AI Paper Atlas

Research map / Image generation / Image restoration

Unsupervised Transformation Learning via Convex Relaxations

Tatsunori B Hashimoto, Percy Liang, John C. Duchi

NeurIPS 2017 · Image generation › Image restoration · approach: Image harmonization and color transformation · 8 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
Add gradient descent refinement after sampled convex relaxation (ablation)Sampled convex relaxation · Downsampled CelebA, single translation recoveryoperator norm errorImproved
Use sampled convex relaxation with gradient descent instead of gradient descent with restartsSingle-transform recovery · Downsampled CelebAoperator norm errorImproved
Use sampled convex relaxation with gradient descent instead of EMSingle-transform recovery · Downsampled CelebAoperator norm errorImproved
Add SVD-based disentangling (ablation)Multiple-transformation recovery · Downsampled CelebAoperator norm errorImproved
Add SVD-based disentangling (ablation)Gradient descent baseline · Downsampled CelebA, multiple transformationsoperator norm errorImproved
Use a five-dimensional linear transformation model learned from nearest-neighbor pairsMNIST transformation learning · MNISTqualitative transformation interpretabilityImproved
Apply learned linear transformations beyond the training image distributionMNIST-trained transformation model · Kannada handwritingqualitative transformation transferImproved
Learn transformations with the proposed method rather than PCAMNIST transformation visualization · MNISTstyle and identity separationImproved
Use the proposed method rather than InfoGANMNIST transformation learning · MNISTstyle and identity separationMixed

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