细粒度分类:WS-DAN论文笔记——See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
综述
论文题目《See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification》
论文地址:https://arxiv.org/pdf/1901.09891v2.pdf源码地址(PyTorch版本):https://github.com/GuYuc/WS-DAN.PyTorch
针对领域:细粒度图像分类(FGVC)
关键词:数据增广、弱监督学习、注意力机制、双线性池化
源码笔记:https://blog.csdn.net/qq_50001789/article/details/131352887?spm=1001.2014.3001.5501
主要思想
本文主要是提出了一种基于注意力图