目录
1 Image Classification Introduction
Image Classification:给出1幅图片,在固定的标签(Label)中给出图片中对应物体的概率分布。这个任务定义看起来简单,实现起来却不容易。而且很多Computer Vision task最后都可化约为Image Classification问题。
Image Classification有如下几个主要难点:
-
视角变化(Viewpoint variation)
-
大小变化(Scale variation)
-
变形(Deformation)
-
遮盖(Occlusion)
-
光照变化(Illumination Conditions)
-
背景杂波(Background Clutter)
-
类内变化(Intra-class Variation)
1.1 Nearest Neighbor Classifier
1.1.1 k-Nearest Neighbor
1.2 Train/Val/Test Split
1.3 Pros/Cons of Nearest Neighbor
2 Summary
2.1
2.2 Applying kNN in practice
repeat until convergence: