AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang, Samuel Schulter, Buyu Liu, Sparsh Garg, In So Kweon, Kuk-Jin Yoon

CVPR 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 61 citations (OpenAlex)

Check 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 MM-TTA soft selection instead of the strongest reported baseline3D semantic segmentation · A2D2 → SemanticKITTImIoU (Softmax avg): 49.1 -> 47.1Hurt
use MM-TTA soft selection instead of the strongest reported baseline3D semantic segmentation · Synthia → SemanticKITTImIoU (Softmax avg): 35.3 -> 35.1Hurt
use MM-TTA soft selection instead of the strongest reported baseline3D semantic segmentation · nuScenes Day → NightmIoU (Softmax avg): 50.8 -> 51.8Improved
add the slowly updated model to fast-model pseudo-label generation (ablation)MM-TTA Intra-PG · A2D2 → SemanticKITTImIoU (Softmax avg): 40.8 -> 41.9Improved
add pseudo-label thresholding to consensus fusion (ablation)MM-TTA Inter-PR · A2D2 → SemanticKITTImIoU (Softmax avg): 41.8 -> 43.8Improved
use mean-probability merging with pseudo-label thresholding (ablation)MM-TTA · A2D2 → SemanticKITTImIoU (Softmax avg): 41.6 -> 45.3Improved
add the slowly updated model to merge and thresholding (ablation)MM-TTA · A2D2 → SemanticKITTImIoU (Softmax avg): 41.6 -> 45.3Improved
select pseudo-labels using prediction entropy rather than the proposed consistency measure (ablation)MM-TTA Inter-PR · A2D2 → SemanticKITTImIoU (Softmax avg): 43.4 -> 47.1Hurt
use consistency-based hard selection instead of consistency-weighted soft selection (ablation)MM-TTA Inter-PR · A2D2 → SemanticKITTImIoU (Softmax avg): 47.0 -> 47.1No clear effect
set the hard-selection pseudo-label threshold to 0.1 rather than 0.3 (ablation)MM-TTA (Hard Select) · A2D2 → SemanticKITTImIoU (Softmax avg): 47.0 -> 45.2Hurt
set the hard-selection pseudo-label threshold to 0.5 rather than 0.3 (ablation)MM-TTA (Hard Select) · A2D2 → SemanticKITTImIoU (Softmax avg): 47.0 -> 46.7Hurt
set the hard-selection pseudo-label threshold to 0.7 rather than 0.3 (ablation)MM-TTA (Hard Select) · A2D2 → SemanticKITTImIoU (Softmax avg): 47.0 -> 46.2Hurt

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