AI Paper Atlas

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

On Regularized Losses for Weakly-supervised CNN Segmentation

Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov

ECCV 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 299 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 CRF loss on unlabeled pixels to partial cross entropy (ablation)DeepLab-MSc-largeFOV · PASCAL VOC12 val (scribbles)mIoU: 56.0 -> 63.1Improved
add normalized cut loss to partial cross entropy (ablation)DeepLab-MSc-largeFOV · PASCAL VOC12 val (scribbles)mIoU: 56.0 -> 60.5Improved
use CRF loss instead of normalized cut lossDeepLab-MSc-largeFOV · PASCAL VOC12 val (scribbles)mIoU: 60.5 -> 63.1Improved
add normalized cut term to CRF loss (KernelCut loss) (ablation)DeepLab-MSc-largeFOV+CRF · PASCAL VOC12 val (scribbles)mIoU: 65.9 -> 66.7Improved
add normalized cut term to CRF loss (KernelCut loss) (ablation)DeepLab-ResNet101+CRF · PASCAL VOC12 val (scribbles)mIoU: 75.0 -> 75.0No clear effect
use direct CRF loss instead of online CRF proposal generation (SEC*)DeepLab-MSc-largeFOV · PASCAL VOC12 val (scribbles)mIoU: 61.3 -> 63.1Improved
use direct CRF loss instead of one-time GrabCut proposalsDeepLab-MSc-largeFOV · PASCAL VOC12 val (scribbles)mIoU: 55.5 -> 63.1Improved
update proposals online each iteration instead of offline alternation (ScribbleSup)DeepLab-MSc-largeFOV+CRF · PASCAL VOC12 val (scribbles)mIoU: 63.1 -> 65.4Improved
add direct CRF loss to seeding and expansion losses (ablation)DeepLab-largeFOV · PASCAL VOC12 val (image-level tags)mIoU: 38.4 -> 43.9Improved
replace constrain-to-boundary loss with direct CRF lossSEC · PASCAL VOC12 val (image-level tags)mIoU: 43.7 -> 43.9No clear effect
replace constrain-to-boundary loss with direct CRF lossSEC · PASCAL VOC12 val (image-level tags)training time (s/batch): 1.19 -> 0.98Improved
add back-propagation through the CRF inference layer (ablation)SEC · PASCAL VOC12 val (image-level tags)mIoU: 43.8 -> 43.7No clear effect

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