Tag: representation learning
Congratulations to Dr. Ritesh Chowdhry for a Successful Dissertation Defense!
October 29, 2026Congratulations to Dr. Ritesh Chowdhry for successfully passing his PhD dissertation exam! As a member of the Machine Learning and Sensing Lab, his dissertation, “Beyond Band Masking: Decomposition-Guided Self-Supervised Learning for Hyperspectral Images,” explores a key question: how should a masked autoencoder apply its mask? Masking individual spectral bands creates an uneven training signal because […]
Read more: Congratulations to Dr. Ritesh Chowdhry for a Successful Dissertation Defense! »Continuous Latent Spaces for Multi-Task Multi-Modal Learning
August 25, 2026Abstract: Recent advances in remote sensing have expanded Earth observation through an increasing number of sensing modalities, where each sensor provides distinct spectral, spatial, and temporal information. Effective analysis of these data depends on learning representations that integrate complementary information across modalities while supporting multiple learning objectives. Multi-task multi-modal learning in remote sensing remains challenging […]
Read more: Continuous Latent Spaces for Multi-Task Multi-Modal Learning »Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection
April 10, 2025Abstract: Triplet loss traditionally relies only on class labels and does not use all available information in multi-task scenarios where multiple types of annotations are available. This paper introduces a Multi-Annotation Triplet Loss (MATL) framework that extends triplet loss by incorporating additional annotations, such as bounding box information, alongside class labels in the loss formulation. […]
Read more: Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection »