Understanding image representations by measuring their equivariance and equivalence

DOI10.1007/s11263-018-1098-yzbMath1458.68236DBLPjournals/ijcv/LencV19arXiv1411.5908OpenAlexW3005221849WikidataQ64886006 ScholiaQ64886006MaRDI QIDQ2193805

Karel Lenc, Andrea Vedaldi

Publication date: 20 August 2020

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1411.5908

zbMATH Keywords

image representationsconvolutional neural networksequivalent representationsgeometric equivariance

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Machine vision and scene understanding (68T45)

Related Items (5)

Unnamed Item ⋮ Unnamed Item ⋮ Multi-object tracking using deformable convolution networks with tracklets updating ⋮ An efficient Lorentz equivariant graph neural network for jet tagging ⋮ Towards high-accuracy deep learning inference of compressible flows over aerofoils

Uses Software

• Vlfeat
• MatConvNet
• SIFT
• DeCAF
• OverFeat
• CIFAR
• ImageNet
• GitHub
• SpaSM
• ScatNet
• iHOG
• AlexNet
• Faster R-CNN
• HOGgles

Cites Work

• Unsupervised learning of invariant representations
• Representing and recognizing the visual appearance of materials using three-dimensional textons

This page was built for publication: Understanding image representations by measuring their equivariance and equivalence