现有的细粒度分类模型不仅利用图像的类别标签, 还使用大量人工标注的额外信息。为解决该问题, 本文提出一种深度迁移学习模型, 将大规模有标签细粒度数据集上学习到的图像特征有效地迁移至微型细粒度数据集中。首先, 通过衔接域定量计算域间任务的关联度。然后, 根据关联度选择适合目标域的迁移特征。最后, 使用细粒度数据集视图类标签进行辅助学习, 通过联合学习所有属性来获取更多的特征表示。实验表明, 本文方法不仅可以获得较高精度, 而且能够有效减少模型训练时间, 同时也验证了进行域间特征迁移可以加速网络学习与优化这一结论。

Existing fine-grained categorization models require extra manual annotation in addition to the image cat-egory labels. To solve this problem, we propose a novel deep transfer learning model, which transfers the learned representations from large-scale labelled fine-grained datasets to micro fine-grained datasets. Firstly, we introduce a cohesion domain to measure the degree of correlation between source domain and target domain. Secondly, select the transferrable feature that are suitable for the target domain based on the correlation. Finally, we make most of perspective-class labels for auxiliary learning, and learn all the attributes through joint learning to extract more fea-ture representations. The experiments show that our model not only achieves high categorization accuracy but also economizes training time effectively, it also verifies the conclusion that the inter-domain feature transition can acce-lerate learning and optimization.