AI Paper Atlas

Research map / Point clouds / Point cloud classification

Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding

Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao

ICCV 2023 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 17 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
use coarse-to-fine semantic matching with distillation instead of MIL-NCEweakly supervised 3DVG · ScanRefer (ScanNet detector)R@3 IoU@0.25 Overall: 23.53 -> 34.12Improved
add class similarity (L_cls) to coarse candidate selection (ablation)coarse-to-fine matching model · ScanRefer (ScanNet detector)R@3 IoU@0.25: 12.28 -> 32.71Improved
add feature similarity (L_match) in addition to class similarity (ablation)coarse-to-fine matching model · ScanRefer (ScanNet detector)R@3 IoU@0.25: 32.71 -> 33.03Improved
add fine-grained masked-word reconstruction (L_recon) (ablation)coarse-to-fine matching model · ScanRefer (ScanNet detector)R@3 IoU@0.25: 33.03 -> 34.12Improved
select K=8 candidates rather than 4 or 32 (ablation)coarse-grained selection · ScanRefer (ScanNet detector)R@3 IoU@0.25: 33.68 (K=4), 31.29 (K=32) -> 34.12 (K=8)Improved
add knowledge distillation into 3DJCG matching module (ablation)coarse-to-fine matching model · ScanRefer (ScanNet detector)R@3 IoU@0.25: 31.71 -> 34.12Improved
add knowledge distillation for inference efficiency (ablation)matching phase · ScanRefermatching time and params: 31.4 ms -> 8.22 ms; 5.85 M -> 1.93 MImproved
distill into different matching architectures (SAT, 3DVG-Transformer, 3DJCG) (ablation)distillation · ScanRefer (ScanNet detector)R@3 IoU@0.25: 31.71 -> 33.70 (SAT), 34.61 (3DVG-Trans), 34.12 (3DJCG)Improved
use detector pretrained on SUN RGB-D instead of ScanNetNr3D/Sr3D · Nr3D and Sr3DR@3 IoU@0.25: 22.45 -> 10.36 (Nr3D)Hurt
use class similarity alone vs adding feature similarity alone (ablation)coarse selection · ScanRefer (SUN RGB-D detector)R@3 IoU@0.25: 9.03 -> 10.53 (L_match), 9.03 -> 13.10 (L_cls)Improved

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