Search Results for author: Karthik Nandakumar

Found 32 papers, 20 papers with code

PEMMA: Parameter-Efficient Multi-Modal Adaptation for Medical Image Segmentation

no code implementations21 Apr 2024 Nada Saadi, Numan Saeed, Mohammad Yaqub, Karthik Nandakumar

In this work, we propose a parameter-efficient multi-modal adaptation (PEMMA) framework for lightweight upgrading of a transformer-based segmentation model trained only on CT scans to also incorporate PET scans.

Computed Tomography (CT) Image Segmentation +2

Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan

1 code implementation14 Apr 2024 Muhammad Saad Saeed, Shah Nawaz, Muhammad Salman Tahir, Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, Muhammad Haroon Yousaf

The Face-voice Association in Multilingual Environments (FAME) Challenge 2024 focuses on exploring face-voice association under a unique condition of multilingual scenario.

Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline

1 code implementation1 Apr 2024 Anas Al-lahham, Muhammad Zaigham Zaheer, Nurbek Tastan, Karthik Nandakumar

Unsupervised (US) video anomaly detection (VAD) in surveillance applications is gaining more popularity recently due to its practical real-world applications.

Anomaly Detection Privacy Preserving +1

SurvRNC: Learning Ordered Representations for Survival Prediction using Rank-N-Contrast

no code implementations15 Mar 2024 Numan Saeed, Muhammad Ridzuan, Fadillah Adamsyah Maani, Hussain Alasmawi, Karthik Nandakumar, Mohammad Yaqub

Predicting the likelihood of survival is of paramount importance for individuals diagnosed with cancer as it provides invaluable information regarding prognosis at an early stage.

Survival Prediction

Multi-Attribute Vision Transformers are Efficient and Robust Learners

1 code implementation12 Feb 2024 Hanan Gani, Nada Saadi, Noor Hussein, Karthik Nandakumar

Since their inception, Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) across a wide spectrum of tasks.


Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks

no code implementations18 Dec 2023 Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takáč, Maxim Panov

This paper presents a new approach to federated learning that allows selecting a model from global and personalized ones that would perform better for a particular input point.

Personalized Federated Learning Uncertainty Quantification

FLIP: Cross-domain Face Anti-spoofing with Language Guidance

2 code implementations ICCV 2023 Koushik Srivatsan, Muzammal Naseer, Karthik Nandakumar

Specifically, we show that aligning the image representation with an ensemble of class descriptions (based on natural language semantics) improves FAS generalizability in low-data regimes.

Contrastive Learning Face Anti-Spoofing +1

FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection

1 code implementation20 Aug 2023 Naif Alkhunaizi, Koushik Srivatsan, Faris Almalik, Ibrahim Almakky, Karthik Nandakumar

In FedSIS, a hybrid Vision Transformer (ViT) architecture is learned using a combination of FL and split learning to achieve robustness against statistical heterogeneity in the client data distributions without any sharing of raw data (thereby preserving privacy).

Domain Generalization Face Presentation Attack Detection +2

DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation

no code implementations31 Jul 2023 Vu Ngoc Tu, Van Thong Huynh, Hyung-Jeong Yang, M. Zaigham Zaheer, Shah Nawaz, Karthik Nandakumar, Soo-Hyung Kim

Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversation.


FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling

1 code implementation26 Jun 2023 Faris Almalik, Naif Alkhunaizi, Ibrahim Almakky, Karthik Nandakumar

In this work, we propose a framework for medical imaging classification tasks called Federated Split learning of Vision transformer with Block Sampling (FeSViBS).

Federated Learning

Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces

1 code implementation CVPR 2023 Fahad Shamshad, Koushik Srivatsan, Karthik Nandakumar

While these forensic models can detect whether a face image is synthetic or real with high accuracy, they are also vulnerable to adversarial attacks.

Attribute Meta-Learning

CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search

1 code implementation CVPR 2023 Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar

We propose a novel two-step approach for facial privacy protection that relies on finding adversarial latent codes in the low-dimensional manifold of a pretrained generative model.

Face Recognition Face Verification

Single-branch Network for Multimodal Training

1 code implementation10 Mar 2023 Muhammad Saad Saeed, Shah Nawaz, Muhammad Haris Khan, Muhammad Zaigham Zaheer, Karthik Nandakumar, Muhammad Haroon Yousaf, Arif Mahmood

With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text.

Cross-Modal Retrieval Retrieval

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss

1 code implementation CVPR 2023 Nurbek Tastan, Karthik Nandakumar

In CaPriDe learning, participating entities release their private data in an encrypted form allowing other participants to perform inference in the encrypted domain.

Federated Learning Knowledge Distillation

On the Importance of Image Encoding in Automated Chest X-Ray Report Generation

1 code implementation24 Nov 2022 Otabek Nazarov, Mohammad Yaqub, Karthik Nandakumar

Chest X-ray is one of the most popular medical imaging modalities due to its accessibility and effectiveness.

Decoder Text Generation

Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features

1 code implementation12 Oct 2022 Gokul Karthik Kumar, Karthik Nandakumar

A simple classifier based on the FIM representation is able to achieve state-of-the-art performance on the Hateful Memes Challenge (HMC) dataset with an AUROC of 85. 8, which even surpasses the human performance of 82. 65.

Hateful Meme Classification

Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data

1 code implementation3 Oct 2022 Sayed Hashim, Karthik Nandakumar, Mohammad Yaqub

Lack of annotated data is a significant problem in machine learning, and Self-Supervised Learning (SSL) methods are typically used to deal with limited labelled data.

Cancer type classification Self-Supervised Learning +1

Learning an Ensemble of Deep Fingerprint Representations

no code implementations2 Sep 2022 Akash Godbole, Karthik Nandakumar, Anil K. Jain

While learning an ensemble of representations can mitigate this problem, two critical challenges need to be addressed: (i) How to extract multiple diverse representations from the same fingerprint image?

Representation Learning

Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification

1 code implementation4 Aug 2022 Faris Almalik, Mohammad Yaqub, Karthik Nandakumar

Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation.

Image Classification Medical Image Classification

Suppressing Poisoning Attacks on Federated Learning for Medical Imaging

1 code implementation15 Jul 2022 Naif Alkhunaizi, Dmitry Kamzolov, Martin Takáč, Karthik Nandakumar

Federated Learning (FL) is a promising solution that enables collaborative training through exchange of model parameters instead of raw data.

Federated Learning Outlier Detection

On Demographic Bias in Fingerprint Recognition

no code implementations19 May 2022 Akash Godbole, Steven A. Grosz, Karthik Nandakumar, Anil K. Jain

Fingerprint recognition systems have been deployed globally in numerous applications including personal devices, forensics, law enforcement, banking, and national identity systems.

SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification

1 code implementation3 Feb 2022 Sayed Hashim, Muhammad Ali, Karthik Nandakumar, Mohammad Yaqub

In our project, we extend the idea of using a VAE model for low dimensional latent space extraction with the self-supervised learning technique of feature subsetting.

Cancer type classification Decision Making +2

Dynamically Decoding Source Domain Knowledge for Domain Generalization

no code implementations6 Oct 2021 Cuicui Kang, Karthik Nandakumar

Thus, source domain knowledge gets dynamically decoded for inference of the current input from unseen domain.

Decoder Domain Generalization +1

Discovering Spatial Relationships by Transformers for Domain Generalization

no code implementations23 Aug 2021 Cuicui Kang, Karthik Nandakumar

However, though CNNs have a strong ability to find the discriminative features, they do a poor job of modeling the relations between different locations in the image due to the response to CNN filters are mostly local.

Domain Generalization

Efficient Encrypted Inference on Ensembles of Decision Trees

no code implementations5 Mar 2021 Kanthi Sarpatwar, Karthik Nandakumar, Nalini Ratha, James Rayfield, Karthikeyan Shanmugam, Sharath Pankanti, Roman Vaculin

In this work, we propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks (referred to as DTNets) that are highly conducive to encrypted inference.

BIG-bench Machine Learning

Efficient CNN Building Blocks for Encrypted Data

no code implementations30 Jan 2021 Nayna Jain, Karthik Nandakumar, Nalini Ratha, Sharath Pankanti, Uttam Kumar

Using the CKKS scheme available in the open-source HElib library, we show that operational parameters of the chosen FHE scheme such as the degree of the cyclotomic polynomial, depth limitations of the underlying leveled HE scheme, and the computational precision parameters have a major impact on the design of the machine learning model (especially, the choice of the activation function and pooling method).

BIG-bench Machine Learning

Towards Fair and Privacy-Preserving Federated Deep Models

1 code implementation4 Jun 2019 Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, Kee Siong Ng

This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates.

Benchmarking Fairness +3

High-frequency crowd insights for public safety and congestion control

no code implementations23 Apr 2019 Karthik Nandakumar, Sebastien Blandin, Laura Wynter

We present results from several projects aimed at enabling the real-time understanding of crowds and their behaviour in the built environment.

Vocal Bursts Intensity Prediction

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