AI Paper Atlas

Research map / Point clouds / Point cloud classification

Circuit as Set of Points

Jialv Zou, Xinggang Wang, JiaHao Guo, Wenyu Liu, Qian Zhang, Chang Huang

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 2 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 CircuitFormer point-cloud features instead of hand-crafted CNN input featuresCongestion prediction · CircuitNetPearson correlation: 0.6085 -> 0.6374Improved
Use CircuitFormer point-cloud features instead of hand-crafted CNN input featuresCongestion prediction · ISPD2015Spearman correlation: 0.1575 -> 0.1797Improved
Use raw point-cloud features with CircuitFormer rather than RouteNet's hand-crafted featuresDRC violation prediction · CircuitNetPearson correlation: 0.4698 -> 0.3707Hurt
Use raw point-cloud features with CircuitFormer rather than RouteNet's hand-crafted featuresDRC violation prediction · CircuitNetSpearman correlation: 0.2782 -> 0.3094Improved
Replace the proposed encoder with point-based perception encoders (ablation)CircuitFormer · CircuitNet congestionPearson correlation: 0.6374 -> 0.4086Hurt
Replace the proposed encoder with PointPillar (ablation)CircuitFormer · CircuitNet congestionPearson correlation: 0.6374 -> 0.6151Hurt
Add cross-grid information exchange through the proposed attention encoder rather than PointPillar's within-grid features (ablation)CircuitFormer · CircuitNet congestionPearson correlation: 0.6151 -> 0.6374Improved
Add label distribution smoothing (ablation)CircuitFormer · CircuitNet congestionSpearman correlation: 0.5143 -> 0.5282Improved
Add label distribution smoothing (ablation)CircuitFormer · CircuitNet DRC violationPearson correlation: 0.3552 -> 0.3707Improved
Increase encoder depth from one GA stage to four (ablation)CircuitFormer · CircuitNet congestionPearson correlation: 0.5260 -> 0.6374Improved
Add the ResNet-18 backbone before the UNet++ head (ablation)CircuitFormer decoder · CircuitNet congestionPearson correlation: 0.3574 -> 0.6374Improved
Replace UNet++ with UNet as the segmentation head (ablation)CircuitFormer decoder · CircuitNet congestionPearson correlation: 0.6374 -> 0.5237Hurt

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