562 citations · 1.6k across the 39 of their papers we have counts for
8 papers · 1 filter
Synthesizing Informative Training Samples with GAN
Bo Zhao, Hakan Bilen
Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generat…
Dataset Condensation with Distribution Matching
Bo Zhao, Hakan Bilen
Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising…
Dataset Condensation with Differentiable Siamese Augmentation
Bo Zhao, Hakan Bilen
In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this pa…
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…
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…
iDLG: Improved Deep Leakage from Gradients
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recentl…
Learning to Impute: A General Framework for Semi-supervised Learning
Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen
Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification…
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…