Deep learning for fine-grained image analysis: A survey

Deep learning for fine-grained image analysis: A survey

论文链接：https://arxiv.org/pdf/1907.03069.pdf
综述：http://www.weixiushen.com/tutorial/PRICAI18/PRICAI2018_FGIA.pdf

这篇文章主要介绍图像的细粒度分类任务，是一篇综述。

“Fine-grained image analysis(FGIA) focuses on dealing with the objects belonging to multiple sub-categories of the same meta-category and generally involves central tasks loke fine grained image recognition, fine-grained image retrivel, fine-grained image generation, etc.”

Benchmark datasets

Table I lists a number of image datasets commonly used by the fine-gained communitym and specilically indicate their meta-category, the amounts of fine-grained images, the number of fine-grained categories, extra different kinds of available supervisions, i.e., bounding boxes, part annotations, hierarchical labels, attribute labels and text visual descriptions, cf.

CUB200-2011 is one of the most popular fine-grained datasets