Search Results for author:
Found 5 papers, 5 papers with code
DO-Conv: Depthwise Over-parameterized Convolutional Layer
Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.
Mutual Information Maximization in Graph Neural Networks
In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information.
Ranked #1 on
Graph Classification
on Citeseer
PointCNN: Convolution On X-Transformed Points
We present a simple and general framework for feature learning from point cloud.
Ranked #2 on
Semantic Segmentation
on S3DIS Area5
(Number of params metric)
PointCNN: Convolution On $\mathcal{X}$-Transformed Points
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
Ranked #1 on
3D Instance Segmentation
on S3DIS
(mIoU metric)
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
