AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation

Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Shenghai Yuan, Lihua Xie

ICCV 2023 · Continual learning › Domain and prompt-based · approach: Continual test-time adaptation · 33 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
adaptive centroid-weighted fusion of raw and augmentation-average predictions (iMPA) instead of augmentation-average only (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 5.8% degradation using pure augmentation-averageImproved
add centroid-based weighting in iMPA and xMPF versus simple average fusion (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: more than 2.5%Improved
update class-wise centroids by enqueuing confident target features (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 6.1% decrease without updateImproved
add stochastic restoring of pseudo-source features in CMQs (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 8.4% gap without restoreImproved
increase number of 3D augmentations from 1 to 5 (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 33.2 -> 36.6Improved
increase number of 2D augmentations from 1 to 5 (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 35.0 -> 35.3No clear effect
lower restoring probability to 0.3 (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 36.6 -> 34.5Hurt
add confidence filtering tau_cf (0.0 -> 0.8) (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 34.8 -> 36.6Improved
add class-wise contrastive loss (lambda_cts 0.0 -> 1.0) (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 35.8 -> 36.6Improved
add model-based stochastic restoration to MMTTAMMTTA · SemanticKITTI-to-SynthiamIoU: 25.6 -> 28.7Improved
evaluate at end of each sequence (E-Test) instead of immediately (ablation)CoMAC · SemanticKITTI-to-SynthiamIoU: 6.1% improvementImproved

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