47 citations · 131 across the 26 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.CV2017
In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder
In this work we present In-Place Activated Batch Normalization (InPlace-ABN) - a novel approach to drastically reduce the training memory footprint of modern deep neural networks i…
cs.CV2017
Loss Max-Pooling for Semantic Image Segmentation
Samuel Rota Bulò, Gerhard Neuhold, Peter Kontschieder
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for s…