5 papers
Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction
Zexing Zhang, Jichao Li, Tianyang Lei +2
In pattern analysis, models trained independently for the same task often develop complementary capabilities through differences in architecture, data, and optimization. Exploiting…
Beyond Scarcity: When Encoder Adaptation Is Worthwhile
Zexing Zhang, Jichao Li, Tianyang Lei +2
Long-tailed recognition often learns a shared representation before correcting the classifier for class imbalance. Once the classifier has been rebalanced, however, final accuracy…
Selective Posterior Margin Regularization for Forward-Corrected Classification
Zexing Zhang, Jichao Li, Tianyang Lei +2
Learning with class-conditional label noise often relies on a transition model from latent clean classes to observed annotations. Forward correction embeds this transition in the l…
More Criticism Does Not Make a Better Review: EquiReview-R
Zexing Zhang, Jichao Li, Tianyang Lei +2
AI reviewers can now produce many specific criticisms, but more criticism is not necessarily a better review. A review may miss a consequential weakness or retain an allegation tha…
Non-invasive Blood Glucose Estimation from Wearable Physiological Signals
Zexing Zhang, Jichao Li, Yilong Wang +2
Non-invasive blood glucose estimation from wearable physiological signals remains difficult because longitudinal photoplethysmography (PPG) data are subject to distribution drift,…