4 papers
Learning by Shifting: Temporal View Construction for Time Series Contrastive Learning
Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor
Supervised learning demands large quantities of labeled data, a bottleneck that is expensive and reliant on domain-specific expertise. Self-supervised learning, particularly contra…
Divide and Contrast: Learning Robust Temporal Features without Augmentation
Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor
Self-supervised learning for time-series representation aims to reduce reliance on labeled data while maintaining strong downstream performance, yet many existing approaches incur…
eMargin: Revisiting Contrastive Learning with Margin-Based Separation
Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor
We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation le…
Towards Generating Realistic Underwater Images
Abdul-Kazeem Shamba
This paper explores the use of contrastive learning and generative adversarial networks for generating realistic underwater images from synthetic images with uniform lighting. We i…