mlsanityData to 13 Oct 2026

Spatially-sparse convolutional neural networks

arXiv 1409.6070 ↗First posted 22 Sep 2014cs.CV cs.NEcited by 33

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks. Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 dataset containing 3755 character classes we get a test error of 3.82%. Although pictures are not sparse, they can be thought of as sparse by adding padding. Applying a deep convolutional network using sparsity has resulted in a substantial reduction in test error on the CIFAR small picture datasets: 6.28% on CIFAR-10 and 24.30% for CIFAR-100.

Key facts. Cited by 33 papers in the map (data through 13 Oct 2026). First posted on arXiv 22 Sep 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 6; 2024: 5; 2025: 3; 2026: 1.

33 papers.

Sort:

  1. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  2. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  3. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  4. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  5. 2022Spatial Pruned Sparse Convolution for Efficient 3D Object Detectioncited by 26
  6. 2022PeRFception: Perception using Radiance Fieldscited by 19
  7. 2021NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Droppingcited by 16
  8. 2022Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processescited by 15
  9. 2022PCSCNet: Fast 3D Semantic Segmentation of LiDAR Point Cloud for Autonomous Car using Point Convolution and Sparse Convolution Networkcited by 14
  10. 2021Improving Video Instance Segmentation via Temporal Pyramid Routingcited by 13
  11. 2024Memory-based Adapters for Online 3D Scene Perceptioncited by 13
  12. 2025SSF: Sparse Long-Range Scene Flow for Autonomous Drivingcited by 12
21 more
  1. 2022Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Trackingcited by 9
  2. 2022Sequential Point Clouds: A Surveycited by 5
  3. 2023Content-Adaptive Downsampling in Convolutional Neural Networkscited by 5
  4. 2024Optimized CNNs for Rapid 3D Point Cloud Object Recognitioncited by 5
  5. 2025Which2comm: An Efficient Collaborative Perception Framework for 3D Object Detectioncited by 4
  6. 2021Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNetcited by 3
  7. 2022Survey and Systematization of 3D Object Detection Models and Methodscited by 3
  8. 2022Learning Spatial and Temporal Variations for 4D Point Cloud Segmentationcited by 3
  9. 2021Putting 3D Spatially Sparse Networks on a Dietcited by 2
  10. 2023Exploiting Sparsity in Automotive Radar Object Detection Networkscited by 2
  11. 2023Sparse and Privacy-enhanced Representation for Human Pose Estimationcited by 2
  12. 2024DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detectioncited by 2
  13. 2021On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Modelscited by 1
  14. 2022SparseDet: Towards End-to-End 3D Object Detectioncited by 1
  15. 2023CT Perfusion is All We Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Ischemic Strokecited by 1
  16. 2023Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysiscited by 1
  17. 2024Exploring the Relationship: Transformative Adaptive Activation Functions in Comparison to Other Activation Functionscited by 1
  18. 2023Geometry Aware Field-to-field Transformations for 3D Semantic Segmentationcited by 0
  19. 2024Random Search as a Baseline for Sparse Neural Network Architecture Searchcited by 0
  20. 2025SSCATeR: Sparse Scatter-Based Convolution Algorithm with Temporal Data Recycling for Real-Time 3D Object Detection in LiDAR Point Cloudscited by 0
  21. 2026OPUS-V2: Bridging the Gap between Sparse Points and Dense Voxelscited by 0