Meauring Invariances in Deep Networks

N/A

Measuring Invariances in Deep Networks Ian J. Goodfellow, Quoc V. Le, Andrew M. Saxe, Honglak Lee, Andrew Y. Ng Computer Science Department Stanford University Stanford, CA 94305 {ia3n,quocle,asaxe,hllee,ang}@cs.stanford.edu Abstract For many pattern recognition tasks, the ideal input feature would be invariant to multiple confounding properties (such as illumination and viewing angle, in com-…

saved by

• Alexander Davies

related reading

• [1810.13128] The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariancearxiv.org
• Locally Scale-Invariant Convolutional NeuralNetworksarxiv.org
• Scale-Invariant CNNarxiv.org
• Scale-Invariant Recognition by Weight-Shared CNNs in Parallelproceedings.mlr.press
• Naturally Occurring Equivariance in Neural Networksdistill.pub
• An Analysis of Scale Invariance in Object Detection SNIP - Singh_An_Analysis_of_CVPR_2018_paper.pdfopenaccess.thecvf.com
• [1711.08189] An Analysis of Scale Invariance in Object Detection - SNIParxiv.org
• Scale-invariant-CNNs/docs/Report/Implementation.md at master · ruoqizzz/Scale-invariant-CNNsgithub.com
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• The Decade of Deep Learning | Leo Gaobmk.sh
• Feature Visualizationdistill.pub
• Understanding deep learning requires rethinking generalizationarxiv.org