Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models

arXiv:2405.00650v1 Announce Type: new
Abstract: 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. After the initial collection phase, human visual saliency (e.g., eye-tracking data, or handwritten annotations) can be integrated into model training through attention mechanisms, augmented training samples, or through human perception-related components of loss functions. Despite their successes, a vital, but seemingly neglected, aspect of …

abstract arxiv biometric capability collection cs.cv data detection human intelligence presentation samples synthetic tasks tracking tracking data training type visual