Robust training of social media image classification models

HIGHLIGHTS

• who: Firoj Alam et al. from the (UNIVERSITY) have published the research: Robust Training of Social Media Image Classification Models, in the Journal: (JOURNAL)
• what: For a clear understanding, the authors provide an example pipeline in Fig 1(a) that demonstrates how different disaster-related image classification models can be used in real time for information categorization. As the experiment shows, this is challenging due to the incomplete labels for different tasks (see more details in Section IV-F). The authors investigate various data augmentation techniques and show that model generalization improves with data augmentation . . .
  

   

  

  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.