Search Results for author:
Found 58 papers, 8 papers with code
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
Using CC-Neg along with modifications to the contrastive loss of CLIP, our proposed CoN-CLIP framework, has an improved understanding of negations.
Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration
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.
Adventures of Trustworthy Vision-Language Models: A Survey
Recently, transformers have become incredibly popular in computer vision and vision-language tasks.
On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms
However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development.
Multi-task Explainable Skin Lesion Classification
The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
DF-Platter: Multi-Face Heterogeneous Deepfake Dataset
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.
Are Face Detection Models Biased?
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.
DeePhy: On Deepfake Phylogeny
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.
On Biased Behavior of GANs for Face Verification
Datasets for training face verification systems are difficult to obtain and prone to privacy issues.
Anatomizing Bias in Facial Analysis
In this paper, we encapsulate bias detection/estimation and mitigation algorithms for facial analysis.
MTCD: Cataract Detection via Near Infrared Eye Images
We present deep learning-based eye segmentation and multitask network classification networks for cataract detection using NIR images as input.
MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection
MD-CSDNetwork is a novel cross-stitched network with two parallel branches carrying the spatial and frequency information, respectively.
Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models
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.
Indian Masked Faces in the Wild Dataset
We have also benchmarked the performance of existing face recognition models on the proposed IMFW dataset.
Enhancing Fine-Grained Classification for Low Resolution Images
While fine-grained classification with high resolution images has received significant attention, limited attention has been given to low resolution images.
Class Equilibrium using Coulomb's Law
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
In this paper, we propose a novel algorithm for matching faces with temporal variations caused due to age progression.
WaveTransform: Crafting Adversarial Examples via Input Decomposition
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.
Attack Agnostic Adversarial Defense via Visual Imperceptible Bound
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.
Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings
Presentation attacks are posing major challenges to most of the biometric modalities.
MixNet for Generalized Face Presentation Attack Detection
The major problem with existing work is the generalizability against multiple attacks both in the seen and unseen setting.
Unravelling Small Sample Size Problems in the Deep Learning World
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
Deaths and injuries are common in road accidents, violence, and natural disaster.
Multi-Task Driven Explainable Diagnosis of COVID-19 using Chest X-ray Images
Firstly, we present the COVID-19 Multi-Task Network which is an automated end-to-end network for COVID-19 screening.
A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge
Face recognition in the unconstrained environment is an ongoing research challenge.
Generalized Zero-Shot Learning Via Over-Complete Distribution
A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes.
On the Robustness of Face Recognition Algorithms Against Attacks and Bias
Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications.
Detecting Face2Face Facial Reenactment in Videos
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
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.
A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge
Recent advancements in deep learning have significantly increased the capabilities of face recognition.
Dual Directed Capsule Network for Very Low Resolution Image Recognition
The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model.
On Learning Density Aware Embeddings
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.
Deep Learning for Face Recognition: Pride or Prejudiced?
This research attempts to answer these questions and presents an in-depth analysis of `bias' in deep learning based face recognition systems.
On Detecting GANs and Retouching based Synthetic Alterations
For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99. 83%.
Data Fine-tuning
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.
Recognizing Disguised Faces in the Wild
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.
On Matching Faces with Alterations due to Plastic Surgery and Disguise
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.
Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition
Mobile biometric approaches provide the convenience of secure authentication with an omnipresent technology.
Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
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.
Learning A Shared Transform Model for Skull to Digital Face Image Matching
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
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).
Hierarchical Representation Learning for Kinship Verification
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.
Anonymizing k-Facial Attributes via Adversarial Perturbations
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.
Class Representative Autoencoder for Low Resolution Multi-Spectral Gender Classification
Gender is one of the most common attributes used to describe an individual.
Learning Structure and Strength of CNN Filters for Small Sample Size Training
The architecture provides the flexibility of training with both small and large training databases and yields good accuracies even with small size training data.
Are you eligible? Predicting adulthood from face images via class specific mean autoencoder
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.
Residual Codean Autoencoder for Facial Attribute Analysis
Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement.
Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks
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.
MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis
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.
SegDenseNet: Iris Segmentation for Pre and Post Cataract Surgery
This paper presents an efficient iris segmentation algorithm with variations due to cataract and post cataract surgery.
Synthetic Iris Presentation Attack using iDCGAN
We demonstrate the effect of these synthetically generated iris images as presentation attack on iris recognition by using a commercial system.
Face Sketch Matching via Coupled Deep Transform Learning
The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching.
On Matching Skulls to Digital Face Images: A Preliminary Approach
Forensic application of automatically matching skull with face images is an important research area linking biometrics with practical applications in forensics.
Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder
Soft biometric modalities have shown their utility in different applications including reducing the search space significantly.
Demography-based Facial Retouching Detection using Subclass Supervised Sparse Autoencoder
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
In this work we propose a new deep learning tool called deep dictionary learning.
