no code implementations • 21 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.
1 code implementation • 14 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.
1 code implementation • 1 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.
no code implementations • 15 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.
1 code implementation • 12 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.
no code implementations • 18 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.
1 code implementation • 26 Oct 2023 • Anas Al-lahham, Nurbek Tastan, Zaigham Zaheer, Karthik Nandakumar
Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings.
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.
1 code implementation • 20 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).
no code implementations • 31 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.
1 code implementation • 26 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).
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.
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.
1 code implementation • 10 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.
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.
1 code implementation • 24 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.
2 code implementations • 17 Nov 2022 • Gokul Karthik Kumar, Praveen S V, Pratyush Kumar, Mitesh M. Khapra, Karthik Nandakumar
We open-source all models on the Bhashini platform.
Ranked #1 on Speech Synthesis - Rajasthani on IndicTTS
1 code implementation • 12 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.
Ranked #1 on Meme Classification on Tamil Memes
1 code implementation • 3 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.
no code implementations • 2 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?
1 code implementation • 4 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.
1 code implementation • 15 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.
no code implementations • 19 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.
1 code implementation • DravidianLangTech (ACL) 2022 • Gokul Karthik Kumar, Abhishek Singh Gehlot, Sahal Shaji Mullappilly, Karthik Nandakumar
These models are pre-trained in a self-supervised fashion with a large English text corpus and further fine-tuned with a massive English QA dataset (e. g., SQuAD).
1 code implementation • 3 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.
Ranked #1 on Cancer type classification on TCGA
no code implementations • 6 Oct 2021 • Cuicui Kang, Karthik Nandakumar
Thus, source domain knowledge gets dynamically decoded for inference of the current input from unseen domain.
no code implementations • 23 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.
no code implementations • 5 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.
no code implementations • 30 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).
no code implementations • 18 Jul 2020 • Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu, Xingjun Ma
This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy.
1 code implementation • 4 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.
no code implementations • 23 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.