AI Paper Atlas

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

Semi-Supervised Vision Transformers

Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 42 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 FixMatch-style pseudo labels to ViT-SViT-S · ImageNet 10% labelstop-1 accuracy: 48.6 -> 59.0 (+10.4)Improved
use CNN pseudo labels instead of ViT pseudo labels (conv-labeled)ViT-S · ImageNet 10% labelstop-1 accuracy: 59.0 -> 67.2Improved
add cross-stream feature fusion to conv-labeled (ablation)ViT-S + Conv · ImageNet 10% labelstop-1 accuracy: 67.2 -> 72.4 (+5.2)Improved
add cross-stream feature fusion to conv-labeled (PiT-S) (ablation)PiT-S + Conv · ImageNet 10% labelstop-1 accuracy: 67.8 -> 70.8Improved
add cross-stream feature fusion to conv-labeled (ConvMixer) (ablation)ViT-S + ConvMixer · ImageNet 10% labelstop-1 accuracy: 66.7 -> 72.9Improved
average predictions of both streams at inference instead of transformer stream only (ablation)Semiformer ViT-S + Conv · ImageNet 10% labelstop-1 accuracy: 72.4 -> 73.5Improved
generate pseudo labels with CNN stream instead of transformer stream (ablation)Semiformer · ImageNet 10% labelstop-1 accuracy: 67.4 -> 73.5Improved
average CNN and transformer predictions for pseudo labels instead of CNN only (ablation)Semiformer · ImageNet 10% labelstop-1 accuracy: no better than 73.5Hurt
add Semiformer on 5% labels over conv-labeled (ablation)ViT-S + Conv · ImageNet 5% labelstop-1 accuracy: 62.0 -> 66.3 (+4.3)Improved
add Semiformer on 20% labels over conv-labeled (ablation)ViT-S + Conv · ImageNet 20% labelstop-1 accuracy: 74.8 -> 78.1 (+3.3)Improved
add Semiformer on Places205 5% labels over conv-labeled (ablation)ViT-S + Conv · Places205 5% labelstop-1 accuracy: 52.5 -> 53.8 (+1.3)Improved
add Semiformer on Places205 over vanilla ViT-SViT-S · Places205 5% labelstop-1 accuracy: 46.9 -> 53.8 (+6.9)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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