AI Paper Atlas

Research map / Point clouds / Point cloud classification

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Yifan Xu, Tianqi Fan, Mingye Xu, Long Zeng, Yu Qiao

ECCV 2018 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 887 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use top-2 pooling instead of max-pooling (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 92.0 -> 92.4Improved
use top-2 pooling instead of max-pooling (ablation)SpiderCNN 3-layer · ModelNet40accuracy (%): 90.4 -> 91.5Improved
use step times Taylor filter instead of MLP(16, 1) filter (ablation)SpiderCNN 3-layer · ModelNet40accuracy (%): 71.3 -> 91.5Improved
use step times Taylor filter instead of MLP(16, 32, 1) filter (ablation)SpiderCNN 3-layer · ModelNet40accuracy (%): 72.8 -> 91.5Improved
use order-3 Taylor instead of MLP(10, 5, 3) in the Taylor slot (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 91.6 -> 92.4Improved
use order-3 Taylor instead of MLP(6, 5, 3) (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 91.1 -> 92.4Improved
use order-3 Taylor instead of order-2 Taylor (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 91.9 -> 92.4Improved
use order-3 Taylor instead of linear Taylor (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 91.6 -> 92.4Improved
use order-3 Taylor instead of trilinear form f_wT (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 91.9 -> 92.4Improved
add normal vectors to the 1,024 input points (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 90.5 -> 92.4Improved
estimate normals from the 1,024 points by orthogonal distance regression (ablation)SpiderCNN 4-layer · ModelNet40accuracy (%): 90.5 -> 91.8Improved
concatenate PointNet global features with 3-layer SpiderCNN features (ablation)SpiderCNN 3-layer · ModelNet40accuracy (%): 91.5 -> 92.2Improved

Later papers that compared with this method

9 later accepted papers report SpiderCNN as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

1 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy