Activation fine-tuning of convolutional neural networks for improved input attribution based on class activation maps

HIGHLIGHTS

• who: Sungmin Han et al. from the School of Cybersecurity, Korea University, Seoul, Republic of Korea have published the Article: Activation Fine-Tuning of Convolutional Neural Networks for Improved Input Attribution Based on Class Activation Maps, in the Journal: (JOURNAL)
• what: The authors propose a new threshold fine-tuning (TFT) procedure to enhance the quality of input attribution based on model induction. In the experiments the authors show that the per-input optimal thresholding of attribution scores using TFT can significantly improve the quality of input attribution and CNNs fine-tuned with the AFT can . . .
  

   

  

  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.