Understanding image representations by measuring their equivariance and equivalence
Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three key mathematical properties of representations: equivariance,...
| Những tác giả chính: | , |
|---|---|
| Định dạng: | Conference item |
| Được phát hành: |
IEEE
2015
|
Search Result 1
Understanding Image Representations by Measuring Their Equivariance and Equivalence
Được phát hành 2018
Journal article