Publications
Explore our cutting-edge research contributions to machine learning, deep learning, and high-dimensional statistics
Showing 15 of 15 publications
Information preservation with wasserstein autoencoders: generation consistency and adversarial robustness
Amongst the numerous variants Variational Autoencoder (VAE) has inspired, the Wasserstein Autoencoder (WAE) stands out due to its heightened generative quality and intriguing theoretical properties.
Sampling-Tailored Two-Pronged Network for Long-Tailed Class Imbalance Learning
Force of Attraction-Based Distribution Calibration for Enhancing Minority Class Representation
Imbalanced image datasets pose significant challenges for developing robust classifiers, particularly when certain classes are heavily underrepresented. To tackle this issue, we propose Density-Driven Attraction
Can Graph Neural Networks Tackle Heterophily? Yes, With a Label-Guided Graph Rewiring Approach!
Graph neural networks (GNNs) witness impressive performances on homophilic graphs characterized by a higher number of edges connecting nodes of similar class labels. A decline
The Goldilocks Principle: Achieving Just Right Boundary Fidelity for Long-Tailed Classification
This study addresses the challenges of learning from long-tailed class imbalances in deep neural networks, particularly for image recognition. Long-tailed class imbalances occur when a
Deep multi-view clustering: A comprehensive survey of the contemporary techniques
Data can be represented by multiple sets of features, where each semantically coherent set of features is called a view. For example, an image can
Enhancing Medical Image Analysis with MA-DTNet: A Dual Task Network Guided by Morphological Attention
Accurate breast tumor segmentation and malignancy detection are crucial for early cancer diagnosis. In this context, we propose a novel lightweight multi-task learning framework, MA-DTNet,
Improved Alzheimer’s Disease Detection with Dynamic Attention Guided Multi-modal Fusion
The early detection of neurodegenerative disorders such as Alzheimer’s disease is crucial to providing effective healthcare for management and recovery. We address the task of
Enhancing Contrastive Clustering with Negative Pair-guided Regularization
Contrastive Learning (CL) aims to create effective embeddings for input data by minimizing the distance between positive pairs, i.e., different augmentations or views of the
Multi-scale morphology-aided deep medical image segmentation
Medical image segmentation serves as a critical tool for healthcare professionals, enabling the precise extraction of Regions of Interest (ROIs) from clinical images at the
Algorithmic Fairness in Lesion Classification by Mitigating Class Imbalance and Skin Tone Bias
Deep learning models have shown considerable promise in the classification of skin lesions. However, a notable challenge arises from their inherent bias towards dominant skin
CCO: A Cluster Core-Based Oversampling Technique for Improved Class-Imbalanced Learning
Supervised classification problems from the real world typically face a challenge characterized by the scarcity of samples in one or more target classes compared to
Mo2E: Mixture of Two Experts for Class-Imbalanced Learning from Medical Images
Class imbalance in the medical image dataset is almost inherent due to the limited availability of clinical data for certain diseases and patient populations. Under-represented
Affinity-based Homophily: Can we measure homophily of a graph without using node labels?
The homophily (heterophily) ratio in a graph represents the proportion of edges connecting nodes with similar (dissimilar) class labels. Existing methods for estimating the homophily
Lost in Translation: GANs' Inability to Generate Simple Probability Distributions
Since its inception, Generative Adversarial Networks (GAN) have marked a triumph in generative modeling. Its impeccable capacity to mimic observations from unknown probability distributions has