MATLAB Answers

0

More Training data for R-CNN detector causes overfitting?

Abdussalam Elhanashi さんによって質問されました 2019 年 10 月 10 日
最新アクティビティ Abdussalam Elhanashi さんによって 回答されました 2019 年 10 月 16 日
Hi Guys
I am experiencing that when i am using a R-CNN detector for object detection , when i increase the training data , i have bad classification and overfitting
Best,

  0 件のコメント

サインイン to comment.

2 件の回答

Answer by Prabhan Purwar on 16 Oct 2019
Edited by Prabhan Purwar on 16 Oct 2019
 Accepted Answer

Hi,
Overfitting happens when the model fits too well to the training set. It then becomes difficult for the model to generalize to new examples that were not in the training set. For example, model recognizes specific images in the training set instead of general patterns. Training accuracy will be higher than the accuracy on the validation/test set.
Steps for reducing overfitting:
  • Add more variant Dataset
  • Make use of balance Dataset
  • Use data augmentation
  • Use architectures that generalize well
  • Add regularization (mostly dropout, L1/L2 regularization are also possible)
Refer to the following link for further information:

  0 件のコメント

サインイン to comment.


Answer by Abdussalam Elhanashi on 16 Oct 2019

Thanks Prabhan

  0 件のコメント

サインイン to comment.



Translated by