对象检测/分割是否会提高分类准确性?

huangapple go评论73阅读模式
英文:

Will object detection/segmentation improve classification accuracy?

问题

如果我想进行分类任务,如果有边界框或像素级信息,分类得分会提高吗?

或者在分类方面,分类网络会胜过目标检测/分割网络吗?

英文:

if i want to do a classification task will the classification score improve if i have bounding box or pixel wise information?

or will a classification network outperform an object detection/Segmentation network in classification?

答案1

得分: 1

好问题。

答案如下:这取决于情况。

例如,假设您在10种狗上训练了YoloV3。然后,YoloV3的输出是一个带有相应类别的边界框。

然而,拥有两个神经网络,一个用于检测狗(目标检测),另一个用于分类(狗的种类)可能会得到更好的分数。

同样适用于语义/实例分割网络。

尽管没有固定的方法来确定哪种方法效果更好,但我个人倾向于认为第二步骤的流程可能会产生稍微更好的结果(这些观察是基于我的经验,因为我曾经在某个时候实施过这两种方法)。

英文:

Good question.

The answer is the following: it depends on the case.

For instance, say you train YoloV3 on 10 types of dogs. Then the output of YoloV3 is a bounding box with the corresponding class.

Having two neural networks however, one for detecting dogs(object detection) and the other one for classification(what type of dog) may perhaps yield a better score.

The same goes for semantic/instance segmentation network.

Although there is no recipe for saying which approach works better, I would personally incline to believe that the second step pipeline would yield slightly better results(there observations are based on my experience, since I have implemented both approaches at a point).

huangapple
  • 本文由 发表于 2020年1月7日 02:29:21
  • 转载请务必保留本文链接:https://go.coder-hub.com/59617147.html
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定