Search Results for author: Richa Singh

Found 63 papers, 9 papers with code

Low-Resolution Chest X-ray Classification via Knowledge Distillation and Multi-task Learning

no code implementations22 May 2024 Yasmeena Akhter, Rishabh Ranjan, Richa Singh, Mayank Vatsa

This research addresses the challenges of diagnosing chest X-rays (CXRs) at low resolutions, a common limitation in resource-constrained healthcare settings.

Knowledge Distillation Multi-Task Learning

Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations

1 code implementation29 Mar 2024 Jaisidh Singh, Ishaan Shrivastava, Mayank Vatsa, Richa Singh, Aparna Bharati

Using CC-Neg along with modifications to the contrastive loss of CLIP, our proposed CoN-CLIP framework, has an improved understanding of negations.

Image Classification Zero-Shot Image Classification

Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration

no code implementations16 Feb 2024 Mahapara Khurshid, Mayank Vatsa, Richa Singh

The rising global prevalence of skin conditions, some of which can escalate to life-threatening stages if not timely diagnosed and treated, presents a significant healthcare challenge.

Lesion Classification Skin Lesion Classification +1

ToonerGAN: Reinforcing GANs for Obfuscating Automated Facial Indexing

no code implementations CVPR 2024 Kartik Thakral, Shashikant Prasad, Stuti Aswani, Mayank Vatsa, Richa Singh

The rapid evolution of automatic facial indexing tech- nologies increases the risk of compromising personal and sensitive information.

De-identification

Adventures of Trustworthy Vision-Language Models: A Survey

no code implementations7 Dec 2023 Mayank Vatsa, Anubhooti Jain, Richa Singh

Recently, transformers have become incredibly popular in computer vision and vision-language tasks.

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms

no code implementations24 Oct 2023 Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner

However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development.

Fairness

Multi-task Explainable Skin Lesion Classification

no code implementations11 Oct 2023 Mahapara Khurshid, Mayank Vatsa, Richa Singh

The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.

Classification Lesion Classification +2

DF-Platter: Multi-Face Heterogeneous Deepfake Dataset

no code implementations the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 Kartik Narayan, Harsh Agarwal, Kartik Thakral, Surbhi Mittal, Mayank Vatsa, Richa Singh

In this research, we emulate the real-world scenario of deepfake generation and spreading, and propose the DF-Platter dataset, which contains (i) both low-resolution and high-resolution deepfakes generated using multiple generation techniques and (ii) single-subject and multiple-subject deepfakes, with face images of Indian ethnicity.

DeepFake Detection Face Swapping

Are Face Detection Models Biased?

no code implementations7 Nov 2022 Surbhi Mittal, Kartik Thakral, Puspita Majumdar, Mayank Vatsa, Richa Singh

Since facial region localization is an essential task for all face recognition pipelines, it is imperative to analyze the presence of such bias in popular deep models.

Attribute Binary Classification +2

DeePhy: On Deepfake Phylogeny

no code implementations19 Sep 2022 Kartik Narayan, Harsh Agarwal, Kartik Thakral, Surbhi Mittal, Mayank Vatsa, Richa Singh

In order to enable the research community to address these questions, this paper proposes DeePhy, a novel Deepfake Phylogeny dataset which consists of 5040 deepfake videos generated using three different generation techniques.

DeepFake Detection Face Swapping

On Biased Behavior of GANs for Face Verification

1 code implementation27 Aug 2022 Sasikanth Kotti, Mayank Vatsa, Richa Singh

Datasets for training face verification systems are difficult to obtain and prone to privacy issues.

Attribute Face Verification +1

Anatomizing Bias in Facial Analysis

no code implementations13 Dec 2021 Richa Singh, Puspita Majumdar, Surbhi Mittal, Mayank Vatsa

In this paper, we encapsulate bias detection/estimation and mitigation algorithms for facial analysis.

Bias Detection

On-board Fault Diagnosis of a Laboratory Mini SR-30 Gas Turbine Engine

no code implementations17 Oct 2021 Richa Singh

Inspired by recent progress in machine learning, a data-driven fault diagnosis and isolation (FDI) scheme is explicitly developed for failure in the fuel supply system and sensor measurements of the laboratory gas turbine system.

BIG-bench Machine Learning

MTCD: Cataract Detection via Near Infrared Eye Images

no code implementations6 Oct 2021 Pavani Tripathi, Yasmeena Akhter, Mahapara Khurshid, Aditya Lakra, Rohit Keshari, Mayank Vatsa, Richa Singh

We present deep learning-based eye segmentation and multitask network classification networks for cataract detection using NIR images as input.

Classification Iris Recognition

MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection

no code implementations15 Sep 2021 Aayushi Agarwal, Akshay Agarwal, Sayan Sinha, Mayank Vatsa, Richa Singh

MD-CSDNetwork is a novel cross-stitched network with two parallel branches carrying the spatial and frequency information, respectively.

DeepFake Detection Face Swapping

Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models

1 code implementation14 Aug 2021 Puspita Majumdar, Surbhi Mittal, Richa Singh, Mayank Vatsa

We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions across different \textit{gender} and \textit{race} subgroups.

Face Recognition

Indian Masked Faces in the Wild Dataset

no code implementations17 Jun 2021 Shiksha Mishra, Puspita Majumdar, Richa Singh, Mayank Vatsa

We have also benchmarked the performance of existing face recognition models on the proposed IMFW dataset.

Diversity Face Recognition

Enhancing Fine-Grained Classification for Low Resolution Images

no code implementations1 May 2021 Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh

While fine-grained classification with high resolution images has received significant attention, limited attention has been given to low resolution images.

Attribute Classification +1

Class Equilibrium using Coulomb's Law

no code implementations25 Apr 2021 Saheb Chhabra, Puspita Majumdar, Mayank Vatsa, Richa Singh

Projection algorithms learn a transformation function to project the data from input space to the feature space, with the objective of increasing the inter-class distance.

Age Gap Reducer-GAN for Recognizing Age-Separated Faces

no code implementations11 Nov 2020 Daksha Yadav, Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore

In this paper, we propose a novel algorithm for matching faces with temporal variations caused due to age progression.

Age Estimation Face Recognition +2

Trustworthy AI

no code implementations2 Nov 2020 Richa Singh, Mayank Vatsa, Nalini Ratha

Modern AI systems are reaping the advantage of novel learning methods.

Fairness

WaveTransform: Crafting Adversarial Examples via Input Decomposition

no code implementations29 Oct 2020 Divyam Anshumaan, Akshay Agarwal, Mayank Vatsa, Richa Singh

Experiments are performed using multiple databases and CNN models to establish the effectiveness of the proposed WaveTransform attack and analyze the importance of a particular frequency component.

Adversarial Defense Object Recognition +1

Attack Agnostic Adversarial Defense via Visual Imperceptible Bound

no code implementations25 Oct 2020 Saheb Chhabra, Akshay Agarwal, Richa Singh, Mayank Vatsa

However, the lack of generalizability of existing defense algorithms and the high variability in the performance of the attack algorithms for different databases raises several questions on the effectiveness of the defense algorithms.

Adversarial Defense

MixNet for Generalized Face Presentation Attack Detection

1 code implementation25 Oct 2020 Nilay Sanghvi, Sushant Kumar Singh, Akshay Agarwal, Mayank Vatsa, Richa Singh

The major problem with existing work is the generalizability against multiple attacks both in the seen and unseen setting.

Face Presentation Attack Detection Face Recognition

Unravelling Small Sample Size Problems in the Deep Learning World

no code implementations8 Aug 2020 Rohit Keshari, Soumyadeep Ghosh, Saheb Chhabra, Mayank Vatsa, Richa Singh

However, there are a lot of \textit{small sample size or $S^3$} problems for which it is not feasible to collect large training databases.

Subclass Contrastive Loss for Injured Face Recognition

no code implementations5 Aug 2020 Puspita Majumdar, Saheb Chhabra, Richa Singh, Mayank Vatsa

Deaths and injuries are common in road accidents, violence, and natural disaster.

Face Recognition

Generalized Zero-Shot Learning Via Over-Complete Distribution

1 code implementation CVPR 2020 Rohit Keshari, Richa Singh, Mayank Vatsa

A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes.

Generalized Zero-Shot Learning

On the Robustness of Face Recognition Algorithms Against Attacks and Bias

no code implementations7 Feb 2020 Richa Singh, Akshay Agarwal, Maneet Singh, Shruti Nagpal, Mayank Vatsa

Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications.

Face Recognition

Detecting Face2Face Facial Reenactment in Videos

1 code implementation21 Jan 2020 Prabhat Kumar, Mayank Vatsa, Richa Singh

This has led to an increase in alterations in images and videos to make them more informative and eye-catching for the viewers worldwide.

AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework

no code implementations26 Nov 2019 Raunak Sinha, Anush Sankaran, Mayank Vatsa, Richa Singh

Five different GAN models are implemented as a part of this framework and the performance of the different GAN models are shown using the benchmark MNIST dataset.

Dual Directed Capsule Network for Very Low Resolution Image Recognition

no code implementations ICCV 2019 Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa

The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model.

Face Recognition

On Learning Density Aware Embeddings

no code implementations CVPR 2019 Soumyadeep Ghosh, Richa Singh, Mayank Vatsa

The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class.

Face Recognition Metric Learning +1

Deep Learning for Face Recognition: Pride or Prejudiced?

no code implementations2 Apr 2019 Shruti Nagpal, Maneet Singh, Richa Singh, Mayank Vatsa

This research attempts to answer these questions and presents an in-depth analysis of `bias' in deep learning based face recognition systems.

Face Recognition

A Comprehensive Overview of Biometric Fusion

no code implementations8 Feb 2019 Maneet Singh, Richa Singh, Arun Ross

A comprehensive review of techniques incorporating ancillary information in the biometric recognition pipeline is also presented.

On Detecting GANs and Retouching based Synthetic Alterations

no code implementations26 Jan 2019 Anubhav Jain, Richa Singh, Mayank Vatsa

For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99. 83%.

Face Recognition

Data Fine-tuning

no code implementations10 Dec 2018 Saheb Chhabra, Puspita Majumdar, Mayank Vatsa, Richa Singh

Stimulated by the advances in adversarial perturbations, this research proposes the concept of Data Fine-tuning to improve the classification accuracy of a given model without changing the parameters of the model.

Attribute Emotion Recognition +2

Guided Dropout

no code implementations10 Dec 2018 Rohit Keshari, Richa Singh, Mayank Vatsa

Dropout is often used in deep neural networks to prevent over-fitting.

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

On Matching Faces with Alterations due to Plastic Surgery and Disguise

no code implementations18 Nov 2018 Saksham Suri, Anush Sankaran, Mayank Vatsa, Richa Singh

In this paper, a novel framework is proposed which transfers fundamental visual features learnt from a generic image dataset to supplement a supervised face recognition model.

Face Recognition

Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!

no code implementations15 Oct 2018 Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore

In this paper, we propose a novel Supervised COSMOS Autoencoder which utilizes a multi-objective loss function to learn representations that simultaneously encode the (i) "similarity" between the input and reconstructed vectors in terms of their direction, (ii) "distribution" of pixel values of the reconstruction with respect to the input sample, while also incorporating (iii) "discriminability" in the feature learning pipeline.

Attribute Face Recognition +1

Learning A Shared Transform Model for Skull to Digital Face Image Matching

no code implementations14 Aug 2018 Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Afzel Noore

Human skull identification is an arduous task, traditionally requiring the expertise of forensic artists and anthropologists.

Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos

no code implementations30 May 2018 Naman Kohli, Daksha Yadav, Mayank Vatsa, Richa Singh, Afzel Noore

In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE).

Kinship Verification

Hierarchical Representation Learning for Kinship Verification

no code implementations27 May 2018 Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar

Utilizing the information obtained from the human study, a hierarchical Kinship Verification via Representation Learning (KVRL) framework is utilized to learn the representation of different face regions in an unsupervised manner.

Face Verification Kinship Verification +1

Anonymizing k-Facial Attributes via Adversarial Perturbations

no code implementations23 May 2018 Saheb Chhabra, Richa Singh, Mayank Vatsa, Gaurav Gupta

A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age.

Attribute

Learning Structure and Strength of CNN Filters for Small Sample Size Training

no code implementations CVPR 2018 Rohit Keshari, Mayank Vatsa, Richa Singh, Afzel Noore

The architecture provides the flexibility of training with both small and large training databases and yields good accuracies even with small size training data.

Face Recognition

Are you eligible? Predicting adulthood from face images via class specific mean autoencoder

no code implementations20 Mar 2018 Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh

Predicting if a person is an adult or a minor has several applications such as inspecting underage driving, preventing purchase of alcohol and tobacco by minors, and granting restricted access.

General Classification

Residual Codean Autoencoder for Facial Attribute Analysis

no code implementations20 Mar 2018 Akshay Sethi, Maneet Singh, Richa Singh, Mayank Vatsa

Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement.

Attribute Marketing

Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks

no code implementations22 Feb 2018 Gaurav Goswami, Nalini Ratha, Akshay Agarwal, Richa Singh, Mayank Vatsa

In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks inspired by commonly observed distortions in the real world that are well handled by shallow learning methods along with learning based adversaries; (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem.

Face Recognition

MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis

no code implementations22 Feb 2018 Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Angshul Majumdar

The proposed algorithm learns multi-level sparse representation for both high and low resolution gallery images, along with an identity aware dictionary and a transformation function between the two representations for face identification scenarios.

Face Identification Face Recognition +2

SegDenseNet: Iris Segmentation for Pre and Post Cataract Surgery

no code implementations30 Jan 2018 Aditya Lakra, Pavani Tripathi, Rohit Keshari, Mayank Vatsa, Richa Singh

This paper presents an efficient iris segmentation algorithm with variations due to cataract and post cataract surgery.

Iris Recognition Iris Segmentation +1

Synthetic Iris Presentation Attack using iDCGAN

no code implementations29 Oct 2017 Naman Kohli, Daksha Yadav, Mayank Vatsa, Richa Singh, Afzel Noore

We demonstrate the effect of these synthetically generated iris images as presentation attack on iris recognition by using a commercial system.

Generative Adversarial Network Iris Recognition

Face Sketch Matching via Coupled Deep Transform Learning

no code implementations ICCV 2017 Shruti Nagpal, Maneet Singh, Richa Singh, Mayank Vatsa, Afzel Noore, Angshul Majumdar

The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching.

Face Recognition

Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder

no code implementations8 Oct 2017 Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar

Soft biometric modalities have shown their utility in different applications including reducing the search space significantly.

Gender Classification General Classification

On Matching Skulls to Digital Face Images: A Preliminary Approach

no code implementations8 Oct 2017 Shruti Nagpal, Maneet Singh, Arushi Jain, Richa Singh, Mayank Vatsa, Afzel Noore

Forensic application of automatically matching skull with face images is an important research area linking biometrics with practical applications in forensics.

Face Recognition

Demography-based Facial Retouching Detection using Subclass Supervised Sparse Autoencoder

no code implementations22 Sep 2017 Aparna Bharati, Mayank Vatsa, Richa Singh, Kevin W. Bowyer, Xin Tong

However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images.

Greedy Deep Dictionary Learning

no code implementations31 Jan 2016 Snigdha Tariyal, Angshul Majumdar, Richa Singh, Mayank Vatsa

In this work we propose a new deep learning tool called deep dictionary learning.

Dictionary Learning

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