no code implementations • 1 May 2024 • Colton R. Crum, Samuel Webster, Adam Czajka
Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic samples.
no code implementations • 13 Feb 2024 • Cary Coglianese, Colton R. Crum
If taken seriously, human-guided training can alleviate some of the technical and ethical pressures on AI, boosting AI performance with human intuition as well as better addressing the needs for fairness and effective explainability.
no code implementations • 30 Oct 2023 • Colton R. Crum, Adam Czajka
In this paper, we introduce MENTOR (huMan pErceptioN-guided preTraining fOr increased geneRalization), which addresses this question through two unique rounds of training the CNNs tasked with open-set anomaly detection.
no code implementations • 8 Jun 2023 • Colton R. Crum, Aidan Boyd, Kevin Bowyer, Adam Czajka
We compare the accuracy achieved by our teacher-student training paradigm with (1) training using all available human salience annotations, and (2) using all available training data without human salience annotations.