Symbiotic Segmentation and Part Localization for Fine-Grained Categorization 讲了利用图像分割和局部定位的方法分离出图像前景，来提高分类结果。
Deep Domain Adaptation for Describing People Based on Fine-Grained Clothing Attributes 没细看，讲的衣服的分类的。
Nonparametric Part Transfer for Fine-grained Recognition 用无参数局部转移的方法来提高识别率。
Hypercolumns for Object Segmentation and Fine-grained Localization 利用较下层的cnn网络的信息来提供空间信息，来提高分类结果。
Fine-Grained Recognition without Part Annotations 讲他这个文章不用局部注释和关键点，效果很好。
Deep LAC: Deep Localization, Alignment and Classification for Fine-grained Recognition 构造一个检测、对其、分类与一体的神经网络，来进行细粒度图像分类
原文：http://www.cnblogs.com/hoey-ge/p/5796799.html