Automatic defect description of railway track line image based on dense captioning

HIGHLIGHTS

• who: Dehua Wei et al. from the School of Traffic and Transportation, Beijing Jiaotong University, Beijing, China have published the research: Automatic Defect Description of Railway Track Line Image Based on Dense Captioning, in the Journal: Sensors 2022, 22, 6419. of /2022/
• what: The FL is modified on the basis of the standard Cross Entropy (CE) loss, which reduces the weight of easy-to-classify samples so that the model can focus more on difficult-to-classify samples during training. In this experiment, by comparing with DenseCap and DenseCap_RF, the validity of the method on . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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