Fine-grained image classification can be considered as a discriminative learning process where images of different subclasses are separated from each other while the same subclass images are clustered. Most existing methods perform synchronous discriminative learning in their approaches. Although achieving promising results in fine-grained visual classification (FGVC) in natural images, these methods may fail in fine-grained ship classification (FGSC) problem in remote sensing (RS) images due to the highly “imbalanced fineness” and “imbalanced appearances” of ships among subclasses. To tackle the issue, we propose an asynchronous contrastive learning-based method for effective FGSC. The proposed method, which we refer to as “Push-and-Pull Network (P2Net)”, includes a “push-out stage” and a “pull-in stage”, where the first stage forces all the instances to be decorrelated and then the second one groups them into each subclass. A dual-branch network is designed to separate/decorrelate the images with each other, while an integration module is designed to aggregate the decorrelated images into their corresponding subclass together with a proxy-based module designed for acceleration. In this way, the correlation between subclasses can be decoupled, which in turn makes the final classification much easier. Our method can be trained end-to-end and requires no additional annotations other than category information. Extensive experiments are conducted on two large-scale FGSC datasets (FGSC-23 and FGSCR-42). Our method outperforms other state-of-the-art approaches. Ablation experiments also suggest the effectiveness of our design. Our code is available at https://github.com/WindVChen/Push-and-Pull-Network.

中文翻译：

---

遥感图像中细粒度船舶分类的对比学习


细粒度图像分类可以被认为是一种判别学习过程，其中不同子类的图像彼此分离，而相同子类的图像被聚类。大多数现有方法在其方法中执行同步判别学习。尽管在自然图像的细粒度视觉分类（FGVC）方面取得了有希望的结果，但由于高度“不平衡的精细度”和“不平衡的外观”，这些方法可能在遥感（RS）图像的细粒度船舶分类（FGSC）问题上失败。子类中的船舶”。为了解决这个问题，我们提出了一种基于异步对比学习的有效 FGSC 方法。所提出的方法，我们称为“推拉网络（P2Net）”，包括“推出阶段”和“拉入阶段”，其中第一阶段强制所有实例去相关并然后第二个将它们分为每个子类。双分支网络旨在将图像彼此分离/去相关，而集成模块则旨在将去相关图像与为加速而设计的基于代理的模块一起聚合到相应的子类中。这样就可以解耦子类之间的相关性，进而使得最终的分类变得更加容易。我们的方法可以进行端到端训练，并且除了类别信息之外不需要额外的注释。在两个大型 FGSC 数据集（FGSC-23 和 FGSCR-42）上进行了广泛的实验。我们的方法优于其他最先进的方法。消融实验也表明了我们设计的有效性。我们的代码可从 https://github.com/WindVChen/Push-and-Pull-Network 获取。