Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works are mainly part-driven (either explicitly or implicitly), with the assumption that fine-grained information naturally rests within the parts. In this paper, we take a different stance, and show that part operations are not strictly necessary – the key lies with encouraging the network to learn at different granularities and progressively fusing multi-granularity features together. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a consistent block convolution that encourages the network to learn the category-consistent features at specific granularities. We evaluate on several standard FGVC benchmark datasets, and demonstrate the proposed method consistently outperforms existing alternatives or delivers competitive results. Codes are available at https://github.com/PRIS-CV/PMG-V2.

中文翻译：

---

细粒度视觉分类的类别一致多粒度特征的渐进学习


由于类内对象固有的微妙变化，细粒度视觉分类（FGVC）比传统分类任务更具挑战性。最近的工作主要是部分驱动的（显式或隐式），假设细粒度信息自然存在于部分中。在本文中，我们采取了不同的立场，并表明部分操作并不是绝对必要的——关键在于鼓励网络在不同粒度上学习并逐步将多粒度特征融合在一起。特别是，我们提出：（i）一种有效融合不同粒度特征的渐进式训练策略，以及（ii）一种一致的块卷积，鼓励网络学习特定粒度的类别一致特征。我们对几个标准 FGVC 基准数据集进行评估，并证明所提出的方法始终优于现有替代方法或提供有竞争力的结果。代码可在 https://github.com/PRIS-CV/PMG-V2 获取。