Search Results for author:
Found 12 papers, 3 papers with code
Surveying Facial Recognition Models for Diverse Indian Demographics: A Comparative Analysis on LFW and Custom Dataset
Facial recognition technology has made significant advances, yet its effectiveness across diverse ethnic backgrounds, particularly in specific Indian demographics, is less explored.
Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis
Shared training approaches, such as multi-task learning (MTL) and gradient-based meta-learning, are widely used in various machine learning applications, but they often suffer from negative transfer, leading to performance degradation in specific tasks.
F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics
}, client-specific layer importance score that selects the most important VLM layers for fine-tuning and inter-client layer diversity score that encourages diverse layer selection across clients for optimal VLM layer selection.
Large Language Models in the Clinic: A Comprehensive Benchmark
The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention.
Medical records condensation: a roadmap towards healthcare data democratisation
The prevalence of artificial intelligence (AI) has envisioned an era of healthcare democratisation that promises every stakeholder a new and better way of life.
Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention
Experimental evaluation highlights that models trained on encoded time-series data effectively uphold the information bottleneck principle and hence, exhibit lesser information leakage from trained models.
All models are local: time to replace external validation with recurrent local validation
We submit that external validation is insufficient to establish ML models' safety or utility.
Adversarial De-confounding in Individualised Treatment Effects Estimation
Observational studies have recently received significant attention from the machine learning community due to the increasingly available non-experimental observational data and the limitations of the experimental studies, such as considerable cost, impracticality, small and less representative sample sizes, etc.
COPER: Continuous Patient State Perceiver
COPER uses Perceiver model and the concept of neural ordinary differential equations (ODEs) to learn the continuous time dynamics of patient state, i. e., continuity of input space and continuity of output space.
Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss
Experimental results also confirm the superiority of the triplet loss over the cross-entropy loss in low training data conditions
Directional Embedding Based Semi-supervised Framework For Bird Vocalization Segmentation
The proposed framework utilizes a reference directional model for obtaining a feature representation called directional embeddings (DE).
Conv-codes: Audio Hashing For Bird Species Classification
In this work, we propose a supervised, convex representation based audio hashing framework for bird species classification.
