SparseConvNet | Submanifold sparse convolutional networks | Computer Vision library

ICDAR 2013 Chinese Handwriting Recognition Competition 2013 First place in task 3, with test error of 2.61%. Human performance on the test set was 4.81%. ReportSpatially-sparse convolutional neural networks, 2014 SparseConvNets for Chinese handwriting recognitionFractional max-pooling, 2014 A SparseConvNet with fractional max-pooling achieves an error rate of 3.47% for CIFAR-10.Sparse 3D convolutional neural networks, BMVC 2015 SparseConvNets for 3D object recognition and (2+1)D video action recognition.Kaggle plankton recognition competition, 2015 Third place. The competition solution is being adapted for research purposes in EcoTaxa.Kaggle Diabetic Retinopathy Detection, 2015 First place in the Kaggle Diabetic Retinopathy Detection competition.Submanifold Sparse Convolutional Networks, 2017 Introduces deep 'submanifold' SparseConvNets.Workshop on Learning to See from 3D Data, 2017 First place in the semantic segmentation competition. Report3D Semantic Segmentation with Submanifold Sparse Convolutional Networks, 2017 Semantic segmentation for the ShapeNet Core55 and NYU-DepthV2 datasets, CVPR 2018Unsupervised learning with sparse space-and-time autoencoders (3+1)D space-time autoencodersScanNet 3D semantic label benchmark 2018 0.726 average IOU.MinkowskiEngine is an alternative implementation of SparseConvNet; 0.736 average IOU for ScanNet.SpConv: PyTorch Spatially Sparse Convolution Library is an alternative implementation of SparseConvNet.Live Semantic 3D Perception for Immersive Augmented Reality describes a way to optimize memory access for SparseConvNet.OccuSeg real-time object detection using SparseConvNets.TorchSparse implements 3D submanifold convolutions.TensorFlow 3D implements submanifold convolutions.