关注微信公众号：人工智能前沿讲习班，获取视频PPT及文章学习资料~~~
PPT及文章链接：https://mp.weixin.qq.com/s/j_nU7QB_nArHQj36PL3h9w
在图像分类问题，尤其是细分类问题中，是否由于类间差异不显著，一阶信息有一些不适用了呢？那么二阶信息是否可以带给分类器更有区分性、更有价值的信息呢？本讲内容主要介绍二阶信息运用于图像分类的方法。
讲者介绍
李宏扬：北京大学信息科学技术学院在读硕士，本科毕业于北京科技大学，2018年MS COCO Panoptic Segmentation Contest PKU_360团队（第三名）成员之一。目前主要研究兴趣点在于图像中的object detection。希望可以结识更多的人，彼此分享，共同交流。
报告题目：二阶信息是否可以在图像分类中发挥作用？
报告摘要：By stacking deeper layers of convolutions and nonlinearity, convolutional networks (ConvNets) effectively learn from low-level to high-level features and discriminative representations. Since the end goal of large-scale recognition is to delineate the complex boundaries of thousands of classes in a large-dimensional space, adequate exploration of feature distributions is important for realizing full potentials of ConvNets. However, state-of-the-art works concentrate only on deeper or wider architecture design, while rarely exploring feature statistics higher than first-order. Actually the second order statistics information contains much information that first order information doesn’t have. Therefore the second order information may be helpful for large-scale visual recognition especially for fine-grained classification.
参考资料
https://www.bilibili.com/video/BV1qt411D7Wu/
https://bbs.sffai.com/d/4