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,...
Үндсэн зохиолчид: | Lenc, K, Vedaldi, A |
---|---|
Формат: | Conference item |
Хэвлэсэн: |
IEEE
2015
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Understanding Image Representations by Measuring Their Equivariance and Equivalence
-н: Lenc, K, зэрэг
Хэвлэсэн: (2018) -
Unsupervised learning of object frames by dense equivariant image labelling
-н: Thewlis, J, зэрэг
Хэвлэсэн: (2017) -
Equivariant quantum cohomology and the geometric Satake equivalence
-н: Viscardi, Michael
Хэвлэсэн: (2016) -
Learning equivariant structured output SVM regressors
-н: Vedaldi, A, зэрэг
Хэвлэсэн: (2012) -
Induction equivalence for equivariant D-modules on rigid analytic spaces
-н: Ardakov, K
Хэвлэсэн: (2023)