细粒度分类：WS-DAN源码笔记——See Better Before Looking Closer: Weakly Supervised Data Augmentation Network

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

论文笔记：https://blog.csdn.net/qq_50001789/article/details/131352322?spm=1001.2014.3001.5501

WS-DAN网络整体结构

网络初始化阶段

def __init__(se