Search Results for author: Vishal M. Patel

Found 131 papers, 56 papers with code

Utilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection

no code implementations ECCV 2020 Poojan Oza, Vishal M. Patel

For any recognition system, the ability to identify novel class samples during inference is an important aspect of the system’s robustness.

Multiple Class Novelty Detection Under Data Distribution Shift

no code implementations ECCV 2020 Poojan Oza, Hien V. Nguyen, Vishal M. Patel

To this end, we consider the problem of multiple class novelty detection under dataset distribution shift to improve the novelty detection performance.

Domain Adaptation Object Recognition

On Trace of PGD-Like Adversarial Attacks

no code implementations19 May 2022 Mo Zhou, Vishal M. Patel

Thus, we construct Adversarial Response Characteristics (ARC) features to reflect the model's gradient consistency around the input to indicate the extent of linearity.

Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN

no code implementations23 Apr 2022 Rajeev Yasarla, Vishwanath A. Sindagi, Vishal M. Patel

Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training.

Gaussian Processes

A comparison of different atmospheric turbulence simulation methods for image restoration

no code implementations19 Apr 2022 Nithin Gopalakrishnan Nair, Kangfu Mei, Vishal M. Patel

In this paper, we systematically evaluate the effectiveness of various turbulence simulation methods on image restoration.

Face Recognition Image Restoration

Shape-guided Object Inpainting

no code implementations16 Apr 2022 Yu Zeng, Zhe Lin, Vishal M. Patel

Therefore, we propose a new data preparation method and a novel Contextual Object Generator (CogNet) for the object inpainting task.

Image Inpainting

Towards Online Domain Adaptive Object Detection

1 code implementation11 Apr 2022 Vibashan VS, Poojan Oza, Vishal M. Patel

To the best of our knowledge, this is the first work to address online and offline adaptation settings for object detection.

Object Detection Representation Learning +1

Thermal to Visible Image Synthesis under Atmospheric Turbulence

no code implementations6 Apr 2022 Kangfu Mei, Yiqun Mei, Vishal M. Patel

In this paper, we first investigate the problem with a turbulence simulation method on real-world thermal images.

Face Verification Image Generation +1

Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination

no code implementations30 Mar 2022 Yiqun Mei, Pengfei Guo, Vishal M. Patel

In Heterogeneous Face Recognition (HFR), the objective is to match faces across two different domains such as visible and thermal.

Face Generation Face Hallucination +3

Target and Task specific Source-Free Domain Adaptive Image Segmentation

1 code implementation29 Mar 2022 Vibashan VS, Jeya Maria Jose Valanarasu, Vishal M. Patel

To this end, we propose a two-stage approach for source-free domain adaptive image segmentation: 1) Target-specific adaptation followed by 2) Task-specific adaptation.

Denoising Medical Image Segmentation +2

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

1 code implementation29 Mar 2022 Vibashan VS, Poojan Oza, Vishal M. Patel

The Source-Free Domain Adaptation (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.

Knowledge Distillation Object Detection +2

Interactive Portrait Harmonization

no code implementations15 Mar 2022 Jeya Maria Jose Valanarasu, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Jose Echevarria, Yinglan Ma, Zijun Wei, Kalyan Sunkavalli, Vishal M. Patel

To enable flexible interaction between user and harmonization, we introduce interactive harmonization, a new setting where the harmonization is performed with respect to a selected \emph{region} in the reference image instead of the entire background.

On-the-Fly Test-time Adaptation for Medical Image Segmentation

1 code implementation10 Mar 2022 Jeya Maria Jose Valanarasu, Pengfei Guo, Vibashan VS, Vishal M. Patel

During test-time, the model takes in just the new test image and generates a domain code to adapt the features of source model according to the test data.

Medical Image Segmentation Semantic Segmentation

UNeXt: MLP-based Rapid Medical Image Segmentation Network

2 code implementations9 Mar 2022 Jeya Maria Jose Valanarasu, Vishal M. Patel

Using tokenized MLPs in latent space reduces the number of parameters and computational complexity while being able to result in a better representation to help segmentation.

Medical Image Segmentation Semantic Segmentation

HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening

1 code implementation4 Mar 2022 Wele Gedara Chaminda Bandara, Vishal M. Patel

Existing pansharpening approaches neglect using an attention mechanism to transfer HR texture features from PAN to LR-HSI features, resulting in spatial and spectral distortions.

Super-Resolution

Enhancing Adversarial Robustness for Deep Metric Learning

2 code implementations2 Mar 2022 Mo Zhou, Vishal M. Patel

Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved.

Adversarial Robustness Metric Learning

Open-set Adversarial Defense with Clean-Adversarial Mutual Learning

1 code implementation12 Feb 2022 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

This paper proposes an Open-Set Defense Network with Clean-Adversarial Mutual Learning (OSDN-CAML) as a solution to the OSAD problem.

Adversarial Defense Denoising +2

Transformer-based SAR Image Despeckling

1 code implementation23 Jan 2022 Malsha V. Perera, Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel

Synthetic Aperture Radar (SAR) images are usually degraded by a multiplicative noise known as speckle which makes processing and interpretation of SAR images difficult.

Sar Image Despeckling

ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer

1 code implementation23 Jan 2022 Pengfei Guo, Yiqun Mei, Jinyuan Zhou, Shanshan Jiang, Vishal M. Patel

Accelerating magnetic resonance image (MRI) reconstruction process is a challenging ill-posed inverse problem due to the excessive under-sampling operation in k-space.

MRI Reconstruction

A Transformer-Based Siamese Network for Change Detection

1 code implementation4 Jan 2022 Wele Gedara Chaminda Bandara, Vishal M. Patel

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images.

Change Detection

LTT-GAN: Looking Through Turbulence by Inverting GANs

no code implementations4 Dec 2021 Kangfu Mei, Vishal M. Patel

To mitigate the turbulence effect, in this paper, we propose the first turbulence mitigation method that makes use of visual priors encapsulated by a well-trained GAN.

Face Verification

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection

1 code implementation30 Nov 2021 Deepti Hegde, Vishal M. Patel

We demonstrate our approach on two recent object detectors and achieve results that out-perform the other domain adaptation works.

3D Object Detection Unsupervised Domain Adaptation

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

no code implementations30 Nov 2021 Yu Zeng, Zhe Lin, Vishal M. Patel

Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch.

Image Manipulation

Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer

no code implementations18 Nov 2021 Pengfei Guo, Vishal M. Patel

Deep Learning (DL) based methods for magnetic resonance (MR) image reconstruction have been shown to produce superior performance in recent years.

MRI Reconstruction

Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation

no code implementations25 Oct 2021 Rui Shao, Bochao Zhang, Pong C. Yuen, Vishal M. Patel

The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world deployment, which can be improved when models are trained with face images from different input distributions and different types of spoof attacks.

Face Presentation Attack Detection Face Recognition +1

Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning

no code implementations7 Oct 2021 Vibashan VS, Domenick Poster, Suya You, Shuowen Hu, Vishal M. Patel

Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data.

Meta-Learning Object Detection +1

Fine-Context Shadow Detection using Shadow Removal

no code implementations20 Sep 2021 Jeya Maria Jose Valanarasu, Vishal M. Patel

First, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net), where we constraint the receptive field size and focus on low-level features to learn fine context features better.

Shadow Detection And Removal Shadow Removal

SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving

1 code implementation16 Sep 2021 Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel

Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image which is essential to extract road connectivity.

Autonomous Driving Autonomous Navigation +1

Adversarially Robust One-class Novelty Detection

no code implementations25 Aug 2021 Shao-Yuan Lo, Poojan Oza, Vishal M. Patel

To this end, we propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.

Adversarial Robustness

A Synthesis-Based Approach for Thermal-to-Visible Face Verification

no code implementations21 Aug 2021 Neehar Peri, Joshua Gleason, Carlos D. Castillo, Thirimachos Bourlai, Vishal M. Patel, Rama Chellappa

Lastly, we show that our end-to-end thermal-to-visible face verification system provides strong performance on the MILAB-VTF(B) dataset.

Face Alignment Face Generation +1

Image Fusion Transformer

1 code implementation19 Jul 2021 Vibashan VS, Jeya Maria Jose Valanarasu, Poojan Oza, Vishal M. Patel

Furthermore, we show the effectiveness of the proposed ST fusion strategy with an ablation analysis.

Heterogeneous Face Frontalization via Domain Agnostic Learning

no code implementations17 Jul 2021 Xing Di, Shuowen Hu, Vishal M. Patel

We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations.

Face Generation

Over-and-Under Complete Convolutional RNN for MRI Reconstruction

no code implementations16 Jun 2021 Pengfei Guo, Jeya Maria Jose Valanarasu, Puyang Wang, Jinyuan Zhou, Shanshan Jiang, Vishal M. Patel

Reconstructing magnetic resonance (MR) images from undersampled data is a challenging problem due to various artifacts introduced by the under-sampling operation.

MRI Reconstruction

Unsupervised Domain Adaptation of Object Detectors: A Survey

no code implementations27 May 2021 Poojan Oza, Vishwanath A. Sindagi, Vibashan VS, Vishal M. Patel

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection.

Autonomous Navigation Object Detection +2

Federated Generalized Face Presentation Attack Detection

no code implementations14 Apr 2021 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.

Disentanglement Face Presentation Attack Detection +2

Federated Learning-based Active Authentication on Mobile Devices

no code implementations14 Apr 2021 Poojan Oza, Vishal M. Patel

Using FL/SL frameworks, we can alleviate the lack of negative data problem by training a user authentication model over multiple user data distributed across devices.

Federated Learning

Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN

1 code implementation13 Apr 2021 Rakhil Immidisetti, Shuowen Hu, Vishal M. Patel

Existing thermal-to-visible face verification approaches expect the thermal and visible face images to be of similar resolution.

Face Hallucination Face Verification +1

Multimodal Face Synthesis from Visual Attributes

1 code implementation9 Apr 2021 Xing Di, Vishal M. Patel

Extensive experiments and comparisons with several state-of-the-art methods are performed to verify the effectiveness of the proposed attribute-based multimodal synthesis method.

Face Generation

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning

1 code implementation CVPR 2021 Pengfei Guo, Puyang Wang, Jinyuan Zhou, Shanshan Jiang, Vishal M. Patel

However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc.

Federated Learning Image Reconstruction

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation

1 code implementation21 Feb 2021 Jeya Maria Jose Valanarasu, Poojan Oza, Ilker Hacihaliloglu, Vishal M. Patel

The proposed Medical Transformer (MedT) is evaluated on three different medical image segmentation datasets and it is shown that it achieves better performance than the convolutional and other related transformer-based architectures.

Medical Image Segmentation Semantic Segmentation

Error Diffusion Halftoning Against Adversarial Examples

1 code implementation23 Jan 2021 Shao-Yuan Lo, Vishal M. Patel

In this paper, we propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples.

Adversarial Robustness Quantization

One-Class Classification: A Survey

no code implementations8 Jan 2021 Pramuditha Perera, Poojan Oza, Vishal M. Patel

One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class.

Classification General Classification +1

A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset

no code implementations7 Jan 2021 Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Nimpa Fondje, Vishal M. Patel, Nathaniel J. Short, Benjamin S. Riggan, Nasser M. Nasrabadi, Shuowen Hu

Thermal face imagery, which captures the naturally emitted heat from the face, is limited in availability compared to face imagery in the visible spectrum.

Face Verification

CR-Fill: Generative Image Inpainting With Auxiliary Contextual Reconstruction

1 code implementation ICCV 2021 Yu Zeng, Zhe Lin, Huchuan Lu, Vishal M. Patel

The auxiliary branch (i. e. CR loss) is required only during training, and only the inpainting generator is required during the inference.

Image Inpainting

Overcomplete Representations Against Adversarial Videos

1 code implementation8 Dec 2020 Shao-Yuan Lo, Jeya Maria Jose Valanarasu, Vishal M. Patel

Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images.

Adversarial Robustness Video Recognition

CR-Fill: Generative Image Inpainting with Auxiliary Contexutal Reconstruction

1 code implementation25 Nov 2020 Yu Zeng, Zhe Lin, Huchuan Lu, Vishal M. Patel

Due to the lack of supervision signals for the correspondence between missing regions and known regions, it may fail to find proper reference features, which often leads to artifacts in the results.

Image Inpainting

Overcomplete Deep Subspace Clustering Networks

1 code implementation16 Nov 2020 Jeya Maria Jose Valanarasu, Vishal M. Patel

This method uses undercomplete representations of the input data which makes it not so robust and more dependent on pre-training.

Deep Image Compositing

no code implementations4 Nov 2020 He Zhang, Jianming Zhang, Federico Perazzi, Zhe Lin, Vishal M. Patel

In this paper, we propose a new method which can automatically generate high-quality image compositing without any user input.

Image Matting

Exploring Overcomplete Representations for Single Image Deraining using CNNs

1 code implementation20 Oct 2020 Rajeev Yasarla, Jeya Maria Jose Valanarasu, Vishal M. Patel

Removal of rain streaks from a single image is an extremely challenging problem since the rainy images often contain rain streaks of different size, shape, direction and density.

Single Image Deraining

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

1 code implementation4 Oct 2020 Jeya Maria Jose Valanarasu, Vishwanath A. Sindagi, Ilker Hacihaliloglu, Vishal M. Patel

To overcome this issue, we propose using an overcomplete convolutional architecture where we project our input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network.

3D Medical Imaging Segmentation Brain Tumor Segmentation +5

MultAV: Multiplicative Adversarial Videos

no code implementations17 Sep 2020 Shao-Yuan Lo, Vishal M. Patel

In this paper, we propose a novel attack method against video recognition models, Multiplicative Adversarial Videos (MultAV), which imposes perturbation on video data by multiplication.

Adversarial Attack Video Recognition

Defending Against Multiple and Unforeseen Adversarial Videos

no code implementations11 Sep 2020 Shao-Yuan Lo, Vishal M. Patel

With a multiple BN structure, each BN brach is responsible for learning the distribution of a single perturbation type and thus provides more precise distribution estimations.

Adversarial Robustness General Classification +2

Open-set Adversarial Defense

1 code implementation ECCV 2020 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks.

Adversarial Defense Denoising +1

Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas

1 code implementation6 Aug 2020 Pengfei Guo, Puyang Wang, Rajeev Yasarla, Jinyuan Zhou, Vishal M. Patel, Shanshan Jiang

Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images.

Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs

no code implementations16 Jul 2020 Rajeev Yasarla, Vishal M. Patel

Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths.

Anomaly Detection-Based Unknown Face Presentation Attack Detection

1 code implementation11 Jul 2020 Yashasvi Baweja, Poojan Oza, Pramuditha Perera, Vishal M. Patel

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.

Anomaly Detection Face Presentation Attack Detection +1

Learning to Count in the Crowd from Limited Labeled Data

no code implementations ECCV 2020 Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu, R. Venkatesh Babu, Vishal M. Patel

In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data.

Crowd Counting

Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN

1 code implementation26 Jun 2020 Pengfei Guo, Puyang Wang, Jinyuan Zhou, Vishal M. Patel, Shanshan Jiang

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.

Data Augmentation

Quickest Intruder Detection for Multiple User Active Authentication

no code implementations21 Jun 2020 Pramuditha Perera, Julian Fierrez, Vishal M. Patel

In this paper, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users.

Change Detection

KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations

3 code implementations8 Jun 2020 Jeya Maria Jose, Vishwanath Sindagi, Ilker Hacihaliloglu, Vishal M. Patel

Due to its excellent performance, U-Net is the most widely used backbone architecture for biomedical image segmentation in the recent years.

Medical Image Segmentation Semantic Segmentation

Federated Face Presentation Attack Detection

no code implementations29 May 2020 Rui Shao, Pramuditha Perera, Pong C. Yuen, Vishal M. Patel

A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks.

Face Anti-Spoofing Face Presentation Attack Detection +2

Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis

no code implementations20 Apr 2020 Xing Di, Benjamin S. Riggan, Shuowen Hu, Nathaniel J. Short, Vishal M. Patel

Finally, a pre-trained VGG-Face network is leveraged to extract features from the synthesized image and the input visible image for verification.

Face Verification

JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method

no code implementations7 Apr 2020 Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel

The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors.

Crowd Counting

Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data

no code implementations18 Dec 2019 Jeya Maria Jose V., Rajeev Yasarla, Puyang Wang, Ilker Hacihaliloglu, Vishal M. Patel

We show that our method can synthesize high-quality US images for every manipulated segmentation label with qualitative and quantitative improvements over the recent state-of-the-art synthesis methods.

Image Generation

Facial Synthesis from Visual Attributes via Sketch using Multi-Scale Generators

no code implementations17 Dec 2019 Xing Di, Vishal M. Patel

In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.

Face Generation

Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions

no code implementations ECCV 2020 Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel

Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images.

Object Detection

Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method

no code implementations ICCV 2019 Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel

The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors.

Crowd Counting

Confidence Measure Guided Single Image De-raining

no code implementations10 Sep 2019 Rajeev Yasarla, Vishal M. Patel

Single image de-raining is an extremely challenging problem since the rainy images contain rain streaks which often vary in size, direction and density.

Single Image Deraining

Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

1 code implementation30 Jul 2019 Rajeev Yasarla, Federico Perazzi, Vishal M. Patel

We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring.

Deblurring Image Deblurring

HA-CCN: Hierarchical Attention-based Crowd Counting Network

no code implementations24 Jul 2019 Vishwanath A. Sindagi, Vishal M. Patel

The proposed method, which is based on the VGG16 network, consists of a spatial attention module (SAM) and a set of global attention modules (GAM).

Crowd Counting

Inverse Attention Guided Deep Crowd Counting Network

no code implementations2 Jul 2019 Vishwanath A. Sindagi, Vishal M. Patel

In this paper, we address the challenging problem of crowd counting in congested scenes.

Crowd Counting

Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining

1 code implementation CVPR 2019 Rajeev Yasarla, Vishal M. Patel

Previous approaches have attempted to address this problem by leveraging some prior information to remove rain streaks from a single image.

Single Image Deraining

C2AE: Class Conditioned Auto-Encoder for Open-set Recognition

no code implementations CVPR 2019 Poojan Oza, Vishal M. Patel

It refers to the problem of identifying the unknown classes during testing, while maintaining performance on the known classes.

Classification General Classification +2

Deep CNN-based Multi-task Learning for Open-Set Recognition

no code implementations7 Mar 2019 Poojan Oza, Vishal M. Patel

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition.

General Classification Image Classification +2

Deep Transfer Learning for Multiple Class Novelty Detection

1 code implementation CVPR 2019 Pramuditha Perera, Vishal M. Patel

We show that thresholding the maximal activation of the proposed network can be used to identify novel objects effectively.

Transfer Learning

Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier

no code implementations4 Mar 2019 Poojan Oza, Vishal M. Patel

Generally, an active authentication problem is modelled as a one class classification problem due to the unavailability of data from the impostor users.

Classification General Classification +1

One-Class Convolutional Neural Network

4 code implementations24 Jan 2019 Poojan Oza, Vishal M. Patel

We present a novel Convolutional Neural Network (CNN) based approach for one class classification.

Anomaly Detection General Classification

DAFE-FD: Density Aware Feature Enrichment for Face Detection

no code implementations16 Jan 2019 Vishwanath A. Sindagi, Vishal M. Patel

In this work, we approach the problem of small face detection with the motivation of enriching the feature maps using a density map estimation module.

Crowd Counting Density Estimation +1

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training

1 code implementation CVPR 2019 Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel

We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition.

Action Recognition Hand Gesture Recognition +2

Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks

no code implementations12 Dec 2018 He Zhang, Benjamin S. Riggan, Shuowen Hu, Nathaniel J. Short, Vishal M. Patel

Previous approaches utilize either a two-step procedure (visible feature estimation and visible image reconstruction) or an input-level fusion technique, where different Stokes images are concatenated and used as a multi-channel input to synthesize the visible image given the corresponding polarimetric signatures.

Face Generation Face Verification +1

Disentangled Variational Representation for Heterogeneous Face Recognition

no code implementations6 Sep 2018 Xiang Wu, Huaibo Huang, Vishal M. Patel, Ran He, Zhenan Sun

Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms.

Face Recognition Heterogeneous Face Recognition

Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN

no code implementations26 Jun 2018 Puyang Wang, Vishal M. Patel, Ilker Hacihaliloglu

Various imaging artifacts, low signal-to-noise ratio, and bone surfaces appearing several millimeters in thickness have hindered the success of ultrasound (US) guided computer assisted orthopedic surgery procedures.

General Classification

Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results

no code implementations26 Apr 2018 Hajime Nada, Vishwanath A. Sindagi, He Zhang, Vishal M. Patel

In this work, we identify the next set of challenges that requires attention from the research community and collect a new dataset of face images that involve these issues such as weather-based degradations, motion blur, focus blur and several others.

Face Detection Robust Face Recognition

Deep Multimodal Subspace Clustering Networks

1 code implementation17 Apr 2018 Mahdi Abavisani, Vishal M. Patel

In addition to various spatial fusion-based methods, an affinity fusion-based network is also proposed in which the self-expressive layer corresponding to different modalities is enforced to be the same.

Multi-modal Subspace Clustering Multiview Learning +1

Densely Connected Pyramid Dehazing Network

1 code implementation CVPR 2018 He Zhang, Vishal M. Patel

We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together.

Image Dehazing Single Image Dehazing

Generating High Quality Visible Images from SAR Images Using CNNs

no code implementations27 Feb 2018 Puyang Wang, Vishal M. Patel

We propose a novel approach for generating high quality visible-like images from Synthetic Aperture Radar (SAR) images using Deep Convolutional Generative Adversarial Network (GAN) architectures.

Colorization

Density-aware Single Image De-raining using a Multi-stream Dense Network

1 code implementation CVPR 2018 He Zhang, Vishal M. Patel

In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method.

Density Estimation Single Image Deraining

Learning Deep Features for One-Class Classification

5 code implementations16 Jan 2018 Pramuditha Perera, Vishal M. Patel

We propose a deep learning-based solution for the problem of feature learning in one-class classification.

Anomaly Detection Classification +2

Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs

1 code implementation30 Dec 2017 Xing Di, Vishal M. Patel

In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem.

Face Generation

High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks

1 code implementation27 Oct 2017 Lidan Wang, Vishwanath A. Sindagi, Vishal M. Patel

To this end, we propose a novel synthesis framework called Photo-Sketch Synthesis using Multi-Adversarial Networks, (PS2-MAN) that iteratively generates low resolution to high resolution images in an adversarial way.

Face Sketch Synthesis Image Quality Assessment +2

GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks

2 code implementations3 Oct 2017 Xing Di, Vishwanath A. Sindagi, Vishal M. Patel

The primary aim of this work is to demonstrate that information preserved by landmarks (gender in particular) can be further accentuated by leveraging generative models to synthesize corresponding faces.

Face Generation

Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces

no code implementations8 Aug 2017 He Zhang, Vishal M. Patel, Benjamin S. Riggan, Shuowen Hu

Previous approaches utilize a two-step procedure (visible feature estimation and visible image reconstruction) to synthesize the visible image given the corresponding polarimetric thermal image.

Face Generation Face Recognition +2

Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs

no code implementations ICCV 2017 Vishwanath A. Sindagi, Vishal M. Patel

DME is a multi-column architecture-based CNN that aims to generate high-dimensional feature maps from the input image which are fused with the contextual information estimated by GCE and LCE using F-CNN.

Crowd Counting

Synthesis-based Robust Low Resolution Face Recognition

no code implementations10 Jul 2017 Sumit Shekhar, Vishal M. Patel, Rama Chellappa

Recognition of low resolution face images is a challenging problem in many practical face recognition systems.

Dictionary Learning Face Recognition

A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation

1 code implementation5 Jul 2017 Vishwanath A. Sindagi, Vishal M. Patel

Nevertheless, over the last few years, crowd count analysis has evolved from earlier methods that are often limited to small variations in crowd density and scales to the current state-of-the-art methods that have developed the ability to perform successfully on a wide range of scenarios.

Crowd Counting Density Estimation

Hierarchical Multimodal Metric Learning for Multimodal Classification

no code implementations CVPR 2017 Heng Zhang, Vishal M. Patel, Rama Chellappa

The learned metrics can improve multimodal classification accuracy and experimental results on four datasets show that the proposed algorithm outperforms existing learning algorithms based on multiple metrics as well as other approaches tested on these datasets.

Classification General Classification +2

SAR Image Despeckling Using a Convolutional Neural Network

3 code implementations2 Jun 2017 Puyang Wang, He Zhang, Vishal M. Patel

Synthetic Aperture Radar (SAR) images are often contaminated by a multiplicative noise known as speckle.

Sar Image Despeckling

Sparse Representation-based Open Set Recognition

1 code implementation6 May 2017 He Zhang, Vishal M. Patel

We propose a generalized Sparse Representation- based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training.

Classification General Classification +3

Learning from Ambiguously Labeled Face Images

no code implementations15 Feb 2017 Ching-Hui Chen, Vishal M. Patel, Rama Chellappa

To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance.

Matrix Completion

Image De-raining Using a Conditional Generative Adversarial Network

7 code implementations21 Jan 2017 He Zhang, Vishwanath Sindagi, Vishal M. Patel

Hence, it is important to solve the problem of single image de-raining/de-snowing.

Rain Removal

Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks

no code implementations9 May 2016 Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan, Amit Kumar, Ching-Hui Chen, Vishal M. Patel, Carlos D. Castillo, Rama Chellappa

Over the last five years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems.

Face Detection Face Recognition +2

Partial Face Detection for Continuous Authentication

no code implementations30 Mar 2016 Upal Mahbub, Vishal M. Patel, Deepak Chandra, Brandon Barbello, Rama Chellappa

In this paper, a part-based technique for real time detection of users' faces on mobile devices is proposed.

Face Detection Frame

HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

2 code implementations3 Mar 2016 Rajeev Ranjan, Vishal M. Patel, Rama Chellappa

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN).

Face Detection Multi-Task Learning +1

Deep Feature-based Face Detection on Mobile Devices

no code implementations16 Feb 2016 Sayantan Sarkar, Vishal M. Patel, Rama Chellappa

We propose a deep feature-based face detector for mobile devices to detect user's face acquired by the front facing camera.

Face Detection

Optimized Kernel-based Projection Space of Riemannian Manifolds

no code implementations10 Feb 2016 Azadeh Alavi, Vishal M. Patel, Rama Chellappa

Recently, it was shown that embedding such manifolds into a Random Projection Spaces (RPS), rather than RKHS or tangent space, leads to higher classification and clustering performance.

Classification Dictionary Learning +1

Towards the Design of an End-to-End Automated System for Image and Video-based Recognition

no code implementations28 Jan 2016 Rama Chellappa, Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan, Amit Kumar, Vishal M. Patel, Carlos D. Castillo

In this paper, we present a brief history of developments in computer vision and artificial neural networks over the last forty years for the problem of image-based recognition.

Face Verification Object Detection +1

Sequential Score Adaptation with Extreme Value Theory for Robust Railway Track Inspection

1 code implementation20 Oct 2015 Xavier Gibert, Vishal M. Patel, Rama Chellappa

Periodic inspections are necessary to keep railroad tracks in state of good repair and prevent train accidents.

Defect Detection

Deep Multi-task Learning for Railway Track Inspection

no code implementations17 Sep 2015 Xavier Gibert, Vishal M. Patel, Rama Chellappa

Railroad tracks need to be periodically inspected and monitored to ensure safe transportation.

Multi-Task Learning

A Deep Pyramid Deformable Part Model for Face Detection

no code implementations18 Aug 2015 Rajeev Ranjan, Vishal M. Patel, Rama Chellappa

We present a face detection algorithm based on Deformable Part Models and deep pyramidal features.

Face Detection Robust Face Recognition

Unconstrained Face Verification using Deep CNN Features

no code implementations7 Aug 2015 Jun-Cheng Chen, Vishal M. Patel, Rama Chellappa

In this paper, we present an algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset.

Face Verification

Dictionary Learning from Ambiguously Labeled Data

no code implementations CVPR 2013 Yi-Chen Chen, Vishal M. Patel, Jaishanker K. Pillai, Rama Chellappa, P. J. Phillips

We propose a novel dictionary-based learning method for ambiguously labeled multiclass classification, where each training sample has multiple labels and only one of them is the correct label.

Dictionary Learning General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.