AI Paper Atlas

Research map / Point clouds / Point cloud classification

Differentiable Convolution Search for Point Cloud Processing

Xing Nie, Yongcheng Liu, Shaohong Chen, Jianlong Chang, Chunlei Huo, Gaofeng Meng, Qi Tian, Weiming Hu, Chunhong Pan

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 7 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
add epsilon-greedy algorithm to convolution search (ablation)PointSeaNet · ModelNet40 classificationoverall accuracy: 94.0 -> 94.2Improved
add epsilon-greedy algorithm (ablation)PointSeaNet · ModelNet40 shape retrievalmAP: 89.9 -> 90.3Improved
add epsilon-greedy algorithm (ablation)PointSeaNet · S3DIS Area-5mIoU: 68.2 -> 69.0Improved
add epsilon-greedy algorithm (ablation)PointSeaNet · S3DIS 6-foldmIoU: 71.2 -> 71.9Improved
add epsilon-greedy algorithm (ablation)PointSeaNet · ShapeNetPartclass mIoU: 85.2 -> 85.7Improved
add epsilon-greedy algorithm (ablation)PointSeaNet · ModelNet40 normal estimationerror: 0.12 -> 0.10Improved
add local features e2 to e1 (ablation)PointSeaNet association search · ModelNet40 classificationoverall accuracy: 81.3 -> 87.1Improved
add geometric relations e3 (ablation)PointSeaNet association search · ModelNet40 classificationoverall accuracy: 87.1 -> 90.2Improved
add Euclidean distance e4 (ablation)PointSeaNet association search · ModelNet40 classificationoverall accuracy: 90.2 -> 92.9Improved
add salient information e5 (ablation)PointSeaNet association search · ModelNet40 classificationoverall accuracy: 92.9 -> 94.0Improved
increase cells from 3 to 6 (ablation)PointSeaNet · ModelNet40 classificationoverall accuracy: 93.7 -> 94.2Improved
increase cells from 6 to 9 (ablation)PointSeaNet · ModelNet40 classificationoverall accuracy: 94.2 -> 94.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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