AI Paper Atlas

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

Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

Fatemehsadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Stephen Gould, Jose M. Alvarez

ECCV 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 158 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 the built-in foreground/background mask to the loss (ablation)weakly-supervised segmentation (tags) · PASCAL VOC 2012 val (image tags)mIoU (%): 31.0 -> 44.8Improved
add the built-in mask on MIRFLICKR-1M training (ablation)weakly-supervised segmentation (tags) · PASCAL VOC 2012 val (trained on MIRFLICKR-1M subset)mIoU (%): 30.6 -> 38.1Improved
use built-in mask instead of external objectness priorweakly-supervised segmentation · PASCAL VOC 2012 val (image tags)mIoU (%): 32.2 -> 44.8Improved
add dense CRF smoothingOurs (Tags) · PASCAL VOC 2012 val (image tags)mIoU (%): 44.8 -> 46.6Improved
add dense CRF smoothingOurs (CheckMask) · PASCAL VOC 2012 val (additional weak supervision)mIoU (%): 49.0 -> 51.5Improved
switch to the final loss formulation instead of the Eq. variant (ablation)Ours (Tags) · PASCAL VOC 2012 val (image tags)mIoU (%): 44.8 -> 44.8No clear effect
add CheckMask supervision (choose best mask among candidates)Ours (Tags) · PASCAL VOC 2012 val (image tags) with CRFmIoU (%): 4.9 mIOU pointImproved
add CheckMask supervisionOurs (Tags) · PASCAL VOC 2012 val (image tags)mIoU (%): 4.2 mIOU pointImproved
add CheckMask supervisionOurs (Tags) · PASCAL VOC 2012 val (trained on MIRFLICKR-1M subset)mIoU (%): 38.1 -> 43.9Improved
use Ours instead of CCNNMIRFLICKR-1M-trained model · PASCAL VOC 2012 val (trained on MIRFLICKR-1M subset)mIoU (%): 30.5 -> 38.1Improved
use Ours instead of CCNN on rare class chairMIRFLICKR-1M-trained model · Chair class IoU, PASCAL VOC 2012 val (trained on MIRFLICKR-1M subset)mIoU (%): 10.7 -> 17.0Improved
use Ours instead of CCNN on rare class sofaMIRFLICKR-1M-trained model · Sofa class IoU, PASCAL VOC 2012 val (trained on MIRFLICKR-1M subset)mIoU (%): 0 -> 16.8Improved

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