论文标题

通过相似性转移而弱射的细粒度分类

Weak-shot Fine-grained Classification via Similarity Transfer

论文作者

Chen, Junjie, Niu, Li, Liu, Liu, Zhang, Liqing

论文摘要

由于不同的下属类别之间的微妙区别,认识到细粒类别仍然是一项艰巨的任务,这导致需要大量的注释样本。为了减轻渴望数据的问题,我们考虑了从Web数据中学习新颖类别的问题,并支持一组干净的基本类别,这被称为弱者学习。在这种情况下,我们提出了一种称为Simtrans的方法,将成对语义相似性从基本类别转移到新类别。具体来说,我们首先在干净的数据上训练一个相似性网,然后使用两种简单但有效的策略利用转移的相似性与Denoise Web培训数据。此外,我们将对抗性损失应用于相似性网络,以增强相似性的转移性。全面的实验证明了我们的弱射击设置和Simtrans方法的有效性。数据集和代码可从https://github.com/bcmi/simtrans-weak-shot-classification获得。

Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we consider the problem of learning novel categories from web data with the support of a clean set of base categories, which is referred to as weak-shot learning. In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories. Specifically, we firstly train a similarity net on clean data, and then leverage the transferred similarity to denoise web training data using two simple yet effective strategies. In addition, we apply adversarial loss on similarity net to enhance the transferability of similarity. Comprehensive experiments demonstrate the effectiveness of our weak-shot setting and our SimTrans method. Datasets and codes are available at https://github.com/bcmi/SimTrans-Weak-Shot-Classification.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源