studies, we observe that there is a considerable performance drop in the case of detecting smaller anatomical landmarks with blurred noisy boundaries. We analyze this issue in detail, and address it by proposing an over-complete architecture (Ki-Net) which involves projecting the data onto higher dimensions (in the spatial sense). This netwo...
12345678910