MENTOR: Human Perception-Guided Pretraining for Increased Generalization

Incorporating human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture) and how to efficiently incorporate always-limited human perceptual data into training strategies of models. 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. First, we train an …

architecture capabilities cnn convolutional neural networks cs.cv data human mentor networks neural networks paper perception pretraining questions recognition research set strategies tasks training