Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks
Sign Up to like & getrecommendations! Published in 2022 at "Algorithms"
DOI: 10.3390/a15100384
Abstract: Modern trainable image recognition models are vulnerable to different types of perturbations; hence, the development of resilient intelligent algorithms for safety-critical applications remains a relevant concern to reduce the impact of perturbation on model performance.… read more here.
Keywords: model training; training method; method resilient; image ... See more keywords