3 citations · 4 across the 8 of their papers we have counts for
5 papers · 1 filter
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations
Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni +1
This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantl…
Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni +1
Artificial neural networks often suffer from catastrophic forgetting, where learning new concepts leads to a complete loss of previously acquired knowledge. We observe that this is…
STint: Self-supervised Temporal Interpolation for Geospatial Data
Nidhin Harilal, Bri-Mathias Hodge, Aneesh Subramanian +1
Supervised and unsupervised techniques have demonstrated the potential for temporal interpolation of video data. Nevertheless, most prevailing temporal interpolation techniques hin…
Effectiveness of the Recent Advances in Capsule Networks
Nidhin Harilal, Rohan Patil
Convolutional neural networks (CNNs) have revolutionized the field of deep neural networks. However, recent research has shown that CNNs fail to generalize under various conditions…
Augmented Convolutional LSTMs for Generation of High-Resolution Climate Change Projections
Nidhin Harilal, Udit Bhatia, Mayank Singh
Projection of changes in extreme indices of climate variables such as temperature and precipitation are critical to assess the potential impacts of climate change on human-made and…