AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

Hanxue Liang, Hehe Fan, Zhiwen Fan, Yi Wang, Tianlong Chen, Yu Cheng, Zhangyang Wang

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 27 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 MLSP self-supervision on target dataDGCNN baseline · PointDA-10accuracy (%): 62.2 -> 71.0Improved
add cardinality prediction alone (ablation)DGCNN baseline · PointDA-10accuracy (%): 62.2 -> 68.7Improved
add position prediction alone (ablation)DGCNN baseline · PointDA-10accuracy (%): 62.2 -> 68.6Improved
add normal prediction alone (ablation)DGCNN baseline · PointDA-10accuracy (%): 62.2 -> 68.2Improved
combine cardinality, position and normal prediction (ablation)MLSP · PointDA-10accuracy (%): 68.7 -> 71.0Improved
use two-point KL cardinality loss instead of cross-entropy (ablation)MLSP cardinality only · PointDA-10accuracy (%): 67.8 -> 68.7Improved
increase cardinality classes beyond 8 (ablation)MLSP · PointDA-10accuracy (%)Hurt
use more than 15 neighbours for normal estimation (ablation)MLSP · PointDA-10accuracy (%)Hurt
add entropy-guided self-paced alignment (EGA)MLSP · PointDA-10accuracy (%): 71.0 -> 74.0Improved
select pseudo labels by entropy (EGA) instead of probability threshold (SPST)MLSP · PointDA-10accuracy (%): 73.8 -> 74.0Improved
apply MLSP to segmentationDGCNN · PointSegDAmean IoU (%): 58.1 -> 59.5 vs DefRecImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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