AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni, Nicu Sebe, Fabio Poiesi, Elisa Ricci

TPAMI 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 28 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 source-to-target mixing branch (ablation)CoSMix t->s only · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 31.6 -> 35.0Improved
add mean teacher update (ablation)CoSMix both branches · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 35.0 -> 35.4Improved
add local augmentation h (ablation)CoSMix (d) · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 35.4 -> 36.8Improved
add global augmentation r (ablation)CoSMix (d) · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 35.4 -> 37.3Improved
add both local and global augmentations (ablation)CoSMix (d) · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 35.4 -> 39.0Improved
add long-tail weighted class selection f (ablation)CoSMix (g) · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 39.0 -> 40.4Improved
raise pseudo-label confidence threshold to 0.95 (ablation)CoSMix-UDA · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 40.4 -> 39.2Hurt
lower pseudo-label confidence threshold to 0.65 (ablation)CoSMix-UDA · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 40.4 -> 40.2No clear effect
use CoSMix double-branch mixing instead of PointCutMix (ablation)mixing strategy · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 31.6 -> 38.9Improved
use s->t branch alone instead of t->s alone (ablation)CoSMix mixing · SynLiDAR to SemanticPOSS (UDA ablation)mIoU: 32.9 -> 34.8Improved
use CoSMix SSDA mixing instead of naive use of labeled target points (ablation)CoSMix-SSDA · SynLiDAR to SemanticPOSS (SSDA)mIoU: 33.7 -> 41.0Improved
add few labeled target samples (SSDA over UDA)CoSMix · SynLiDAR to SemanticKITTImIoU: 32.2 -> 34.3Improved

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