AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CPM: Class-conditional Prompting Machine for Audio-visual Segmentation

Yuanhong Chen, Chong Wang, Yuyuan Liu, Hu Wang, Gustavo Carneiro

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 14 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
replace softmax classifier with class-conditional GMM distribution modelling (CCDM) (ablation)AVSegFormer* baseline · AVSBench-SemanticsmIoU: 53.04 -> 54.12Improved
add visual conditional prompting (VCP) (ablation)baseline + CCDM · AVSBench-SemanticsmIoU: 54.12 -> 55.79Improved
add audio conditional prompting (ACP) (ablation)baseline + CCDM · AVSBench-SemanticsmIoU: 54.12 -> 55.07Improved
add both ACP and VCP (ablation)baseline + CCDM · AVSBench-SemanticsmIoU: 54.12 -> 56.41Improved
add prompting-based contrastive learning (PCL) (ablation)CCDM + VCP + ACP · AVSBench-SemanticsmIoU: 56.41 -> 57.25Improved
use GMM distribution representation instead of point representation (linear softmax) (ablation)CPM · AVSBench-SemanticsmIoU: +1.29% mIoU, +1.96% F-betaImproved
use 3 GMM components rather than other counts (M=1 to 7) (ablation)CPM · AVSBench-SemanticsmIoU: +1.42% mIoU, +1.95% F-beta (maximum improvement)Improved
replace masked average pooling with masked max pooling in PCL (ablation)CPM · AVSBench-SemanticsF-beta: -1.07%Hurt
vary loss weight lambda (0.1 too small, 1.0 too large, 0.5 used) (ablation)CPM · AVSBench-SemanticsmIoUMixed
apply CPM to stereo audio on VPO MSMICPM vs CAVP · VPO (MSMI)mIoU: 60.36 -> 60.55No clear effect
use CPM instead of CAVP at original resolutionAVSS · AVSS (full, original resolution)mIoU: 50.75 -> 57.25Improved
use CPM instead of CAVP for efficiencyAVSS · AVSS (full, original resolution)inference speed: 20 fps -> 14 fps; 22 h -> 30 h trainingHurt

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