Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for realworld applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance.
The enantioselective dearomative [3 + 2] cycloaddition reaction of benzazoles with aminocyclopropanes has been successfully developed. In the presence of a copper complex, derived from Cu(OTf) 2 and bisoxazoline, a series of hydropyrrolo-benzazole derivatives containing quaternary stereogenic centers were obtained in high yields with excellent enantioselectivity. This method could also provide 2-amino cyclopropanes with high enantiomeric purity by an efficient kinetic resolution. In addition, products could be transformed to pyrrolobenzothiazines and 1,5-benzothiazepines.
A highly enantioselective dearomative [3+2] cycloaddition of benzothiazole has been successfully developed. A wide range of benzothiazoles and cyclopropane-1,1-dicarboxylates are suitable substrates for this reaction. The desired hydropyrrolo[2,1-b]thiazole compounds were obtained in excellent enantioselectivity and yields (up to 97 % ee and 97 % yield). With the same catalytic system, a highly efficient kinetic resolution of 2-substituted cyclopropane-1,1-dicarboxylates was also realized.
Gracilaria lemaneiformis, a commercial red macroalga with multiple uses, was cultivated under different combinations of temperatures (10, 20, and 30°C) and nutrients (seawater and four different levels of enrichment) to determine its photo‐physiological response pattern. O2 evolution‐based photosynthesis–irradiance (P–I) curves and chlorophyll fluorescence‐based polyphasic chlorophyll fluorescence transients (OJIP) curves increased with increasing temperature up to 20–30°C, but were nutrition insensitive. The same responsive patterns were followed by their corresponding derived specific photosynthetic parameters. The high photosynthetic tolerance of G. lemaneiformis to nutrient‐loaded stress at a wide range of temperatures, makes it a potential candidate for bioremediating eutrophic mariculture zones.
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.