Search Results for author:
Found 32 papers, 20 papers with code
PEMMA: Parameter-Efficient Multi-Modal Adaptation for Medical Image Segmentation
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.
Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan
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
Unsupervised (US) video anomaly detection (VAD) in surveillance applications is gaining more popularity recently due to its practical real-world applications.
SurvRNC: Learning Ordered Representations for Survival Prediction using Rank-N-Contrast
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.
Multi-Attribute Vision Transformers are Efficient and Robust Learners
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
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.
A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection
Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings.
FLIP: Cross-domain Face Anti-spoofing with Language Guidance
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.
FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection
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).
DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation
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
In this work, we propose a framework for medical imaging classification tasks called Federated Split learning of Vision transformer with Block Sampling (FeSViBS).
Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces
While these forensic models can detect whether a face image is synthetic or real with high accuracy, they are also vulnerable to adversarial attacks.
CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search
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.
Single-branch Network for Multimodal Training
With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text.
CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss
In CaPriDe learning, participating entities release their private data in an encrypted form allowing other participants to perform inference in the encrypted domain.
On the Importance of Image Encoding in Automated Chest X-Ray Report Generation
Chest X-ray is one of the most popular medical imaging modalities due to its accessibility and effectiveness.
Towards Building Text-To-Speech Systems for the Next Billion Users
We open-source all models on the Bhashini platform.
Ranked #1 on
Speech Synthesis - Rajasthani
on IndicTTS
Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features
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
Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data
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.
Learning an Ensemble of Deep Fingerprint Representations
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?
Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation.
Suppressing Poisoning Attacks on Federated Learning for Medical Imaging
Federated Learning (FL) is a promising solution that enables collaborative training through exchange of model parameters instead of raw data.
On Demographic Bias in Fingerprint Recognition
Fingerprint recognition systems have been deployed globally in numerous applications including personal devices, forensics, law enforcement, banking, and national identity systems.
MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages
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).
SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification
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
Dynamically Decoding Source Domain Knowledge for Domain Generalization
Thus, source domain knowledge gets dynamically decoded for inference of the current input from unseen domain.
Discovering Spatial Relationships by Transformers for Domain Generalization
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.
Efficient Encrypted Inference on Ensembles of Decision Trees
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.
Efficient CNN Building Blocks for Encrypted Data
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).
How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy.
Towards Fair and Privacy-Preserving Federated Deep Models
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.
High-frequency crowd insights for public safety and congestion control
We present results from several projects aimed at enabling the real-time understanding of crowds and their behaviour in the built environment.
