AI Paper Atlas

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

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Chenyang Si, Xuecheng Nie, Wei Wang, Liang Wang, Tieniu Tan, Jiashi Feng

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 79 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 neighborhood consistency regularization to Sup. (ablation)Sup. + Inp. · NTU RGB+D CS (5% labels)accuracy: 48.4 -> 55.2Improved
add neighborhood consistency instead of inpainting (ablation)Supervised-only · NTU RGB+D CS (5% labels)accuracy: 48.4 -> 52.1Improved
add neighborhood consistency instead of inpainting (ablation)Supervised-only · N-UCLA (15% labels)accuracy: 46.6 -> 60.0Improved
add skeleton inpainting to neighborhood consistency (ablation)Sup. + Nei. · N-UCLA (15% labels)accuracy: 60.0 -> 66.4Improved
add adversarial regularization to Sup. + Inp. + Nei. (ablation)ASSL · N-UCLA (15% labels)accuracy: 66.4 -> 74.8Improved
add adversarial regularization to Sup. + Inp. + Nei. (ablation)ASSL · NTU RGB+D CS (5% labels)accuracy: 55.2 -> 57.3Improved
add adversarial regularization to Sup. + Nei. (ablation)Sup. + Nei. · NTU RGB+D CS (5% labels)accuracy: 52.1 -> 53.4Improved
add adversarial regularization to Sup. + Inp. (ablation)Sup. + Inp. · N-UCLA (15% labels)accuracy: 46.6 -> 52.4Improved
add skeleton inpainting self-supervision (S4L) to supervised trainingSupervised-only · N-UCLA (5% labels)accuracy: 34.1 -> 35.3No clear effect
add skeleton inpainting self-supervision (S4L) to supervised trainingSupervised-only · NTU RGB+D CS (5% labels)accuracy: 47.2 -> 48.4No clear effect
replace VAT + EntMin with ASSLVAT + EntMin · NTU RGB+D CS (5% labels)accuracy: 51.7 -> 57.3Improved
replace VAT + EntMin with ASSLVAT + EntMin · NTU RGB+D CS (40% labels)accuracy: 70.8 -> 72.3Improved

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