Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models
This work addresses the cost-effectiveness of human saliency integration for biometric security, but it is incremental as it focuses on optimizing existing methods rather than introducing new paradigms.
The paper tackled the problem of optimizing saliency granularity in training biometric attack detection models, demonstrating that simple saliency post-processing techniques improve generalization in presentation attack detection and synthetic face detection across various CNNs.
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 any saliency-based training is the level of salience granularity (e.g., bounding boxes, single saliency maps, or saliency aggregated from multiple subjects) necessary to find a balance between reaping the full benefits of human saliency and the cost of its collection. In this paper, we explore several different levels of salience granularity and demonstrate that increased generalization capabilities of PAD and synthetic face detection can be achieved by using simple yet effective saliency post-processing techniques across several different CNNs.