AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Rotation Equivariant Vector Field Networks

Diego Marcos, Michele Volpi, Nikos Komodakis, Devis Tuia

ICCV 2017 · Architectures and efficiency › CNN design · approach: Steerable rotation-equivariant CNNs · 251 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use vector field feature maps instead of scalar field (orientation pooling keeping only magnitude) (ablation)RotEqNet · MNIST-roterror rate (%): 2.01 -> 1.09Improved
add test-time rotation augmentationRotEqNet · MNIST-roterror rate (%): 1.09 -> 1.01Improved
add training data augmentationstandard CNN trained on MNIST · MNIST-roterror rate (%): 57% -> 2.3%Improved
add training data augmentationRotEqNet trained on MNIST · MNIST-roterror rate (%): 20% -> 1.1%Improved
add training data augmentationstandard CNN trained on MNIST-rot · MNIST-roterror rate (%): 4.9% -> 2.2%Improved
add training data augmentationRotEqNet trained on MNIST-rot · MNIST-roterror rate (%): 1.4% -> 1.1%Mixed
replace standard CNN (10x parameters) with RotEqNetMNIST-rot training without augmentation · MNIST-roterror rate (%): 4.9% -> 1.4%Improved
add training data augmentationstandard CNN · ISBI 2012 (validation)score: 0.9232 -> 0.9572Improved
add training data augmentationRotEqNet · ISBI 2012 (validation)score: 0.9726 -> 0.9790Improved
ensemble three models (N=1,2,3) instead of single N=2 modelRotEqNet · ISBI 2012 test (Rand. Thin)Rand score (thinned): 0.9599 -> 0.9712Improved
ensemble three models (N=1,2,3) instead of single N=2 modelRotEqNet · ISBI 2012 test (Inf. Thin)information score (thinned): 0.9806 -> 0.9865Improved
increase number of orientations R beyond 17 at test time (ablation)RotEqNet · Car orientation estimationaverage error (degrees)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy