论文标题
Toan：面向目标的对准网络，用于细度图像分类，很少有标签样品
TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
论文作者
论文摘要
高等差异方差的挑战，而细粒度的视觉分类中的阶层间波动较低，几乎没有标记的样本，\ textit {i.e。高阶特征通常是为了发现FGF中的子类别之间的细微差异，但是它们在处理高层内差异方面的有效性较小。在本文中，我们提出了一个面向目标的对准网络（TOAN），以研究目标查询图像和支持类之间的细粒度关系。每个支持图像的特征都会被转换以匹配嵌入特征空间中的查询图像，从而在每个类别中明确降低了差异。此外，与现有的FGFS方法不同，以较不明确的考虑来设计高阶特征，而对判别零件的考虑较少，我们通过将组合概念表示形式集成到全球二阶池，从而生成歧视性细粒度。与最先进的模型相比，在四个细粒基准上进行了广泛的实验，以证明Toan的有效性。
The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS). High-order features are usually developed to uncover subtle differences between sub-categories in FGFS, but they are less effective in handling the high intra-class variance. In this paper, we propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category. Moreover, different from existing FGFS approaches devise the high-order features over the global image with less explicit consideration of discriminative parts, we generate discriminative fine-grained features by integrating compositional concept representations to global second-order pooling. Extensive experiments are conducted on four fine-grained benchmarks to demonstrate the effectiveness of TOAN compared with the state-of-the-art models.
