AI Paper Atlas

Research map / Detection and segmentation / CNN features

GP-S3Net: Graph-Based Panoptic Sparse Semantic Segmentation Network

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

ICCV 2021 · Detection and segmentation › CNN features · approach: Unified panoptic segmentation · 56 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
replace DBSCAN clustering with the GNN edge-classification instance network (ablation)semantic backbone with clustering · SemanticKITTI valPQ: 49.4 -> 63.3Improved
replace HDBSCAN clustering with the GNN edge-classification instance network (ablation)semantic backbone with clustering · SemanticKITTI valPQ: 53.4 -> 63.3Improved
replace MeanShift clustering with the GNN edge-classification instance network (ablation)semantic backbone with clustering · SemanticKITTI valPQ: 55.8 -> 63.3Improved
replace MeanShift clustering with the GNN edge-classification instance network (ablation)semantic backbone with clustering · SemanticKITTI valPQ Th: 55.7 -> 70.2Improved
use MeanShift instead of HDBSCAN as clustering baseline (ablation)semantic backbone with clustering · SemanticKITTI valPQ: 53.4 -> 55.8Improved
use HDBSCAN instead of DBSCAN as clustering baseline (ablation)semantic backbone with clustering · SemanticKITTI valPQ: 49.4 -> 53.4Improved
use GP-S3Net instead of DS-NetDS-Net · SemanticKITTI testPQ: 55.9 -> 60.0Improved
use GP-S3Net instead of PanosterPanoster · SemanticKITTI testPQ: 52.7 -> 60.0Improved
use GP-S3Net instead of EfficientLPSEfficientLPS · SemanticKITTI testPQ: 57.4 -> 60.0Improved
use GP-S3Net instead of EfficientLPSEfficientLPS · SemanticKITTI testPQ St: 60.5 -> 56.4Hurt
use GP-S3Net instead of EfficientLPSEfficientLPS · nuScenes valPQ: 59.2 -> 61.0Improved
use GP-S3Net instead of DS-NetDS-Net · SemanticPOSS valPQ: 35.6 -> 48.7Improved

Later papers that compared with this method

1 later accepted paper reports GP-S3Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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