AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Label Learning with Contrastive Cluster Self-Supervision for 3D Hierarchical Semantic Segmentation

Shuyu Cao, Chongshou Li, Jie Xu, Tianrui Li, Na Zhao

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning

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
use late-decoupled decoders per hierarchy instead of a shared decoder (ablation)ML3DHS · S3DIS-H, PointNet++Avg. mIoU (%): 62.17 -> 66.43Improved
add coarse-to-fine hierarchical guidance (ablation)ML3DHS · Campus3D, PointNet++Avg. mIoU (%): 59.96 -> 63.28Improved
add contrastive discrimination branch (ablation)ML3DHS · S3DIS-H, PointNet++Avg. mIoU (%): 62.98 -> 66.43Improved
add contrastive loss L_con (ablation)ML3DHS · S3DIS-H, PointNet++Avg. mIoU (%): 61.49 -> 66.43Improved
add cross-hierarchy consistency loss L_chc (ablation)ML3DHS · S3DIS-H, PointNet++Avg. mIoU (%): 64.09 -> 66.43Improved
add bi-branch self-supervised loss L_bis (ablation)ML3DHS · S3DIS-H, PointNet++Avg. mIoU (%): 62.98 -> 66.43Improved
replace DHL with ML3DHS on PointNet++DHL · S3DIS-HAvg. mIoU (%): 63.05 -> 66.43Improved
plug ML3DHS structure and losses into MTHSMTHS · SensatUrban-H, PointNet++Avg. mIoU (%): 47.20 -> 49.05Improved
plug ML3DHS structure and losses into DHLDHL · S3DIS-H, Point Transformer v3Avg. mIoU (%): 72.83 -> 75.34Improved
add auxiliary contrastive branch (training time)ML3DHS · time per epoch, PointNet++training timeHurt
vary auxiliary loss weight lambda in [0.1, 1.0] (ablation)ML3DHS · hyper-parameter analysisAvg. mIoU (%)No clear effect

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