AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

(AF)2-S3Net: Attentive Feature Fusion With Adaptive Feature Selection for Sparse Semantic Segmentation Network

Ran Cheng, Ryan Razani, Ehsan Taghavi, Enxu Li, Bingbing Liu

CVPR 2021 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 264 citations (OpenAlex)

Check 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 AF2M to the MinkNet42 baseline (ablation)MinkNet42 · SemanticKITTI validation seq 08mIoU: 59.8 -> 65.1; increase of 5.3%Improved
Add AFSM using AF2M branch outputs (ablation)MinkNet42 baseline · SemanticKITTI validation seq 08mIoU: 59.8 -> 63.3; increase of 3.5%Improved
Add AF2M and AFSM together (ablation)MinkNet42 · SemanticKITTI validation seq 08mIoU: 59.8 -> 68.6; increase of 8.8%Improved
Add Lovász loss (ablation)AF2M + AFSM · SemanticKITTI validation seq 08mIoU: 68.6 -> 70.2Improved
Add geo-aware anisotropic loss with Lovász loss (ablation)AF2M + AFSM · SemanticKITTI validation seq 08mIoU: 70.2 -> 74.2Improved
Use (AF)²-S3Net instead of SPVNASSemanticKITTI test · SemanticKITTI testmIoU: 67.0 -> 69.7Improved
Use (AF)²-S3Net instead of MinkNet42nuScenes-lidarseg · nuScenes-lidarseg validationMean IoU: 60.8 -> 62.2Improved

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