AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Interpretable Transformations With Encoder-Decoder Networks

Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov, Gabriel J. Brostow

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 85 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 the feature-transform-layer invariant features with a CNN instead of a standard CNN with data augmentationCNN classifier · MNIST-rottest error (%): 3.50 -> 2.14Improved
use a CNN encoder instead of an MLP encoder in the proposed modelfeature transform layer model · MNIST-rottest error (%): 4.90 -> 2.14Improved
use the MLP variant of the proposed model instead of a baseline CNNbaseline CNN · MNIST-rottest error (%): 5.03 -> 4.90Improved
add a regularization term that keeps invariant code lengths of transformed encodings equal (ablation)MNIST-rot classifier · MNIST-rottest error (%)Improved
add the feature transform layer (block-diagonal rotation matrices) to the networkencoder-decoder · training speedslowdown: slow down of just 2%Hurt
compare against rotation-specific equivariant networks (RotEqNet, Harmonic Networks, P4CNN)proposed CNN · MNIST-rottest error (%): 1.16 vs 2.14Hurt
classify ModelNet10 from relative-phase invariants of the equivariant code instead of using specialized 3D classifiersModelNet10 classifier · ModelNet10accuracy (%): 97.14% (VRN Ensemble) vs 90.4%Hurt

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