AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi Supervised Semantic Segmentation Using Generative Adversarial Network

Nasim Souly, Concetto Spampinato, Mubarak Shah

ICCV 2017 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 604 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 unlabeled data via GAN semi-supervised trainingFCN-VGG16 baseline · VOC 2012 val (all labeled + unlabeled)mean IU: 59.5 -> 64.1Improved
add unlabeled data via GAN semi-supervised trainingFCN-VGG16 baseline · VOC 2012 val (all labeled + unlabeled)mean accuracy: 69.2 -> 80.7Improved
add unlabeled data via GAN semi-supervised trainingFCN-VGG16 baseline · VOC 2012 val (all labeled + unlabeled)pixel accuracy: 89.9 -> 90.5No clear effect
add image-level class conditioning (weak supervision) to semi-supervised GANSemi Supervised GAN · VOC 2012 val (all labeled + unlabeled)mean IU: 64.1 -> 65.8Improved
add image-level class conditioning (weak supervision) to semi-supervised GANSemi Supervised GAN · VOC 2012 val (all labeled + unlabeled)mean accuracy: 80.7 -> 80.0No clear effect
add unlabeled data via GAN semi-supervised trainingFully supervised · VOC 2012 val (30% labeled)mean IU: 38.9 -> 42.2Improved
add weak supervisionFully supervised · VOC 2012 val (30% labeled)mean IU: 38.9 -> 44.6Improved
add unlabeled data via GAN semi-supervised trainingFully supervised · SiftFlow (2000 unlabeled SUN2012 images)mean IU: 34.4 -> 35.1Improved
add unlabeled data with 20% labeled dataFull · VOC 2012 val (20% labeled)mean IU: 16.0 -> 19.8Improved
add unlabeled data with 50% labeled dataFull · VOC 2012 val (50% labeled)pixel accuracy: 88.5 -> 88.4No clear effect
add unlabeled data via GAN semi-supervised trainingFully supervised · StanfordBG (10k unlabeled PASCAL images)mean IU: 53.1 -> 63.3Improved
add unlabeled frames via GAN semi-supervised trainingOurs Fully supervised · CamVid (11k unlabeled frames)pixel accuracy: 88.4 -> 87.0Hurt

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