Image classification, classification with localization, and detection
Remember this is from Google Research, so this isn`t live.
The robots at Google are trying to understand images more and more. This article tries to explain how they do that. In essence there are three things the robots try to do:
- " The classification track measures an algorithm’s ability to assign correct labels to an image. "
- " The classification with localization track is designed to assess how well an algorithm models both the labels of an image and the location of the underlying objects. "
- " the detection challenge is similar, but uses much stricter evaluation criteria. As an additional difficulty, this challenge includes a lot of images with tiny objects which are hard to recognize. "?
Building a deeper understanding of images
