论文标题
通过进行拼图斑块的进行性多晶训练的细颗粒视觉分类
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
论文作者
论文摘要
由于固有细微的类别内对象变化，细粒度的视觉分类（FGVC）比传统的分类任务更具挑战性。最近的作品主要通过关注如何找到最歧视性的部分，更多互补部分以及各个粒度的部分来解决这个问题。但是，粒子是最歧视性以及如何融合信息跨多粒性的努力。在这项工作中，我们提出了一个新颖的框架，以解决这些问题，以解决这些问题。我们特别提出：（i）有效地融合来自不同粒度的特征的渐进式培训策略，以及（ii）一个随机的拼图斑块生成器，鼓励网络以特定的粒度学习特征。我们在几个标准的FGVC基准数据集上获得了最先进的性能，该数据集始终超过现有方法或提供竞争结果。该代码将在https://github.com/pris-cv/pmg-progressive-multi-granaularity-training上找到。
Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts, more complementary parts, and parts of various granularities. However, less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity. In this work, we propose a novel framework for fine-grained visual classification to tackle these problems. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a random jigsaw patch generator that encourages the network to learn features at specific granularities. We obtain state-of-the-art performances on several standard FGVC benchmark datasets, where the proposed method consistently outperforms existing methods or delivers competitive results. The code will be available at https://github.com/PRIS-CV/PMG-Progressive-Multi-Granularity-Training.
