AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

Chenfeng Xu, Bichen Wu, Zining Wang, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

ECCV 2020 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 455 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 SAC-ISK to SSGV3-21 baseline (ablation)SSGV3-21 baseline · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.0 -> 46.3Improved
add SAC-SK to baseline (ablation)SSGV3-21 baseline · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.0 -> 45.4Improved
add SAC-S to baseline (ablation)SSGV3-21 baseline · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.0 -> 44.9Improved
add input-channel dimension to SAC-S attention (SAC-IS) (ablation)SAC-S · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.9 -> 44.0Hurt
add kernel dimension attention to SAC-S (SAC-SK) (ablation)SAC-S · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.9 -> 45.4Improved
swap SAC-ISK for squeeze-and-excitation (SE) (ablation)SAC-ISK · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 46.3 -> 44.2Hurt
swap SAC-ISK for context-aggregation module (CAM) (ablation)SAC-ISK · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 46.3 -> 42.1Hurt
swap SAC-SK for pixel-adaptive convolution (PAC) (ablation)SAC-SK · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 45.4 -> 45.2Hurt
use CBAM instead of no attention (ablation)baseline · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.0 -> 44.8Improved
increase SAC attention kernel from 1x1 to 7x7 (ablation)SAC-ISK · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 45.5 -> 46.3Improved
increase SAC attention kernel from 3x3 to 5x5 (ablation)SAC-ISK · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 44.5 -> 45.4Mixed
remove last two downsampling layers and reduce channels of last two stages to 256 (ablation)RangeNet21 · SemanticKITTI val (64x512, SSGV3-21 ablation)mIoU (%): 38.6 -> 42.5Improved

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