AI Paper Atlas

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

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng, Maxwell D. Collins, Ekin D. Cubuk, Barret Zoph, Hartwig Adam, Jonathon Shlens

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 169 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 pseudo-labeled video frames (train-sequence + train-extra) and WR-41 studentPanoptic-DeepLab X-71 · Cityscapes val-finePQ (%): 65.3 -> 69.1Improved
iterate once more with WR-41 teacherNaive-Student · Cityscapes val-finePQ (%): 69.1 -> 70.4Improved
initialize student from iteration 1 checkpoint (ablation)Naive-Student iteration 2 · Cityscapes val-finePQ (%): 70.4 -> 70.8Improved
train longer (60K to 120K iterations) (ablation)Panoptic-DeepLab on train-fine · CityscapesPQ (%): 62.9 -> 62.7No clear effect
add pseudo-labeled train-sequence instead of train-fine (ablation)Student X-71 · Cityscapes valPQ (%): 63.1 -> 65.3Improved
mix human-labeled train-fine with pseudo-labeled train-sequence (ablation)Student X-71 · Cityscapes valPQ (%): 65.3 -> 65.2Hurt
add pseudo-labeled train-extra (ablation)Student X-71 · Cityscapes valPQ (%): 65.3 -> 66.9Improved
add Void-Ego-Car assignment in teacher (ablation)Teacher pseudo-labels · Cityscapes valPQ (%): 66.8 -> 67.5Improved
add test-time augmentation to teacher (ablation)Teacher pseudo-labels · Cityscapes valPQ (%): 66.7 -> 67.5Improved
add val-fine human labels to teacher training (ablation)Teacher pseudo-labels · Cityscapes valPQ (%): 66.1 -> 67.5Improved
add Mapillary Vistas pretraining to teacher (ablation)Teacher pseudo-labels · Cityscapes valPQ (%): 65.3 -> 67.5Improved
add semi-supervised pseudo-label training (ablation)WR-41 · Cityscapes valPQ (%): 64.0 -> 69.1Improved

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