347 citations · 684 across the 26 of their papers we have counts for
4 papers · 1 filter
Federated Learning with a Single Shared Image
Sunny Soni, Aaqib Saeed, Yuki M. Asano
Federated Learning (FL) enables multiple machines to collaboratively train a machine learning model without sharing of private training data. Yet, especially for heterogeneous mode…
COCOA: Cross Modality Contrastive Learning for Sensor Data
Shohreh Deldari, Hao Xue, Aaqib Saeed +2
Self-Supervised Learning (SSL) is a new paradigm for learning discriminative representations without labelled data and has reached comparable or even state-of-the-art results in co…
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
Yuki M. Asano, Aaqib Saeed
What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objec…
Damage detection using in-domain and cross-domain transfer learning
Zaharah A. Bukhsh, Nils Jansen, Aaqib Saeed
We investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typi…