一、基于流形的视觉目标计数

1. 提出了一种基于流形的视觉目标计数方法；
2. 通过正则化和非线性映射来考虑非负性和稀疏表示，来优化局部几何的特征；
3. 用局部模式学习和分层搜索被用来进一步提高所提出的方法及其变体的计算效率。

Abstract

1. We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task.
2. This problem could be viewed as a kind of weakly supervised segmentation task, and naturally fits the Multiple Instance Learning (MIL) framework. We propose a Convolutional Neural Network-based model, which is constrained during training to put more weight on pixels which are important for classifying the image.
3. At the test time, the model has learned to discriminate the right pixels well enough, such that it performs very well on an existing segmentation benchmark, by adding only few smoothing priors.

在做数据分析大作业的时候偶然发现了pyecharts，发现这是一个非常好用的画图工具，这篇博客记录我在数据分析大作业中使用到的pyecharts绘图方法。

1.BatchNormalization和Dropout虽然可以在大约50个epoch内实现loss的收敛，同时减少过拟合，但是会在后续的epoch中带来loss的突然震荡。若网络层数不多，不建议每一个卷积层后都加一个BatchNormalization层。

这是我使用Hexo和Github搭建的第一篇博客，留以纪念