7步走写摘要：Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning

---

摘要书写解读 
第一步: 交代背景：多视角数据的普遍性和重要性
第二步: 概括当前方法 。
第三步: 一般介绍现有方法的不足 
第四步: 提出当前的方法
第五步: 在提出论文的方法之后，需要进行对自己提出的方法的大致的介绍 
第六步: 第五步进行了理论上的阐述。这一步呢，通常是对提出的算法怎么样实现优化的一句话或者两句话。不能太长，因为有字数限制。
第七步: 简要介绍一下实验，这个比较的套路。
以上就是大致的一个流程，我也正在学习，若有不足请各位耐心支出。非常感谢。
一般的摘要都会遵循这七个步骤，不同的步骤之间可能会融合到一块进行书写，在我们自己进行书写摘要的时候，可以参照这个步骤。如果自己在某个步骤实在想不出来，就暂时空下来。​
 

---

原摘要：
"Galaxy morphology reflects structural properties which contribute to understand the formation and evolution of galaxies. Deep convolutional networks have proven to be very successful in learning hidden features that allow for unprecedented performance on galaxy morphological classification. Such networks mostly follow the supervised learning paradigm which requires sufficient labelled data for training. However, it is an expensive and complicated process of labeling for million galaxies, particularly for the forthcoming survey projects. In this paper, we present an approach based on contrastive learning with aim for learning galaxy morphological visual representation using only unlabeled data. Considering the properties of low semantic information and contour dominated of galaxy image, the feature extraction layer of the proposed method incorporates vision transformers and convolutional network to provide rich semantic representation via the fusion of the multi-hierarchy features. We train and test our method on 3 classifications of datasets from Galaxy Zoo 2 and SDSS-DR17, and 4 classifications from Galaxy Zoo DECaLS. The testing accuracy achieves 94.7%, 96.5% and 89.9% respectively. The experiment of cross validation demonstrates our model possesses transfer and generalization ability when applied to the new datasets. The code that reveals our proposed method and pretrained models are publicly available and can be easily adapted to new surveys."

七步分如下:
交代背景: 
"Galaxy morphology reflects structural properties which contribute to understand the formation and evolution of galaxies."
翻译：银河形态反映了构成银河形成和演化理解的结构性质。

概括当前方法:
"Deep convolutional networks have proven to be very successful in learning hidden features that allow for unprecedented performance on galaxy morphological classification. Such networks mostly follow the supervised learning paradigm which requires sufficient labelled data for training."
翻译：深度卷积网络已经在学习隐藏特征方面取得了巨大成功，这些特征允许在银河形态分类上取得前所未有的性能。这些网络大多遵循监督学习范式，这需要足够的标记数据进行训练。

现有方法的不足 : 
"However, it is an expensive and complicated process of labeling for million galaxies, particularly for the forthcoming survey projects."
翻译：然而，为数百万个星系进行标记是一个昂贵和复杂的过程，特别是对于即将进行的调查项目。

提出当前的方法: 
"In this paper, we present an approach based on contrastive learning with aim for learning galaxy morphological visual representation using only unlabeled data."
翻译：在这篇论文中，我们提出了一种基于对比学习的方法，目标是只使用未标记的数据学习银河形态的视觉表示。

简要介绍方法: 
"Considering the properties of low semantic information and contour dominated of galaxy image, the feature extraction layer of the proposed method incorporates vision transformers and convolutional network to provide rich semantic representation via the fusion of the multi-hierarchy features."
翻译：考虑到银河图像的低语义信息和轮廓主导的属性，我们提出的方法的特征提取层整合了视觉变换器和卷积网络，通过融合多层次的特征来提供丰富的语义表示。

如何实现或优化: 
(摘要中并未详细介绍优化方法)

实验介绍: 
"We train and test our method on 3 classifications of datasets from Galaxy Zoo 2 and SDSS-DR17, and 4 classifications from Galaxy Zoo DECaLS. The testing accuracy achieves 94.7%, 96.5% and 89.9% respectively. The experiment of cross validation demonstrates our model possesses transfer and generalization ability when applied to the new datasets."
翻译：我们在Galaxy Zoo 2和SDSS-DR17的三个分类数据集，以及Galaxy Zoo DECaLS的四个分类数据集上训练和测试了我们的方法。测试准确率分别达到94.7%、96.5%和89.9%。交叉验证的实验表明，我们的模型在应用到新的数据集时具有迁移和泛化的能力。