ABSTRACT
As the mainstream and trend of urban development in China, deeply exploring the spatiotemporal patterns and influencing mechanisms of ecosystem service value in the Yangtze River Delta urban agglomeration is of great significance for achieving sustainable development goals in urban agglomerations. This paper uses the normalized difference vegetation index and net primary productivity as dynamic adjustment factors to measure the ecosystem service value of the Yangtze River Delta urban agglomeration and analyze its spatiotemporal evolution characteristics. Furthermore, a panel quantile regression model is constructed to explore the response differences of ecosystem service value at different levels to various influencing factors. The results show that: (1) From 2006 to 2020, the ecosystem service value of the Yangtze River Delta urban agglomeration decreased by 37.086 billion yuan, with high-value areas mainly concentrated in the southern part of the urban agglomeration. (2) The value structure of various land type ecosystems and primary ecosystem sub-services in the Yangtze River Delta urban agglomeration is stable. (3) The number of grid units with reduced ecosystem service value is continuously increasing, mainly distributed in the eastern coastal areas. (4) The degree of interference of various types of land on ecosystem service value varies, and the response of ecosystem service value at different levels to the same influencing factor also shows heterogeneity. In summary, exploring the spatiotemporal patterns of ecosystem service value in the Yangtze River Delta urban agglomeration and analyzing its influencing mechanisms is conducive to adjusting the intensity of human utilization and protection methods of ecosystems, which is of great significance for enhancing the value of ecosystem products in urban agglomerations.
ABSTRACT
Vitiligo lesion segmentation is crucial for the assessment and treatment of vitiligo. There are two significant challenges in this problem, namely, the availability of dense segmentation annotations and the collection of large amounts of vitiligo images, which are also major challenges in medical image analysis (MIA). However, most existing methods often heavily rely on the availability of large-scale labeled datasets and high-quality annotations. Consequently, the performance of these models may not be easily reproducible or transferable to those domains with limited data availability. As a result, there is a need to develop alternative approaches that can leverage unlabeled datasets for segmentation with a small-scale training set. In this paper, we propose a data augmentation strategy based on image editing, which can synthesize a large number of samples using a small number of annotated data. The synthesized examples are of high visual quality and enforce the segmentation performance without any cost. Besides, we also adapt the Mean-Teacher framework for reliable predictions mining from unlabeled samples to alleviate the demands of densely annotated segmentations. We obtain pseudo-labels for unlabeled samples by utilizing highly confident pixels. On the other hand, we proposed a new Bimodal Vitiligo Lesions Segmentation (BVLS) dataset containing fine-grain segmentation masks and bimodal images usually used for vitiligo diagnosis to mitigate the lack of a vitiligo segmentation dataset. Extensive experiments conducted on the BLVS dataset demonstrate that our approach can achieve significant improvements (+17.27%) compared with previous data augmentation methods on the UNet backbone. Furthermore, the semi-supervised framework can reach an IoU of 49.71% with only 10% annotated images. Our code and dataset are availabel at https://github.com/JcWang20/BLVS.