KCNet: Kernel-Based Canonicalization Network for Entities in Recruitment Domain

Goyal, Nidhi; Sachdeva, Niharika; Goel, Anmol; Kalra, Jushaan; Kumaraguru, Ponnurangam

doi:10.1007/978-3-030-86340-1_13

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, max-pooling could lead to the loss of critical geometric information in the point cloud. A number of work [49,29,48,37,17,73] build a kNN graph from the point cloud and conduct message passing using graph convolution. Later on, [75,83,69,80,45,41,15,40] conduct continuous convolution on point clouds.…”

Section: Related Workmentioning

confidence: 99%

PointConvFormer: Revenge of the Point-based Convolution

Wu¹,

Qi²,

Li³

2022

Preprint

View full text Add to dashboard Cite

We introduce PointConvFormer, a novel building block for point cloud based deep neural network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative position, and Transformers which utilizes feature-based attention. In PointConvFormer, feature difference between points in the neighborhood serves as an indicator to re-weight the convolutional weights. Hence, we preserved the invariances from the point convolution operation whereas attention is used to select relevant points in the neighborhood for convolution. To validate the effectiveness of PointConvFormer, we experiment on both semantic segmentation and scene flow estimation tasks on point clouds with multiple datasets including ScanNet, SemanticKitti, FlyingThings3D and KITTI. Our results show that PointConvFormer substantially outperforms classic convolutions, regular transformers, and voxelized sparse convolution approaches with smaller, more computationally efficient networks. Visualizations show that PointConvFormer performs similarly to convolution on flat surfaces, whereas the neighborhood selection effect is stronger on object boundaries, showing that it got the best of both worlds.

show abstract