AI Paper Atlas

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

A Semi-Supervised Deep Rule-Based Approach for Complex Satellite Sensor Image Analysis

Xiaowei Gu, Plamen Parvanov Angelov, Ce Zhang, Peter M. Atkinson

TPAMI 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 22 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 chunk-wise semi-supervised pseudo-labelling over DRB baselineSeRBIA · WHU-RS 10% labelledaccuracy: 0.8454 -> 0.9006Improved
add chunk-wise semi-supervised learning over DRB baselineSeRBIA · NWPU45 10% labelledaccuracy: 0.7411 -> 0.8732Improved
add chunk-wise semi-supervised learning over DRB baselineSeRBIA · AID 20% labelled (SOTA protocol)accuracy: 0.8358 -> 0.9429Improved
add chunk-wise semi-supervised learning over DRB baselineSeRBIA · UCMerced 10% labelledaccuracy: 0.8025 -> 0.8871Improved
use SeRBIA instead of LGC semi-supervised baselineSeRBIA · RSSCN7 10% labelledaccuracy: 0.8848 -> 0.8740Hurt
use SeRBIA instead of LGCSeRBIA · AID 10% labelledaccuracy: 0.8290 -> 0.8053Hurt
use SeRBIA instead of TSDA-ELMSeRBIA · WHU-RS 60% labelledaccuracy: 0.9892 -> 0.9802Hurt
increase labelled ratio from 10% to 20%SeRBIA · AIDaccuracy: 0.8053 -> 0.8351Improved
lower phi (looser pseudo-label rigour) (ablation)SeRBIA · Singapore/UCMerced/WHU-RS/RSSCN7 (10% labelled)accuracyHurt
raise phi (stricter pseudo-labelling) (ablation)SeRBIA · Singapore/UCMerced/WHU-RS/RSSCN7 (10% labelled)accuracyHurt
increase gamma (more sensitivity to new patterns) (ablation)SeRBIA · Singapore/UCMerced/WHU-RS/RSSCN7 (10% labelled)accuracyImproved
vary chunk size W from 100 to 800 (ablation)SeRBIA · Singapore/UCMerced/WHU-RS/RSSCN7 (10% labelled)accuracyNo clear effect

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