AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance

Xiaoxu Xu, Yitian Yuan, Jinlong Li, Qiudan Zhang, Zequn Jie, Lin Ma, Hao Tang, Nicu Sebe, Xu Wang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 3 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 scene-level label filtering to pseudo labels (ablation)baseline MinkowskiNet18A · S3DISmIoU: 37.7 -> 42.6Improved
add Embeddings Soft-Guidance Stage instead of direct pseudo-label supervision (ablation)baseline MinkowskiNet18A · S3DISmIoU: 37.7 -> 38.2Improved
add filtering and Embeddings Specialization Stage on top of soft-guidance (ablation)3DSS-VLG · S3DISmIoU: 38.2 -> 45.3Improved
use text-embedding guidance from 2D vision-language model instead of CAM3D WSSS with scene-level labels · S3DISmIoU: 27.7 -> 45.3 versus MITImproved
3DSS-VLG with scene-level labels versus Kweon et al. with extra image-level labels3DSS-VLG · ScanNet testmIoU: 47.4 -> 48.9Improved
change 3D backbone from MinkowskiNet18A to 14A or 34A (ablation)3DSS-VLG · S3DISmIoU: 45.3 -> 44.5 (14A), 44.7 (34A)Hurt
use Transformers instead of MLP in ESS adapter (ablation)3DSS-VLG · S3DISmIoU: 45.3 -> 45.0No clear effect
train on S3DIS and test on ScanNet versus the reverse3DSS-VLG · cross-dataset generalizationmIoU: S3DIS->ScanNet 13.4; ScanNet->S3DIS 33.3Mixed

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