8 citations · 14 across the 3 of their papers we have counts for
3 papers
cs.LG2020★ 2 cited
Deep Anomaly Detection by Residual Adaptation
Lucas Deecke, Lukas Ruff, Robert A. Vandermeulen +1
Deep anomaly detection is a difficult task since, in high dimensions, it is hard to completely characterize a notion of "differentness" when given only examples of normality. In th…
cs.LG2020★ 4 cited
Latent Domain Learning with Dynamic Residual Adapters
Lucas Deecke, Timothy Hospedales, Hakan Bilen
A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable t…
cs.LG2018★ 8 cited
Mode Normalization
Lucas Deecke, Iain Murray, Hakan Bilen
Normalization methods are a central building block in the deep learning toolbox. They accelerate and stabilize training, while decreasing the dependence on manually tuned learning…