AI Paper Atlas

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

Universal Semi-Supervised Semantic Segmentation

Tarun Kalluri, Girish Varma, Manmohan Chandraker, C.V. Jawahar

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 122 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 within- and cross-dataset entropy losses to joint training (ablation)Univ-basic · CS+CamVid average (N=100, ResNet-18)mIoU: 43.97 -> 47.83Improved
add within- and cross-dataset entropy losses to joint training (ablation)Univ-basic · CS+CamVid average (N=50, ResNet-18)mIoU: 40.69 -> 43.62Improved
add cross-dataset entropy loss only (ablation)Univ-basic · CamVid test (N=100, ResNet-18)mIoU: 51.90 -> 49.31Hurt
add within-dataset entropy loss on top of cross-dataset loss (ablation)Univ-cross · CS+CamVid average (N=100, ResNet-18)mIoU: 43.57 -> 47.83Improved
add entropy losses to joint training (ablation)Univ-basic · CS+IDD average (N=100, ResNet-18)mIoU: 31.58 -> 31.97Improved
add entropy losses to joint training (ablation)Univ-basic · CS+IDD average (N=1500, ResNet-50)mIoU: 58.38 -> 59.63Improved
add entropy losses to joint training (ablation)Univ-basic · CS+SUN-RGBD average (1.5k labeled, ResNet-50)mIoU: 44.78 -> 50.52Improved
add entropy losses to joint training (ablation)Univ-basic · Cityscapes val (N=100, CS+IDD, ResNet-18)mIoU: 37.94 -> 36.48Hurt
use K=3 prototype embeddings per label instead of 1 (ablation)Univ-full · CS+CamVid average (N=100, ResNet-18)mIoU: 47.83 -> 48.39Improved
use K=5 prototype embeddings per label instead of 1 (ablation)Univ-full · CS+CamVid average (N=100, ResNet-18)mIoU: 47.83 -> 47.55Hurt
use prototype label embeddings instead of Word2Vec (ablation)Univ-full · CS+CamVid average (N=100, ResNet-18)mIoU: 44.45 -> 47.83Improved
keep label embeddings fixed instead of updating them (theta=0.5) (ablation)Univ-full · CS+CamVid average (N=100, ResNet-18)mIoU: 41.50 -> 47.83Improved

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