182 citations · 210 across the 10 of their papers we have counts for
23 papers
2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
Xiaoxi Wei, A. Aldo Faisal, Moritz Grosse-Wentrup +18
Transfer learning and meta-learning offer some of the most promising avenues to unlock the scalability of healthcare and consumer technologies driven by biosignal data. This is bec…
Team Cogitat at NeurIPS 2021: Benchmarks for EEG Transfer Learning Competition
Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas +5
Building subject-independent deep learning models for EEG decoding faces the challenge of strong covariate-shift across different datasets, subjects and recording sessions. Our app…
Defensive Tensorization
Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya +5
We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as…
Tensor Methods in Computer Vision and Deep Learning
Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos +4
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent…
CoPE: Conditional image generation using Polynomial Expansions
Grigorios G Chrysos, Markos Georgopoulos, Yannis Panagakis
Generative modeling has evolved to a notable field of machine learning. Deep polynomial neural networks (PNNs) have demonstrated impressive results in unsupervised image generation…
Multilinear Latent Conditioning for Generating Unseen Attribute Combinations
Markos Georgopoulos, Grigorios Chrysos, Maja Pantic +1
Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images. However, empirical studies have s…