Search Results for author:
Found 4 papers, 0 papers with code
Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models
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.
Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
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.
MENTOR: Human Perception-Guided Pretraining for Increased Generalization
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.
Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training
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.
