Automatic facial age estimation can be used in a wide range of real-world applications. However, this process is challenging due to the randomness and slowness of the aging process. Accordingly, in this paper, we propose a novel method aimed at overcoming the challenges associated with facial age estimation. First, we propose a novel age encoding method, referred to as 'Soft-ranking', which encodes two important properties of facial age, i.e., the ordinal property and the correlation between adjacent ages. Therefore, Soft-ranking provides a richer supervision signal for training deep models. Moreover, we carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods. Moreover, we achieve state-of-the-art performance on four most popular age databases, i.e., Morph II, AgeDB, CLAP2015, and CLAP2016.
Automatic facial age estimation can be used in a wide range of real-world applications. However, this process is challenging due to the randomness and slowness of the aging process. Accordingly, in this paper, we propose a comprehensive framework aimed at overcoming the challenges associated with facial age estimation. First, we propose a novel age encoding method, referred to as Soft-ranking, which encodes two important properties of facial age, i.e., the ordinal property and the correlation between adjacent ages. Therefore, Soft-ranking provides a richer supervision signal for training deep models. Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods. Finally, since existing face databases for age estimation are generally small, deep models tend to suffer from an overfitting problem. To address this issue, we propose a novel regularization strategy to encourage deep models to learn more robust features from facial parts for age estimation purposes. Extensive experiments indicate that the proposed techniques improve the age estimation performance; moreover, we achieve state-of-the-art performance on the three most popular age databases, i.e., Morph II, CLAP2015, and CLAP2016.
Large-scale remote sensing images, including both satellite and aerial photographs, are widely used to render terrain scenes in real-time geographic visualization systems. Such systems often require large memories in order to store fine terrain details and fast network speeds to transfer image data, if they are built as web applications. In this paper, we propose a progressive texture compression framework to reduce the memory and bandwidth cost by compressing repeated content within and among large-scale remote sensing images. Different from existing image factorization methods, our algorithm incrementally find similar regions in new images so that large-scale images can be more efficiently compressed over time. We further propose a descriptor, the Gray Split Rotate (GSR) descriptor, to accelerate the similarity search. The reconstruction quality is finally improved by compressing residual error maps using customized S3TC-like compression. Our experiment shows that even with the error maps, our system still has higher compression rate and higher compression quality than using S3TC alone, which is a typical compression solution in most existing visualization systems.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.