5 papers
Gradient based Severity Labeling for Biomarker Classification in OCT
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib +2
In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and…
Countering Multi-modal Representation Collapse through Rank-targeted Fusion
Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar +1
Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eige…
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
A key factor in effective Self-Supervised learning (SSL) is preventing dimensional collapse, where higher-dimensional representation spaces () span a lower-dimensional subspace.…
Subject Invariant Contrastive Learning for Human Activity Recognition
Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar +1
The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learn…
HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
Kiran Kokilepersaud, Seulgi Kim, Mohit Prabhushankar +1
In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during…