AI Paper Atlas

Research map / Detection and segmentation / CNN features

SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information

Dasol Han, Jaewook Yoo, Dokwan Oh

CVPR 2022 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 6 citations (OpenAlex)

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 CPP pooling to auxiliary headsOCRNet · Cityscapes valmIoU (%): 81.17 -> 81.79Improved
Add CPP pooling to auxiliary headsDeepLabV3+ · Pascal VOC 2012 valmIoU (%): 78.35 -> 79.89Improved
Add CPP pooling to auxiliary headsANN · Pascal Context valmIoU (%): 44.42 -> 47.19Improved
Add CPP pooling to auxiliary headsOCRNet · NYU-Depth-v2 valmIoU (%): 58.09 -> 58.59Improved
Add CPP pooling (ablation)SeeThroughNet · Cityscapes valIoU (%): 84.06 -> 84.69Improved
Add multi-scale attention masks (ablation)SeeThroughNet · Cityscapes valIoU (%): 84.06 -> 84.37Improved
Combine CPP pooling with multi-scale attention masks (ablation)SeeThroughNet · Cityscapes valIoU (%): 84.06 -> 85.29Improved
Use CPP pooling with a multi-scale attention-coupled decoderSeeThroughNet · Cityscapes testmIoU (%): 85.61 -> 86.12Improved

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