AI Paper Atlas

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

CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation

Feng Wang, Huiyu Wang, Chen Wei, Alan Yuille, Wei Shen

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 34 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
pretrain with CP2 from scratch (200 epochs) instead of MoCo v2ResNet-50 200 ep · PASCAL VOC 2012 valmIoU: 74.9 -> 77.6 (+2.7)Improved
add 20-epoch CP2 Quick Tuning to MoCo v2 800-epochCP2 Quick Tuning (ResNet-50, MoCo v2 800 ep) · PASCAL VOC 2012 valmIoU: 77.2 -> 78.6 (+1.4)Improved
add 20-epoch CP2 Quick Tuning to MoCo v2 200-epochResNet-50 200 ep · PASCAL VOC 2012 valmIoU: 74.9 -> 76.5 (+1.6)Improved
add CP2 Quick Tuning to ViT-S/16 MoCo v2ViT-S/16 300 ep · PASCAL VOC 2012 valmIoU: 78.8 -> 79.5 (+0.7)Improved
pretrain the segmentation head with CP2 instead of random head (ResNet-50 200 ep) (ablation)CP2 200 ep · PASCAL VOC 2012 valmIoU: 76.3 -> 77.6Improved
pretrain the segmentation head with CP2 instead of random head (QT 800 ep) (ablation)CP2 Quick Tuning (ResNet-50, MoCo v2 800 ep) · PASCAL VOC 2012 valmIoU: 78.2 -> 78.6Improved
pretrain the segmentation head with CP2 instead of random head (ViT-S/16) (ablation)CP2 QT ViT-S/16 · PASCAL VOC 2012 valmIoU: 79.3 -> 79.5Improved
use CP2 backbone with random head versus MoCo v2 (backbone effect alone) (ablation)CP2 200 ep · PASCAL VOC 2012 valmIoU: 74.9 -> 76.3 (+1.4)Improved
add copy-paste composition (instance loss only, masked pooling) over no copy-paste (ablation)CP2 Quick Tuning (ResNet-50, MoCo v2 800 ep) · PASCAL VOC 2012 valmIoU: 77.6 -> 78.0Improved
add dense contrastive loss to instance loss (ablation)CP2 Quick Tuning (ResNet-50, MoCo v2 800 ep) · PASCAL VOC 2012 valmIoU: 78.0 -> 78.6 (+0.6)Improved
add instance contrastive loss to dense loss (ablation)CP2 Quick Tuning (ResNet-50, MoCo v2 800 ep) · PASCAL VOC 2012 valmIoU: 75.6 -> 78.6Improved
use rectangular masks instead of random patches (ablation)CP2 QT ResNet-50 · PASCAL VOC 2012 valmIoU: 75.3 -> 78.6Improved

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