Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs

DOI10.1007/s11263-020-01302-5zbMath1477.68362arXiv1801.10585OpenAlexW3104750475MaRDI QIDQ2193592

Jan D. Wegner, Timo Hackel, Silvano Galliani, Mikhail Usvyatsov, Konrad Schindler

Publication date: 20 August 2020

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1801.10585

zbMATH Keywords

deep learningsparse convolutionsvoxel grids

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Machine vision and scene understanding (68T45)

Uses Software

• ggks
• TensorFlow
• DeepLab
• cuDNN
• ImageNet
• AdaGrad
• FlowNet
• PointNet
• ScanNet
• OctNet
• VoxNet
• AlexNet
• KPConv
• Faster R-CNN
• Vote3Deep
• MinkowskiEngine

Cites Work

• Unnamed Item
• Fast <it>k</it>-selection algorithms for graphics processing units