Search Results for author:
Found 36 papers, 11 papers with code
On Robust Cross Domain Alignment
The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces.
On the Universal Statistical Consistency of Expansive Hyperbolic Deep Convolutional Neural Networks
The emergence of Deep Convolutional Neural Networks (DCNNs) has been a pervasive tool for accomplishing widespread applications in computer vision.
Self-Tuning Spectral Clustering for Speaker Diarization
Spectral clustering has proven effective in grouping speech representations for speaker diarization tasks, although post-processing the affinity matrix remains difficult due to the need for careful tuning before constructing the Laplacian.
TCG CREST System Description for the Second DISPLACE Challenge
In this report, we describe the speaker diarization (SD) and language diarization (LD) systems developed by our team for the Second DISPLACE Challenge, 2024.
Consistent Spectral Clustering in Hyperbolic Spaces
However, with the rapid evolution of data complexity, Euclidean Space is proving to be inefficient for representing and learning algorithms.
Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures
Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart.
Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning
Accounting for the uncertainty of value functions boosts exploration in Reinforcement Learning (RL).
Enhancing MRI-Based Classification of Alzheimer's Disease with Explainable 3D Hybrid Compact Convolutional Transformers
Alzheimer's disease (AD), characterized by progressive cognitive decline and memory loss, presents a formidable global health challenge, underscoring the critical importance of early and precise diagnosis for timely interventions and enhanced patient outcomes.
Exploring Green AI for Audio Deepfake Detection
In contrast to existing methods that fine-tune SSL models and employ additional deep neural networks for downstream tasks, we exploit classical machine learning algorithms such as logistic regression and shallow neural networks using the SSL embeddings extracted using the pre-trained model.
Ranked #2 on
Voice Anti-spoofing
on ASVspoof 2019 - LA
HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings
Graph Transformers (GTs) facilitate the comprehension of graph-structured data by calculating the self-attention of node pairs without considering node position information.
Concurrent Density Estimation with Wasserstein Autoencoders: Some Statistical Insights
Variational Autoencoders (VAEs) have been a pioneering force in the realm of deep generative models.
Dirichlet Process-based Robust Clustering using the Median-of-Means Estimator
On a different note, another limitation in many commonly used clustering methods is the need to specify the number of clusters beforehand.
Reinforcement Learning-assisted Evolutionary Algorithm: A Survey and Research Opportunities
Reinforcement learning (RL) integrated as a component in the EA framework has demonstrated superior performance in recent years.
Hybrid Gromov-Wasserstein Embedding for Capsule Learning
Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing.
GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Tracking
To address this issue, we propose a mode-seeking algorithm called GridShift, with significant speedup and principally based on MS. To accelerate, GridShift employs a grid-based approach for neighbor search, which is linear in the number of data points.
Hamiltonian Monte Carlo Particle Swarm Optimizer
We introduce the Hamiltonian Monte Carlo Particle Swarm Optimizer (HMC-PSO), an optimization algorithm that reaps the benefits of both Exponentially Averaged Momentum PSO and HMC sampling.
Interval Bound Interpolation for Few-shot Learning with Few Tasks
We then use a novel strategy to artificially form new tasks for training by interpolating between the available tasks and their respective interval bounds.
Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification
The problem of linear predictions has been extensively studied for the past century under pretty generalized frameworks.
Uniform Concentration Bounds toward a Unified Framework for Robust Clustering
Recent advances in center-based clustering continue to improve upon the drawbacks of Lloyd's celebrated $k$-means algorithm over $60$ years after its introduction.
Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency
The introduction of Variational Autoencoders (VAE) has been marked as a breakthrough in the history of representation learning models.
An Adaptive Learning based Generative Adversarial Network for One-To-One Voice Conversion
VC task is performed through a three-stage pipeline consisting of speech analysis, speech feature mapping, and speech reconstruction.
Robust Principal Component Analysis: A Median of Means Approach
Principal Component Analysis (PCA) is a fundamental tool for data visualization, denoising, and dimensionality reduction.
Automated Clustering of High-dimensional Data with a Feature Weighted Mean Shift Algorithm
Mean shift is a simple interactive procedure that gradually shifts data points towards the mode which denotes the highest density of data points in the region.
Kernel k-Means, By All Means: Algorithms and Strong Consistency
We show the method implicitly performs annealing in kernel feature space while retaining efficient, closed-form updates, and we rigorously characterize its convergence properties both from computational and statistical points of view.
Appropriateness of Performance Indices for Imbalanced Data Classification: An Analysis
Indices quantifying the performance of classifiers under class-imbalance, often suffer from distortions depending on the constitution of the test set or the class-specific classification accuracy, creating difficulties in assessing the merit of the classifier.
A Black-box Adversarial Attack Strategy with Adjustable Sparsity and Generalizability for Deep Image Classifiers
Constructing adversarial perturbations for deep neural networks is an important direction of research.
Entropy Regularized Power k-Means Clustering
Despite its well-known shortcomings, $k$-means remains one of the most widely used approaches to data clustering.
Utilizing Dependence among Variables in Evolutionary Algorithms for Mixed-Integer Programming: A Case Study on Multi-Objective Constrained Portfolio Optimization
Consequently, we point out one challenge, faced by a direct coding scheme for MOEAs, to this problem.
A Strongly Consistent Sparse $k$-means Clustering with Direct $l_1$ Penalization on Variable Weights
We propose the Lasso Weighted $k$-means ($LW$-$k$-means) algorithm as a simple yet efficient sparse clustering procedure for high-dimensional data where the number of features ($p$) can be much larger compared to the number of observations ($n$).
Generative Adversarial Minority Oversampling
We propose a three-player adversarial game between a convex generator, a multi-class classifier network, and a real/fake discriminator to perform oversampling in deep learning systems.
Fuzzy Clustering to Identify Clusters at Different Levels of Fuzziness: An Evolutionary Multi-Objective Optimization Approach
This paper presents Entropy $c$-Means (ECM), a method of fuzzy clustering that simultaneously optimizes two contradictory objective functions, resulting in the creation of fuzzy clusters with different levels of fuzziness.
Diversifying Support Vector Machines for Boosting using Kernel Perturbation: Applications to Class Imbalance and Small Disjuncts
The diversification (generating slightly varying separating discriminators) of Support Vector Machines (SVMs) for boosting has proven to be a challenge due to the strong learning nature of SVMs.
Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuning
We then demonstrate how this insight can be used to attain a good compromise between the rare and abundant classes without having to resort to cost set tuning, which has long been the norm for imbalanced classification.
Clustering with Missing Features: A Penalized Dissimilarity Measure based approach
Many real-world clustering problems are plagued by incomplete data characterized by missing or absent features for some or all of the data instances.
Kernelized Weighted SUSAN based Fuzzy C-Means Clustering for Noisy Image Segmentation
The paper proposes a novel Kernelized image segmentation scheme for noisy images that utilizes the concept of Smallest Univalue Segment Assimilating Nucleus (SUSAN) and incorporates spatial constraints by computing circular colour map induced weights.
Multi-Agent Shape Formation and Tracking Inspired from a Social Foraging Dynamics
Principle of Swarm Intelligence has recently found widespread application in formation control and automated tracking by the automated multi-agent system.
