Search Results for author: Rama Chellappa

Found 155 papers, 37 papers with code

DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection

no code implementations23 May 2023 Jiang Liu, Chun Pong Lau, Rama Chellappa

In this work, we ask: can diffusion models be used to generate adversarial examples to improve both visual quality and attack performance?

Image Generation

Attribute-Guided Encryption with Facial Texture Masking

no code implementations22 May 2023 Chun Pong Lau, Jiang Liu, Rama Chellappa

In this paper, we propose Attribute Guided Encryption with Facial Texture Masking (AGE-FTM) that performs a dual manifold adversarial attack on FR systems to achieve both good visual quality and high black box attack success rates.

Adversarial Attack

The 7th AI City Challenge

no code implementations15 Apr 2023 Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Sanjita Prajapati, Alice Li, Shangru Li, Krishna Kunadharaju, Shenxin Jiang, Rama Chellappa

The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.


MOST: Multiple Object localization with Self-supervised Transformers for object discovery

no code implementations11 Apr 2023 Sai Saketh Rambhatla, Ishan Misra, Rama Chellappa, Abhinav Shrivastava

In this work, we present Multiple Object localization with Self-supervised Transformers (MOST) that uses features of transformers trained using self-supervised learning to localize multiple objects in real world images.

object-detection Object Detection +5

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances

1 code implementation17 Mar 2023 Arun V. Reddy, Ketul Shah, William Paul, Rohita Mocharla, Judy Hoffman, Kapil D. Katyal, Dinesh Manocha, Celso M. de Melo, Rama Chellappa

The dataset is composed of both real and synthetic videos from seven gesture classes, and is intended to support the study of synthetic-to-real domain shift for video-based action recognition.

Action Recognition Domain Adaptation +1

STEPs: Self-Supervised Key Step Extraction from Unlabeled Procedural Videos

no code implementations2 Jan 2023 Anshul Shah, Benjamin Lundell, Harpreet Sawhney, Rama Chellappa

We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and performance.

Optical Flow Estimation Representation Learning +1

A Brief Survey on Person Recognition at a Distance

no code implementations17 Dec 2022 Chrisopher B. Nalty, Neehar Peri, Joshua Gleason, Carlos D. Castillo, Shuowen Hu, Thirimachos Bourlai, Rama Chellappa

Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveillance cameras.

Face Verification Person Recognition +1

Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning

1 code implementation17 Oct 2022 Yuxin Wen, Jonas Geiping, Liam Fowl, Hossein Souri, Rama Chellappa, Micah Goldblum, Tom Goldstein

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates.

Federated Learning Image Classification +2

DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images

no code implementations11 Oct 2022 Cheng Peng, S. Kevin Zhou, Rama Chellappa

Medical image super-resolution (SR) is an active research area that has many potential applications, including reducing scan time, bettering visual understanding, increasing robustness in downstream tasks, etc.

Domain Adaptation Image Super-Resolution

VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment

no code implementations9 Oct 2022 Shraman Pramanick, Li Jing, Sayan Nag, Jiachen Zhu, Hardik Shah, Yann Lecun, Rama Chellappa

Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.

object-detection Object Detection +2

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

no code implementations8 Oct 2022 Yuxiang Guo, Cheng Peng, Chun Pong Lau, Rama Chellappa

In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition.

Gait Recognition

REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition

no code implementations17 Aug 2022 Cheng Peng, Haofu Liao, S. Kevin Zhou, Rama Chellappa

It is a long-standing challenge to reconstruct Cone Beam Computed Tomography (CBCT) of the lung under respiratory motion.

PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images

no code implementations17 Aug 2022 Cheng Peng, Rama Chellappa

We present Progressively Deblurring Radiance Field (PDRF), a novel approach to efficiently reconstruct high quality radiance fields from blurry images.


Scalable Vehicle Re-Identification via Self-Supervision

no code implementations16 May 2022 Pirazh Khorramshahi, Vineet Shenoy, Rama Chellappa

As Computer Vision technologies become more mature for intelligent transportation applications, it is time to ask how efficient and scalable they are for large-scale and real-time deployment.

Vehicle Re-Identification

Where in the World is this Image? Transformer-based Geo-localization in the Wild

1 code implementation29 Apr 2022 Shraman Pramanick, Ewa M. Nowara, Joshua Gleason, Carlos D. Castillo, Rama Chellappa

Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem.

Scene Recognition Semantic Segmentation

Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting

no code implementations16 Apr 2022 Guangxing Han, Long Chen, Jiawei Ma, Shiyuan Huang, Rama Chellappa, Shih-Fu Chang

Our approach is motivated by the high-level conceptual similarity of (metric-based) meta-learning and prompt-based learning to learn generalizable few-shot and zero-shot object detection models respectively without fine-tuning.

Few-Shot Learning Few-Shot Object Detection +3

Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking

no code implementations15 Apr 2022 Pirazh Khorramshahi, Vineet Shenoy, Michael Pack, Rama Chellappa

Multi-camera vehicle tracking is one of the most complicated tasks in Computer Vision as it involves distinct tasks including Vehicle Detection, Tracking, and Re-identification.

Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach

no code implementations12 Jan 2022 Sai Saketh Rambhatla, Saksham Suri, Rama Chellappa, Abhinav Shrivastava

Our algorithm then processes the labeled and un-labeled foreground regions differently, a common practice in semi-supervised methods.

object-detection Object Detection +1

EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Images

no code implementations CVPR 2022 Prithviraj Dhar, Amit Kumar, Kirsten Kaplan, Khushi Gupta, Rakesh Ranjan, Rama Chellappa

To overcome this, we propose Eye Authentication with PAD (EyePAD), a distillation-based method that trains a single network for EA and PAD while reducing the effect of forgetting.

Max-Margin Contrastive Learning

1 code implementation21 Dec 2021 Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence.

Contrastive Learning Representation Learning +1

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection

1 code implementation CVPR 2022 Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi

In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks.

Adversarial Attack Detection Adversarial Defense +4

The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces

1 code implementation31 Oct 2021 Joseph P. Robinson, Can Qin, Ming Shao, Matthew A. Turk, Rama Chellappa, Yun Fu

Recognizing Families In the Wild (RFIW), held as a data challenge in conjunction with the 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG), is a large-scale, multi-track visual kinship recognition evaluation.

Gesture Recognition Retrieval

Self-Denoising Neural Networks for Few Shot Learning

no code implementations26 Oct 2021 Steven Schwarcz, Sai Saketh Rambhatla, Rama Chellappa

This architecture, which we call a Self-Denoising Neural Network (SDNN), can be applied easily to most modern convolutional neural architectures, and can be used as a supplement to many existing few-shot learning techniques.

Action Detection Denoising +1

Identification of Attack-Specific Signatures in Adversarial Examples

no code implementations13 Oct 2021 Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks.

Adversarial Attack

LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network

no code implementations29 Sep 2021 Nitin Balachandran, Jun-Cheng Chen, Rama Chellappa

Face super-resolution is a challenging and highly ill-posed problem since a low-resolution (LR) face image may correspond to multiple high-resolution (HR) ones during the hallucination process and cause a dramatic identity change for the final super-resolved results.

Face Hallucination Super-Resolution

Finding Facial Forgery Artifacts with Parts-Based Detectors

no code implementations21 Sep 2021 Steven Schwarcz, Rama Chellappa

Manipulated videos, especially those where the identity of an individual has been modified using deep neural networks, are becoming an increasingly relevant threat in the modern day.

DeepFake Detection Face Swapping

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

PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

no code implementations ICCV 2021 Prithviraj Dhar, Joshua Gleason, Aniket Roy, Carlos D. Castillo, Rama Chellappa

We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface.

Face Recognition

To Boost or not to Boost: On the Limits of Boosted Neural Networks

no code implementations28 Jul 2021 Sai Saketh Rambhatla, Michael Jones, Rama Chellappa

Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate.

Object Recognition

Hierarchical Video Prediction Using Relational Layouts for Human-Object Interactions

no code implementations CVPR 2021 Navaneeth Bodla, Gaurav Shrivastava, Rama Chellappa, Abhinav Shrivastava

Our work builds on hierarchical video prediction models, which disentangle the video generation process into two stages: predicting a high-level representation, such as pose sequence, and then learning a pose-to-pixels translation model for pixel generation.

Human-Object Interaction Detection Relational Reasoning +3

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

1 code implementation16 Jun 2021 Hossein Souri, Liam Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein

In contrast, the Hidden Trigger Backdoor Attack achieves poisoning without placing a trigger into the training data at all.

Backdoor Attack

Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer

no code implementations16 May 2021 Arthita Ghosh, Max Ehrlich, Larry Davis, Rama Chellappa

Urban material recognition in remote sensing imagery is a highly relevant, yet extremely challenging problem due to the difficulty of obtaining human annotations, especially on low resolution satellite images.

Material Recognition Super-Resolution +1

The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory

no code implementations ICCV 2021 Sai Saketh Rambhatla, Rama Chellappa, Abhinav Shrivastava

We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset.

Cortical Features for Defense Against Adversarial Audio Attacks

1 code implementation30 Jan 2021 Ilya Kavalerov, Ruijie Zheng, Wojciech Czaja, Rama Chellappa

We propose using a computational model of the auditory cortex as a defense against adversarial attacks on audio.

Certified Watermarks for Neural Networks

no code implementations1 Jan 2021 Arpit Amit Bansal, Ping-Yeh Chiang, Michael Curry, Hossein Souri, Rama Chellappa, John P Dickerson, Rajiv Jain, Tom Goldstein

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio.

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

1 code implementation4 Dec 2020 Cheng Peng, Haofu Liao, Gina Wong, Jiebo Luo, Shaohua Kevin Zhou, Rama Chellappa

A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane.

3D-Aware Image Synthesis Anatomy +3

A study of quality and diversity in K+1 GANs

no code implementations NeurIPS Workshop ICBINB 2020 Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

We study the K+1 GAN paradigm which generalizes the canonical true/fake GAN by training a generator with a K+1-ary classifier instead of a binary discriminator.

Pose And Joint-Aware Action Recognition

1 code implementation16 Oct 2020 Anshul Shah, Shlok Mishra, Ankan Bansal, Jun-Cheng Chen, Rama Chellappa, Abhinav Shrivastava

Unlike other modalities, constellation of joints and their motion generate models with succinct human motion information for activity recognition.

Action Classification Action Recognition In Videos +5

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

2 code implementations NeurIPS 2020 Yogesh Balaji, Rama Chellappa, Soheil Feizi

To remedy this issue, robust formulations of OT with unbalanced marginal constraints have previously been proposed.

Domain Adaptation

GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue

no code implementations24 Sep 2020 Pirazh Khorramshahi, Hossein Souri, Rama Chellappa, Soheil Feizi

To tackle this issue, we take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

no code implementations NeurIPS 2020 Wei-An Lin, Chun Pong Lau, Alexander Levine, Rama Chellappa, Soheil Feizi

Using OM-ImageNet, we first show that adversarial training in the latent space of images improves both standard accuracy and robustness to on-manifold attacks.

Adversarial Robustness

Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition

no code implementations14 Jun 2020 Prithviraj Dhar, Joshua Gleason, Hossein Souri, Carlos D. Castillo, Rama Chellappa

Therefore, we present a novel `Adversarial Gender De-biasing algorithm (AGENDA)' to reduce the gender information present in face descriptors obtained from previously trained face recognition networks.

Face Recognition Face Verification +1

Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition

no code implementations12 May 2020 Hui Ding, Peng Zhou, Rama Chellappa

Recognizing the expressions of partially occluded faces is a challenging computer vision problem.

Facial Expression Recognition (FER)

The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification

no code implementations ECCV 2020 Pirazh Khorramshahi, Neehar Peri, Jun-Cheng Chen, Rama Chellappa

In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information.

Vehicle Re-Identification

Spatial Priming for Detecting Human-Object Interactions

no code implementations9 Apr 2020 Ankan Bansal, Sai Saketh Rambhatla, Abhinav Shrivastava, Rama Chellappa

The proposed method consists of a layout module which primes a visual module to predict the type of interaction between a human and an object.

Human-Object Interaction Detection

Recognizing Families In the Wild: White Paper for the 4th Edition Data Challenge

2 code implementations15 Feb 2020 Joseph P. Robinson, Yu Yin, Zaid Khan, Ming Shao, Siyu Xia, Michael Stopa, Samson Timoner, Matthew A. Turk, Rama Chellappa, Yun Fu

Recognizing Families In the Wild (RFIW): an annual large-scale, multi-track automatic kinship recognition evaluation that supports various visual kin-based problems on scales much higher than ever before.

Gesture Recognition Retrieval

cGANs with Multi-Hinge Loss

2 code implementations9 Dec 2019 Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings.

Conditional Image Generation

Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference

1 code implementation23 Nov 2019 Wei-An Lin, Yogesh Balaji, Pouya Samangouei, Rama Chellappa

Additionally, we show how InvGAN can be used to implement reparameterization white-box attacks on projection-based defense mechanisms.

How are attributes expressed in face DCNNs?

no code implementations12 Oct 2019 Prithviraj Dhar, Ankan Bansal, Carlos D. Castillo, Joshua Gleason, P. Jonathon Phillips, Rama Chellappa

In the final fully connected layer of the networks, we found the order of expressivity for facial attributes to be Age > Sex > Yaw.

ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence

no code implementations7 Oct 2019 Chun Pong Lau, Hossein Souri, Rama Chellappa

To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image.

Disentanglement Face Recognition +1

Wasserstein Distance Based Domain Adaptation for Object Detection

no code implementations18 Sep 2019 Pengcheng Xu, Prudhvi Gurram, Gene Whipps, Rama Chellappa

Prior approaches utilize adversarial training based on cross entropy between the source and target domain distributions to learn a shared feature mapping that minimizes the domain gap.

object-detection Object Detection +1

Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement

no code implementations15 Aug 2019 Cheng Peng, Wei-An Lin, Haofu Liao, Rama Chellappa, S. Kevin Zhou

We propose a marginal super-resolution (MSR) approach based on 2D convolutional neural networks (CNNs) for interpolating an anisotropic brain magnetic resonance scan along the highly under-sampled direction, which is assumed to axial without loss of generality.

Semantic Segmentation Super-Resolution

Landmark Detection in Low Resolution Faces with Semi-Supervised Learning

no code implementations30 Jul 2019 Amit Kumar, Rama Chellappa

Landmark detection algorithms trained on high resolution images perform poorly on datasets containing low resolution images.

Face Recognition

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

no code implementations CVPR 2019 Wei-An Lin, Haofu Liao, Cheng Peng, Xiaohang Sun, Jingdan Zhang, Jiebo Luo, Rama Chellappa, Shaohua Kevin Zhou

The linkage between the sigogram and image domains is a novel Radon inversion layer that allows the gradients to back-propagate from the image domain to the sinogram domain during training.

Computed Tomography (CT) Medical Diagnosis +1

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

2 code implementations17 Jun 2019 Ilya Kavalerov, Weilin Li, Wojciech Czaja, Rama Chellappa

Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery.

Anomaly Detection Classification +2

Uncertainty Modeling of Contextual-Connections between Tracklets for Unconstrained Video-based Face Recognition

no code implementations ICCV 2019 Jingxiao Zheng, Ruichi Yu, Jun-Cheng Chen, Boyu Lu, Carlos D. Castillo, Rama Chellappa

In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph.

Face Recognition

Detecting Human-Object Interactions via Functional Generalization

no code implementations5 Apr 2019 Ankan Bansal, Sai Saketh Rambhatla, Abhinav Shrivastava, Rama Chellappa

We present an approach for detecting human-object interactions (HOIs) in images, based on the idea that humans interact with functionally similar objects in a similar manner.

Human-Object Interaction Detection

3DRegNet: A Deep Neural Network for 3D Point Registration

1 code implementation CVPR 2020 G. Dias Pais, Srikumar Ramalingam, Venu Madhav Govindu, Jacinto C. Nascimento, Rama Chellappa, Pedro Miraldo

Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame.


On measuring the iconicity of a face

no code implementations4 Mar 2019 Prithviraj Dhar, Carlos D. Castillo, Rama Chellappa

For a given identity in a face dataset, there are certain iconic images which are more representative of the subject than others.

Face Verification

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation

1 code implementation1 Feb 2019 Yogesh Balaji, Rama Chellappa, Soheil Feizi

Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance.

Clustering Domain Adaptation

An Automatic System for Unconstrained Video-Based Face Recognition

no code implementations10 Dec 2018 Jingxiao Zheng, Rajeev Ranjan, Ching-Hui Chen, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa

In this work, we consider challenging scenarios for unconstrained video-based face recognition from multiple-shot videos and surveillance videos with low-quality frames.

Face Recognition

Recognizing Disguised Faces in the Wild

no code implementations21 Nov 2018 Maneet Singh, Richa Singh, Mayank Vatsa, Nalini Ratha, Rama Chellappa

While upcoming algorithms continue to achieve improved performance, a majority of the face recognition systems are susceptible to failure under disguise variations, one of the most challenging covariate of face recognition.

Disguised Face Verification Face Recognition

Learning without Memorizing

1 code implementation CVPR 2019 Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng, Ziyan Wu, Rama Chellappa

Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model.

Incremental Learning

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

1 code implementation ICLR 2019 Yogesh Balaji, Hamed Hassani, Rama Chellappa, Soheil Feizi

Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs).

An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification

no code implementations16 Aug 2018 Boyu Lu, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa

In this paper, we comprehensively study two covariate related problems for unconstrained face verification: first, how covariates affect the performance of deep neural networks on the large-scale unconstrained face verification problem; second, how to utilize covariates to improve verification performance.

Face Recognition Face Verification

Soft Sampling for Robust Object Detection

1 code implementation18 Jun 2018 Zhe Wu, Navaneeth Bodla, Bharat Singh, Mahyar Najibi, Rama Chellappa, Larry S. Davis

Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.

object-detection Robust Object Detection

Deep Density Clustering of Unconstrained Faces

no code implementations CVPR 2018 Wei-An Lin, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa

In this paper, we consider the problem of grouping a collection of unconstrained face images in which the number of subjects is not known.


Zero-Shot Object Detection

no code implementations ECCV 2018 Ankan Bansal, Karan Sikka, Gaurav Sharma, Rama Chellappa, Ajay Divakaran

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training.

object-detection Zero-Shot Learning +1

Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition

no code implementations3 Apr 2018 Rajeev Ranjan, Ankan Bansal, Hongyu Xu, Swami Sankaranarayanan, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa

We show that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems.

Face Verification

Face-MagNet: Magnifying Feature Maps to Detect Small Faces

1 code implementation14 Mar 2018 Pouya Samangouei, Mahyar Najibi, Larry Davis, Rama Chellappa

In this paper, we introduce the Face Magnifier Network (Face-MageNet), a face detector based on the Faster-RCNN framework which enables the flow of discriminative information of small scale faces to the classifier without any skip or residual connections.

Face Detection Region Proposal

Task-Aware Compressed Sensing with Generative Adversarial Networks

1 code implementation5 Feb 2018 Maya Kabkab, Pouya Samangouei, Rama Chellappa

We propose to train the GANs in a task-aware fashion, specifically for reconstruction tasks.

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

no code implementations31 Jan 2018 Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikainen

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention.

General Classification Texture Classification

Semi-supervised FusedGAN for Conditional Image Generation

no code implementations ECCV 2018 Navaneeth Bodla, Gang Hua, Rama Chellappa

We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation.

Conditional Image Generation Face Generation +1

Segment-based Methods for Facial Attribute Detection from Partial Faces

no code implementations10 Jan 2018 Upal Mahbub, Sayantan Sarkar, Rama Chellappa

Taking several facial segments and the full face as input, the proposed method takes a data driven approach to determine which attributes are localized in which facial segments.

Improving Network Robustness against Adversarial Attacks with Compact Convolution

no code implementations3 Dec 2017 Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo, Rama Chellappa

In particular, we show that learning features in a closed and bounded space improves the robustness of the network.

Face Verification

A Deep Cascade Network for Unaligned Face Attribute Classification

no code implementations12 Sep 2017 Hui Ding, Hao Zhou, Shaohua Kevin Zhou, Rama Chellappa

First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes.

Classification General Classification +1

ExprGAN: Facial Expression Editing with Controllable Expression Intensity

2 code implementations12 Sep 2017 Hui Ding, Kumar Sricharan, Rama Chellappa

To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity.

Data Augmentation Image Retrieval +2

SSH: Single Stage Headless Face Detector

6 code implementations ICCV 2017 Mahyar Najibi, Pouya Samangouei, Rama Chellappa, Larry Davis

Surprisingly, with a headless VGG-16, SSH beats the ResNet-101-based state-of-the-art on the WIDER dataset.

General Classification

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

UPSET and ANGRI : Breaking High Performance Image Classifiers

no code implementations4 Jul 2017 Sayantan Sarkar, Ankan Bansal, Upal Mahbub, Rama Chellappa

In this paper, targeted fooling of high performance image classifiers is achieved by developing two novel attack methods.

Vocal Bursts Intensity Prediction

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 +3

Regularizing deep networks using efficient layerwise adversarial training

no code implementations22 May 2017 Swami Sankaranarayanan, Arpit Jain, Rama Chellappa, Ser Nam Lim

In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations as a regularizer during training.

The Do's and Don'ts for CNN-based Face Verification

no code implementations21 May 2017 Ankan Bansal, Carlos Castillo, Rajeev Ranjan, Rama Chellappa

While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answered.

Face Recognition Face Verification

Soft-NMS -- Improving Object Detection With One Line of Code

8 code implementations ICCV 2017 Navaneeth Bodla, Bharat Singh, Rama Chellappa, Larry S. Davis

To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.

object-detection Object Detection

Partial Face Detection in the Mobile Domain

no code implementations7 Apr 2017 Upal Mahbub, Sayantan Sarkar, Rama Chellappa

The three detectors following this approach, namely Facial Segment-based Face Detector (FSFD), SegFace and DeepSegFace, discussed in this paper, perform binary classification on each proposal based on features learned from facial segments.

Binary Classification Data Augmentation +3

A Convolution Tree with Deconvolution Branches: Exploiting Geometric Relationships for Single Shot Keypoint Detection

no code implementations6 Apr 2017 Amit Kumar, Rama Chellappa

Different from existing approaches of modeling these relationships, we propose learnable transform functions which captures the relationships between keypoints at feature level.

Face Alignment Keypoint Detection

L2-constrained Softmax Loss for Discriminative Face Verification

1 code implementation28 Mar 2017 Rajeev Ranjan, Carlos D. Castillo, Rama Chellappa

In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs).

Face Verification

A Proximity-Aware Hierarchical Clustering of Faces

no code implementations14 Mar 2017 Wei-An Lin, Jun-Cheng Chen, Rama Chellappa

In this paper, we propose an unsupervised face clustering algorithm called "Proximity-Aware Hierarchical Clustering" (PAHC) that exploits the local structure of deep representations.

Clustering Face Clustering +1

KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors

no code implementations16 Feb 2017 Amit Kumar, Azadeh Alavi, Rama Chellappa

In this paper, we show that without using any 3D information, KEPLER outperforms state of the art methods for alignment on challenging datasets such as AFW and AFLW.

Face Alignment Head Pose Estimation +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

Deep Heterogeneous Feature Fusion for Template-Based Face Recognition

no code implementations15 Feb 2017 Navaneeth Bodla, Jingxiao Zheng, Hongyu Xu, Jun-Cheng Chen, Carlos Castillo, Rama Chellappa

Thus, in this work, we propose a deep heterogeneous feature fusion network to exploit the complementary information present in features generated by different deep convolutional neural networks (DCNNs) for template-based face recognition, where a template refers to a set of still face images or video frames from different sources which introduces more blur, pose, illumination and other variations than traditional face datasets.

Face Recognition Face Verification

Designing Deep Convolutional Neural Networks for Continuous Object Orientation Estimation

no code implementations6 Feb 2017 Kota Hara, Raviteja Vemulapalli, Rama Chellappa

The third method works by first converting the continuous orientation estimation task into a set of discrete orientation estimation tasks and then converting the discrete orientation outputs back to the continuous orientation using a mean-shift algorithm.

Pooling Facial Segments to Face: The Shallow and Deep Ends

no code implementations29 Jan 2017 Upal Mahbub, Sayantan Sarkar, Rama Chellappa

One promising technique to handle the challenge of partial faces is to design face detectors based on facial segments.

Data Augmentation Face Detection

UMDFaces: An Annotated Face Dataset for Training Deep Networks

no code implementations4 Nov 2016 Ankan Bansal, Anirudh Nanduri, Carlos Castillo, Rajeev Ranjan, Rama Chellappa

Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, and (ii) larger datasets.

Face Detection Face Recognition +1

An All-In-One Convolutional Neural Network for Face Analysis

1 code implementation3 Nov 2016 Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo, Rama Chellappa

The proposed method employs a multi-task learning framework that regularizes the shared parameters of CNN and builds a synergy among different domains and tasks.

Age Estimation Face Alignment +5

PATH: Person Authentication using Trace Histories

no code implementations25 Oct 2016 Upal Mahbub, Rama Chellappa

In this paper, a solution to the problem of Active Authentication using trace histories is addressed.

DCNNs on a Diet: Sampling Strategies for Reducing the Training Set Size

no code implementations14 Jun 2016 Maya Kabkab, Azadeh Alavi, Rama Chellappa

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance.

General Classification

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 +3

Convolutional Neural Networks for Attribute-based Active Authentication on Mobile Devices

no code implementations29 Apr 2016 Pouya Samangouei, Rama Chellappa

We present a Deep Convolutional Neural Network (DCNN) architecture for the task of continuous authentication on mobile devices.

Attributes for Improved Attributes: A Multi-Task Network for Attribute Classification

no code implementations25 Apr 2016 Emily M. Hand, Rama Chellappa

Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification.

Activity Recognition Face Verification +1

Triplet Probabilistic Embedding for Face Verification and Clustering

2 code implementations19 Apr 2016 Swami Sankaranarayanan, Azadeh Alavi, Carlos Castillo, Rama Chellappa

Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem.

Clustering Face Verification

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

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 Clustering +2

Triplet Similarity Embedding for Face Verification

no code implementations10 Feb 2016 Swami Sankaranarayanan, Azadeh Alavi, Rama Chellappa

In this work, we present an unconstrained face verification algorithm and evaluate it on the recently released IJB-A dataset that aims to push the boundaries of face verification methods.

Face Verification

Face Alignment by Local Deep Descriptor Regression

no code implementations29 Jan 2016 Amit Kumar, Rajeev Ranjan, Vishal Patel, Rama Chellappa

We also present a face alignment algorithm based on regression using these local descriptors.

Face Alignment regression

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 +2

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

Class Consistent Multi-Modal Fusion With Binary Features

no code implementations CVPR 2015 Ashish Shrivastava, Mohammad Rastegari, Sumit Shekhar, Rama Chellappa, Larry S. Davis

Many existing recognition algorithms combine different modalities based on training accuracy but do not consider the possibility of noise at test time.

Submodular Attribute Selection for Action Recognition in Video

no code implementations NeurIPS 2014 Jingjing Zheng, Zhuolin Jiang, Rama Chellappa, Jonathon P. Phillips

In real-world action recognition problems, low-level features cannot adequately characterize the rich spatial-temporal structures in action videos.

Action Recognition Dictionary Learning +1

MKL-RT: Multiple Kernel Learning for Ratio-trace Problems via Convex Optimization

no code implementations16 Oct 2014 Raviteja Vemulapalli, Vinay Praneeth Boda, Rama Chellappa

We experimentally demonstrate that the proposed MKL approach, which we refer to as MKL-RT, can be successfully used to select features for discriminative dimensionality reduction and cross-modal retrieval.

Cross-Modal Retrieval Dimensionality Reduction +1

Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group

1 code implementation 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014 Raviteja Vemulapalli, Felipe Arrate, Rama Chellappa

Recently introduced cost-effective depth sensors coupled with the real-time skeleton estimation algorithm of Shotton et al. have generated a renewed interest in skeleton-based human action recognition.

Action Recognition Dynamic Time Warping +3

Adaptive-Rate Compressive Sensing Using Side Information

no code implementations3 Jan 2014 Garrett Warnell, Sourabh Bhattacharya, Rama Chellappa, Tamer Basar

We provide two novel adaptive-rate compressive sensing (CS) strategies for sparse, time-varying signals using side information.

Compressive Sensing

Growing Regression Forests by Classification: Applications to Object Pose Estimation

no code implementations22 Dec 2013 Kota Hara, Rama Chellappa

We apply the regression forest employing our node splitting to head pose estimation (Euclidean target space) and car direction estimation (circular target space) and demonstrate that the proposed method significantly outperforms state-of-the-art methods (38. 5% and 22. 5% error reduction respectively).

General Classification Head Pose Estimation +1

Compositional Dictionaries for Domain Adaptive Face Recognition

no code implementations1 Aug 2013 Qiang Qiu, Rama Chellappa

This approach has three advantages: first, the extracted sparse representation for a subject is consistent across domains and enables pose and illumination insensitive face recognition.

Dictionary Learning Face Recognition

Sparse Dictionary-based Attributes for Action Recognition and Summarization

no code implementations1 Aug 2013 Qiang Qiu, Zhuolin Jiang, Rama Chellappa

We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes.

Action Recognition Dictionary Learning +1

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

Kernel Learning for Extrinsic Classification of Manifold Features

no code implementations CVPR 2013 Raviteja Vemulapalli, Jaishanker K. Pillai, Rama Chellappa

In this paper, we address the issue of kernelselection for the classification of features that lie on Riemannian manifolds using the kernel learning approach.

Activity Recognition Classification +1

Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation

no code implementations CVPR 2013 Jie Ni, Qiang Qiu, Rama Chellappa

Domain adaptation addresses the problem where data instances of a source domain have different distributions from that of a target domain, which occurs frequently in many real life scenarios.

Dictionary Learning Face Recognition +2

Compressive Acquisition of Dynamic Scenes

no code implementations23 Jan 2012 Aswin C. Sankaranarayanan, Pavan K Turaga, Rama Chellappa, Richard G. Baraniuk

Compressive sensing (CS) is a new approach for the acquisition and recovery of sparse signals and images that enables sampling rates significantly below the classical Nyquist rate.

Compressive Sensing

Manifold Precis: An Annealing Technique for Diverse Sampling of Manifolds

no code implementations NeurIPS 2011 Nitesh Shroff, Pavan Turaga, Rama Chellappa

In this paper, we consider the 'Precis' problem of sampling K representative yet diverse data points from a large dataset.

Document Summarization

Large-Scale Matrix Factorization with Missing Data under Additional Constraints

no code implementations NeurIPS 2010 Kaushik Mitra, Sameer Sheorey, Rama Chellappa

We further demonstrate the effectiveness of the proposed algorithm in solving the affine SfM problem, non-rigid SfM and photometric stereo problems.

Matrix Completion

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