AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Language-Assisted 3D Feature Learning for Semantic Scene Understanding

Junbo Zhang, Guofan Fan, Guanghan Wang, Zhengyuan Su, Kaisheng Ma, Li Yi

AAAI 2023 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 4 citations (OpenAlex)

Read the paper

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 language-assisted training with object-level relationship and attribute supervisionVoteNet · ScanNetV2 object detectionmAP@0.5: 31.67 -> 33.41Improved
Add language-assisted trainingMLCVNet · ScanNetV2 object detectionmAP@0.5: 30.18 -> 33.69Improved
Add language-assisted trainingVoteNet · ScanNetV2 detection with 1 or 4 boxes per scenemAP@0.25: 13.74 -> 18.55; 23.08 -> 30.61Improved
Add language-assisted training to PointGroupPointGroup · ScanNetV2 instance segmentationmAP@0.5: 55.7 -> 56.9Improved
Train the 3D backbone with language assistanceScanRefer · ScanRefer val visual grounding, overall 3D inputAcc@0.5IoU: 25.81 -> 28.00Improved
Train the 3D backbone with language assistanceScan2Cap · ScanRefer val captioningCiDEr@0.25IoU: 50.95 -> 52.97Improved
Add relationship classification auxiliary supervision (ablation)VoteNet · ScanNetV2 object detectionmAP@0.5: 31.67 -> 32.47Improved
Add attribute classification auxiliary supervision (ablation)VoteNet · ScanNetV2 object detectionmAP@0.5: 31.67 -> 32.80Improved
Add both relationship and attribute classification tasks (ablation)VoteNet · ScanNetV2 object detectionmAP@0.5: 31.67 -> 33.41Improved
Increase the number of relationship categories from 5 to 16 (ablation)VoteNet with language-assisted training · ScanNetV2 object detectionmAP@0.5: 32.48 -> 33.46Improved
Increase the number of attribute categories from 13 to 37 (ablation)VoteNet with language-assisted training · ScanNetV2 object detectionmAP@0.5: 32.81 -> 33.31Improved
Use binary cross-entropy rather than cross-entropy for relation classification (ablation)VoteNet with language-assisted training · ScanNetV2 object detectionmAP@0.5: 32.51 -> 33.13Improved

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