AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention Sampling

Cheng-Kun Yang, Yung-Yu Chuang, Yen-Yu Lin

ICCV 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 14 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 mutual attention instead of self-attention (ablation)co-contrastive samplers · ScanObjectNNmIoU: 0.59 -> 0.61Improved
add mutual attention instead of self-attention (ablation)co-contrastive samplers · S3DISmIoU: 0.45 -> 0.46Improved
add attention module (mutual) to losses (ablation)samplers with all three losses · ScanObjectNNmIoU: 0.57 -> 0.61Improved
add attention module (mutual) to losses (ablation)samplers with all three losses · S3DISmIoU: 0.43 -> 0.46Improved
use unsupervised co-segmentation vs cloud-level weak supervision (MPRM)segmentation · ScanObjectNN OBJ_BGmIoU: 0.518 -> 0.605Improved
use our method vs Xu et al. 10% point labelssegmentation · ScanObjectNN OBJ_BGmIoU: 0.602 vs 0.605No clear effect
use our method vs AdaCoSegsegmentation · ScanObjectNN OBJ_BGmIoU: 0.385 -> 0.605Improved
use our method vs Xu et al. 10% point labelssegmentation · S3DISmIoU: 0.706 vs 0.463Hurt
vary number of sampled FG/BG points (256/512/1024) (ablation)samplers · ScanObjectNN OBJ_BGmIoU: .54 to .61No clear effect
train BGA with our pseudo labelsPointNet++ classification · ScanObjectNN PB_T50_RSaccuracy (%): 78.5 -> 79.4Improved
train BGA with our pseudo labelsDGCNN classification · ScanObjectNN PB_T50_RSaccuracy (%): 78.1 -> 79.1Improved

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