Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the process of classification. However, building large scale datasets with such annotations is a mammoth task. Moreover, this extensive annotation is time-consuming and often requires expertise, which is a huge bottleneck in building large datasets. On the other hand, self-supervised learning (SSL) exploits the freely available data to generate supervisory signals which act as labels. The features learnt by performing some pretext tasks on huge unlabelled data proves to be very helpful for multiple downstream tasks. Our idea is to leverage self-supervision such that the model learns useful representations of fine-grained image classes. We experimented with 3 kinds of models: Jigsaw solving as pretext task, adversarial learning (SRGAN) and contrastive learning based (SimCLR) model. The learned features are used for downstream tasks such as fine-grained image classification. Our code is available at http://github.com/rush2406/Self-Supervised-Learning-for-Fine-grained-Image-Classification

中文翻译：

---

细粒度图像分类的自监督学习

细粒度图像分类涉及识别具有非常微妙的区分特征的类别的不同子类别。细粒度数据集通常提供边界框注释和类标签，以帮助分类过程。然而，构建具有此类注释的大规模数据集是一项艰巨的任务。此外，这种广泛的注释非常耗时，并且通常需要专业知识，这是构建大型数据集的巨大瓶颈。另一方面，自监督学习 (SSL) 利用免费可用的数据来生成充当标签的监督信号。通过在巨大的未标记数据上执行一些借口任务而学习到的特征被证明对多个下游任务非常有帮助。我们的想法是利用自我监督，使模型学习细粒度图像类的有用表示。我们试验了 3 种模型：作为借口任务的拼图求解、对抗性学习 (SRGAN) 和基于对比学习的 (SimCLR) 模型。学习到的特征用于下游任务，例如细粒度图像分类。我们的代码可在 http://github.com/rush2406/Self-Supervised-Learning-for-Fine-grained-Image-Classification 获得