论文标题
使用自评估分类器的细粒度视觉分类
Fine-Grained Visual Classification using Self Assessment Classifier
论文作者
论文摘要
提取区分特征在细粒度的视觉分类任务中起着至关重要的作用。大多数现有方法都集中在开发关注或增强机制以实现这一目标。但是，无法充分研究TOP-K预测类中的歧义。在本文中，我们引入了一个自评估分类器，该分类器同时利用图像和TOP-K预测类的表示来重新评估分类结果。我们的方法的启发是通过使用粗粒和细粒分类器进行的持续学习的启发，以增加主链特征的歧视，并在图像上产生信息图的注意力图。实际上，我们的方法是辅助分支，可以轻松地集成到不同的体系结构中。我们表明，通过有效解决Top-K预测类的歧义，我们的方法可以在Cub200-2011，Stanford Dog和FGVC飞机数据集上实现新的最新结果。此外，我们的方法还始终通过统一设置提高了不同现有细粒分类器的准确性。
Extracting discriminative features plays a crucial role in the fine-grained visual classification task. Most of the existing methods focus on developing attention or augmentation mechanisms to achieve this goal. However, addressing the ambiguity in the top-k prediction classes is not fully investigated. In this paper, we introduce a Self Assessment Classifier, which simultaneously leverages the representation of the image and top-k prediction classes to reassess the classification results. Our method is inspired by continual learning with coarse-grained and fine-grained classifiers to increase the discrimination of features in the backbone and produce attention maps of informative areas on the image. In practice, our method works as an auxiliary branch and can be easily integrated into different architectures. We show that by effectively addressing the ambiguity in the top-k prediction classes, our method achieves new state-of-the-art results on CUB200-2011, Stanford Dog, and FGVC Aircraft datasets. Furthermore, our method also consistently improves the accuracy of different existing fine-grained classifiers with a unified setup.
