SGC uses anomaly scores from an unsupervised generative network as a normalized pathological prior fused into deep features to improve EEG-based MDD detection without data augmentation or synthesis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
SGC uses anomaly scores from an unsupervised generative network as a normalized pathological prior fused into deep features to improve EEG-based MDD detection without data augmentation or synthesis.