Learning feature representation from discriminative local regions plays a key role in fine-grained visual classification. Employing attention mechanisms to extract part features has become a trend. However, there are two major limitations in these methods: First, they often focus on the most salient part while neglecting other inconspicuous but distinguishable parts. Second, they treat different part features in isolation while neglecting their relationships. To handle these limitations, we propose to locate multiple different distinguishable parts and explore their relationships in an explicit way. In this pursuit, we introduce two lightweight modules that can be easily plugged into existing convolutional neural networks. On one hand, we introduce a feature boosting and suppression module that boosts the most salient part of feature maps to obtain a part-specific representation and suppresses it to force the following network to mine other potential parts. On the other hand, we introduce a feature diversification module that learns semantically complementary information from the correlated part-specific representations. Our method does not need bounding boxes/part annotations and can be trained end-to-end. Extensive experimental results show that our method achieves state-of-the-art performances on several benchmark fine-grained datasets. Source code is available at https://github.com/chaomaer/FBSD.
翻译:在细微的视觉分类中,来自歧视性地方地区的学习特征代表具有关键作用。使用关注机制来提取部分特征已成为一种趋势。然而,这些方法有两大局限性:首先,它们往往侧重于最突出的部分,而忽略其他不明显但可辨别的部分。第二,它们孤立地对待不同部分特征,而忽视它们的关系。为了处理这些局限性,我们建议用明确的方式找到多个不同可辨别的部分,并探索它们之间的关系。在这项工作中,我们引入了两个轻量的模块,这些模块可以很容易地插入现有的超动神经网络。一方面,我们引入了一个促进和抑制功能模块,以提升特征地图中最突出的部分,从而获得一个特定部分的代表性,并抑制它迫使以下网络去挖掘其他潜在部分。另一方面,我们引入了一个特征多样化模块,从相关部分的表达中学习精度互补信息。我们的方法不需要装箱/部分说明,也可以经过最终培训。广泛的实验结果显示,我们的方法达到了州-州/州/州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州-州