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: | Lenc, K, Vedaldi, A |
---|---|
Định dạng: | Conference item |
Được phát hành: |
IEEE
2015
|
Những quyển sách tương tự
-
Understanding Image Representations by Measuring Their Equivariance and Equivalence
Bằng: Lenc, K, et al.
Được phát hành: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
Bằng: Thewlis, J, et al.
Được phát hành: (2017) -
Equivariant quantum cohomology and the geometric Satake equivalence
Bằng: Viscardi, Michael
Được phát hành: (2016) -
Learning equivariant structured output SVM regressors
Bằng: Vedaldi, A, et al.
Được phát hành: (2012) -
Induction equivalence for equivariant D-modules on rigid analytic spaces
Bằng: Ardakov, K
Được phát hành: (2023)