Tag: weak supervision

An invariant-guided geometric framework detects anomalous execution regime transitions in distributed software telemetry under weak supervision.

A human-in-the-loop framework combining active learning with weak supervision halves the annotation effort needed for surgical tool segmentation in laparoscopic ...

A lightweight neural network classifies seven types of radio interference at a small urban telescope array with 95.37% accuracy and ...

A new method called Conflict-Aware Posterior Correction softens the hard masking used in partial-label learning, improving Top-1 accuracy by 1.01 ...

Researchers in Würzburg developed CAFEx, a weakly supervised AI pipeline that uses an anatomical bottleneck to estimate cardiac ejection fraction ...

Researchers at the University of Tehran have shown that a training-free, ontology-guided label propagation method can enrich weak AudioSet annotations ...

Researchers have developed a dual-channel graph completion network that reconstructs missing node features and structure simultaneously while performing well even ...

A new audit protocol reveals that machine learning models trained on cheap proxy labels for cryptocurrency risk can excel at ...

Researchers in China have developed a neighbor-constrained attention framework that improves how artificial intelligence classifies gigapixel whole-slide pathology images by ...