AI Paper Atlas

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

Topological Parallax: A Geometric Specification for Deep Perception Models

Abraham David Smith, Michael J. Catanzaro, Gabrielle Angeloro, Nirav Patel, Paul Bendich

NeurIPS 2023 · 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
Use the local-chart model K2 instead of the fully connected K1 modelCyclo-octane model · Cyclo-octane2λ_lo: 3.45 -> 1.0Mixed
Use a model built from many local chartsCyclo-octane model K2 · Cyclo-octanehomological matching scale 2λ_hi: 2λ_hi≈1.25Improved
Allow interpolation across longer edges using K1Cyclo-octane model K1 · Cyclo-octane bond lengthsmean bond length (Å): 1.2876Hurt
Use a hard cutoff at distance 1.0 from jar imagesUtah jar classifier · Utah jar interpolationinterpolation acceptanceHurt

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