Active reinforcement learning for the semantic segmentation of images captured by mobile sensors

HIGHLIGHTS

• who: M. Jodeiri Rad and collaborators from the XXIV ISPRS Congress (, edition), June, Nice, France have published the article: ACTIVE REINFORCEMENT LEARNING FOR THE SEMANTIC SEGMENTATION OF IMAGES CAPTURED BY MOBILE SENSORS, in the Journal: (JOURNAL)
• what: The authors experiment with implementing a reinforced active learning method with a weighted performance metric to reduce human labour while achieving competitive results. METHODOLOGY To increase the attention even further on the underrepresented classes, the authors propose to use a weighted average of IoU score for computing the reward of the DQN network. By using weighted average IoU . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.