Transform-Invariant Convolutional Neural Networks for Image Classification and Search

28 Nov 2019Xu ShenXinmei TianAnfeng HeShaoyan SunDacheng Tao

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper