This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S 3 FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchorbased detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-theart detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.
Higher aridity and more extreme rainfall events in drylands are predicted due to climate change. Yet, it is unclear how changing precipitation regimes may affect nitrogen (N) cycling, especially in areas with extremely high aridity. Here we investigate soil N isotopic values (d 15 N) along a 3,200 km aridity gradient and reveal a hump-shaped relationship between soil d 15 N and aridity index (AI) with a threshold at AI ¼ 0.32. Variations of foliar d 15 N, the abundance of nitrification and denitrification genes, and metabolic quotient along the gradient provide further evidence for the existence of this threshold. Data support the hypothesis that the increase of gaseous N loss is higher than the increase of net plant N accumulation with increasing AI below AI ¼ 0.32, while the opposite is favoured above this threshold. Our results highlight the importance of N-cycling microbes in extremely dry areas and suggest different controlling factors of N-cycling on either side of the threshold.
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.