Eye pupil localization is one of the indispensable technologies in various computer vision applications such as virtual reality and augmented reality. In general, the algorithm consists of finding the approximate eye region and finding the pupil position by extracting the semantic feature from each eye region. However, the performance of the eye pupil location is affected not only by illumination and image resolution but also by glasses wear. Therefore, this paper proposes an eye pupil localization algorithm which is robust against the above disturbance conditions and provides high accuracy. First, a face is detected from an input image and it is determined whether to wear glasses using the detected face. If glasses are present, the glasses are removed to find the correct eye region. Then, facial landmarks are extracted, and eye regions are detected based on facial landmarks. Next, the pupil region is segmented using fully convolutional networks. Finally, the position of the segmented pupil is calculated. Experimental results show that the proposed algorithm outperforms the state-of-the-art algorithms for public databases such as BioID and GI4E by up to 3.44% 0.5%, respectively.
Knowledge distillation (KD) is one of the most effective neural network light-weighting techniques when training data is available. However, KD is seldom applicable to an environment where it is difficult or impossible to access training data. To solve this problem, a complete zero-shot KD (C-ZSKD) based on adversarial learning has been recently proposed, but the so-called biased sample generation problem limits the performance of C-ZSKD. To overcome this limitation, this paper proposes a novel C-ZSKD algorithm that utilizes a label-free adversarial perturbation. The proposed adversarial perturbation derives a constraint of the squared norm of gradient style by using the convolution of probability distributions and the 2nd order Taylor series approximation. The constraint serves to increase the variance of the adversarial sample distribution, which makes the student model learn the decision boundary of the teacher model more accurately without labeled data. Through analysis of the distribution of adversarial samples on the embedded space, this paper also provides an insight into the characteristics of adversarial samples that are effective for adversarial learning-based C-ZSKD. INDEX TERMS zero-shot learning, knowledge distillation, adversarial learning I. INTRODUCTION
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.