AI Paper Atlas

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

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

Ferran Alet, Maria Bauza Villalonga, Kenji Kawaguchi, Nurullah Giray Kuru, Tomas Perez, Leslie Pack Kaelbling

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 5 citations (OpenAlex)

Read the paper

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
meta-tailor randomized smoothing with cosine-feature smoothness lossRandomized Smoothing · ImageNet sigma=0.25ACR: 0.470 -> 0.494Improved
meta-tailor randomized smoothing with cosine-feature smoothness lossRandomized Smoothing · ImageNet sigma=0.5ACR: 0.720 -> 0.819Improved
meta-tailor randomized smoothing with cosine-feature smoothness lossRandomized Smoothing · ImageNet sigma=1.0ACR: 0.863 -> 1.032Improved
meta-tailor randomized smoothingRandomized Smoothing · CIFAR-10 sigma=0.25/0.5/1.0ACR: 8.6%,10.4%,19.2%Improved
meta-tailor the linear layer of SimCLR with a contrastive lossSimCLR · CIFAR-10accuracy: 0.5% and 0.8%Improved
meta-tailoring versus inductive learning with physics tailoring loss3-layer MLP · 5-body planetary systemtest MSE: 35%Improved
tailor model parameters instead of directly optimizing the output y (ablation)Physics tailoring loss · 5-body planetary systemtest MSEImproved
use first-order instead of second-order CNGrad (ablation)Meta-tailoring · 5-body planetary systemtest MSEMixed
meta-tailoring with no query-time tailoring steps (ablation)Meta-tailoring · 5-body planetary systemtest MSEImproved
add test-time training (TTT) to SimCLRSimCLR · CIFAR-10accuracyHurt
meta-tailor MLP with soft energy conservation instead of built-in conservation (HNN)Vanilla MLP · real pendulumlong-term prediction lossImproved

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