AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks

Sanbao Su, Xin Li, Thang Doan, Sima Behpour, Wenbin He, Liang Gou, Fei Miao, Liu Ren

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Semi-supervised instance segmentation · 0 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
add region-level loss to meta model training (ablation)MetaAT · Pascal VOC UNet image levelER (%): 10.95 -> 6.21Improved
add equal-width binning (regression to classification) (ablation)MetaAT · Pascal VOC UNet image levelER (%): 8.02 -> 6.21Improved
use ViT meta model instead of ResNet or MLP (ablation)MetaAT · Pascal VOC UNet image levelER (%): 7.69 (ResNet) / 10.73 (MLP) -> 6.21Improved
add output entropy as meta model input (ablation)MetaAT · Segmentation region-16 levelER (%): 10.36 -> 4.27Improved
add target model output as meta model input (ablation)MetaAT · Segmentation region-16 levelER (%): 5.38 -> 4.27Improved
add original image as meta model input (ablation)MetaAT · Segmentation region-16 levelER (%): 4.54 -> 4.27No clear effect
region-level instead of image-level annotationMetaAT · Pascal VOC segmentationlabels needed for ER below 10%: 2.5% -> less than 0.05% (region-32), 0.02% (region-16)Improved
MetaAT vs RS on ADE20K FCN image levelMetaAT · ADE20K FCN image levelER (%): 7.85 (RS) vs 8.08No clear effect
MetaAT vs random sampling on COCO detectionMetaAT · COCO detection image levelER (%): 2.19 -> 0.67Improved

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