Is there any publication or research article from Zimmerman et al. or any other scholar in which it is mentioned that using small kernal size i.e. 3x3 achieve better results?


You are probably referring to this article:

Simonyan K. and Zissermann, A. (2014): Very Deep Convolutional Networks for Large-Scale Image Recognition.

Arguably, their main message is not that small kernels are better, rather demonstrating that the depth of the network is much more important than the size of the kernels. Also, they accredit the idea of using small kernels to Cireşan, D. C. et al. (2011): Flexible, High Performance Convolutional Neural Networks for Image Classification, however, this work performs no thorough comparison of effects of using small kernel size.

  • $\begingroup$ I want to cite the Simonyan's paper but the citation is available in arXiv preprint arXiv. Isn't should have with journal or conference name? $\endgroup$ – Addee Jul 9 '18 at 6:19

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.