mlsanityData to 14 Oct 2026

DAGrid: Directed Accumulator Grid

arXiv 2306.02589 ↗First posted 5 Jun 2023cs.CV cs.AI eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent research highlights that the Directed Accumulator (DA), through its parametrization of geometric priors into neural networks, has notably improved the performance of medical image recognition, particularly with small and imbalanced datasets. However, DA's potential in pixel-wise dense predictions is unexplored. To bridge this gap, we present the Directed Accumulator Grid (DAGrid), which allows geometric-preserving filtering in neural networks, thus broadening the scope of DA's applications to include pixel-level dense prediction tasks. DAGrid utilizes homogeneous data types in conjunction with designed sampling grids to construct geometrically transformed representations, retaining intricate geometric information and promoting long-range information propagation within the neural networks. Contrary to its symmetric counterpart, grid sampling, which might lose information in the sampling process, DAGrid aggregates all pixels, ensuring a comprehensive representation in the transformed space. The parallelization of DAGrid on modern GPUs is facilitated using CUDA programming, and also back propagation is enabled for deep neural network training. Empirical results show DAGrid-enhanced neural networks excel in supervised skin lesion segmentation and unsupervised cardiac image registration. Specifically, the network incorporating DAGrid has realized a 70.8% reduction in network parameter size and a 96.8% decrease in FLOPs, while concurrently improving the Dice score for skin lesion segmentation by 1.0% compared to state-of-the-art transformers. Furthermore, it has achieved improvements of 4.4% and 8.2% in the average Dice score and Dice score of the left ventricular mass, respectively, indicating an increase in registration accuracy for cardiac images. The source code is available at https://github.com/tinymilky/DeDA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 72 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

48 of 72 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  9. 2023Segment Anythingcited by 8,234
  10. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  11. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  12. 2017Non-local Neural Networkscited by 2,293
36 more
  1. 2015Spatial Transformer Networkscited by 1,429
  2. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  3. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  6. 2017Road Extraction by Deep Residual U-Netcited by 333
  7. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  8. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  9. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  10. 2018Boundary loss for highly unbalanced segmentationcited by 190
  11. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  12. 2018Cell Detection with Star-convex Polygonscited by 183
  13. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 172
  14. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  15. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  16. 2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
  17. 2017Polar Transformer Networkscited by 81
  18. 2022What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factorscited by 61
  19. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  20. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  21. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  22. 2020Deep Hough Transform for Semantic Line Detectioncited by 44
  23. 2020Deep Hough-Transform Line Priorscited by 44
  24. 2019Explicit Shape Encoding for Real-Time Instance Segmentationcited by 41
  25. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  26. 2016Hough-CNN: Deep Learning for Segmentation of Deep Brain Regions in MRI and Ultrasoundcited by 17
  27. 2021A Deep Discontinuity-Preserving Image Registration Networkcited by 17
  28. 2019Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstructioncited by 16
  29. 20223D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transformcited by 11
  30. 2022Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximationcited by 10
  31. 2023Spatially Covariant Lesion Segmentationcited by 10
  32. 2020Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentationcited by 9
  33. 2020Geometric Loss for Deep Multiple Sclerosis lesion Segmentationcited by 8
  34. 2022Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR imagescited by 5
  35. 2023DeDA: Deep Directed Accumulatorcited by 5
  36. 2020Accumulated Polar Feature-based Deep Learning for Efficient and Lightweight Automatic Modulation Classification with Channel Compensation Mechanismcited by 3

Built on by

Not cited yet.