AI Paper Atlas

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

Underground Diagnosis Based on GPR and Learning in the Model Space

Ao Chen, Xiren Zhou, Yizhan Fan, Huanhuan Chen

TPAMI 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 18 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
use KNN in 2D-ESN model space instead of HOG+SVManomaly classification · GPR comparisonF1 (%): 95.46% -> 98.29%Improved
use model-space KNN instead of AlexNetanomaly classification · GPR comparisonF1 (%): 95.55% -> 98.29%Improved
use model-space KNN instead of ResNet-18anomaly classification · GPR comparisonF1 (%): 95.87% -> 98.29%Improved
use model-space KNN instead of ResNet-18 for training timeanomaly classification · GPR comparisonTime (s): 543 -> 20.71Improved
use model-space KNN instead of HOG+SVM for timeanomaly classification · GPR comparisonTime (s): 2.57 -> 20.71Hurt
use KNN instead of SVM in the model space (ablation)2D-ESN model space · GPR supervisedF1 (%): 95.11% -> 98.29%Improved
use KNN instead of Random Forest in the model space (ablation)2D-ESN model space · GPR supervisedF1 (%): 97.04% -> 98.29%Improved
map GPR images to 2D-ESN model space instead of data space for CNNanomaly classification · new roadsAccuracy: about 80% -> 98.29%Improved

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