基于FCN的图像感兴趣区域提取与细粒度分类的研究

Research on Extracting Regions of Interest and Fine-Grain Classification Based on FCN

近年来基于深度学习的细粒度分类是研究的热点,细粒度分类的主要方法是先找出分类对象再分类。找出分类对象的方法中主要分为两种:强监督与弱监督,强监督需要使用昂贵的人工标签,为了减少人工标注成本,提出一种基于FCN的图像感兴趣区域的分割与提取,并利用分割的图像进一步训练网络提高正确率。

In recent years, fine-grained classification based on deep learning is a hot topic. The main method of fine-grained classification is to first find the classification object and then classify it. There are two main methods for finding classification objects: strong supervision and weak supervision. Strong supervision requires the use of expensive manual labels. In order to reduce the cost of manual labeling, mainly proposes a segmentation and extraction of image regions based on improved FCN. The method and use the segmented image to further train the network to improve the correct rate.