Published in


[Paper Review] 5. YOLO ver 1

1. Contribution of YOLO

1.1 Why are previous networks slow?

1.2 Unifying regression and classification tasks into one.

Figure 1. Illustration of YOLO detection system, from [1]
Figure 2. Limitation of a sliding window, from [2]

2. YOLO Architecture

Figure 3. YOLO architecture with 24 convolutional layers followed by two FC layers to ensure the fixed number of predictions.

2.1 Regression

2.2 Classification

2.3 Test time

Figure 4. Bird’s eye view on YOLO, from [1]
mathematical definitions of probability term, from [4]

2.4 Loss function

2.5 NMS

Illustration of NMS, from [5]

3. Limitation

4. Reference



This publication is for organizing and posting what I’ve studied in scope of CS and Mathematics

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store