AI Paper Atlas

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

Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance

Lorenzo Tausani, Paolo Muratore, Morgan Bruce Talbot, Giacomo Amerio, Gabriel Kreiman, Davide Zoccolan

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 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
optimize with both stretch and squeeze losses instead of one (ablation)SnS · invariant/adversarial image synthesisimage propertiesImproved
use SnS invariant images instead of affine transformations of the MEISnS · L2-robust ResNet50 readout unitspixel distance vs activation preserved: L2 distance 271 with 34% activation dropImproved
stretch deeper layer representations instead of pixel space (robust network) (ablation)SnS on L2-robust ResNet50 · human 12-AFC recognitionhuman classification accuracyHurt
stretch deeper layer representations instead of pixel space (standard network) (ablation)SnS on standard ResNet50 · human 12-AFC recognitionhuman classification accuracyImproved
L2 adversarial training of the subject networkResNet50 · human recognition of SnS invariant imageshuman classification accuracyImproved
L2 robustification effect at deeper stretching layersResNet50 · interpretability gap robust vs standardhuman classification accuracyMixed
use L-infinity instead of L2 robustificationResNet50 · observer recognition of invariant imagesobserver accuracyImproved
subsample the stretched layer representation (ablation)SnS · representational distance of invariant imagesqualitative / distanceNo clear effect

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