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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the local-chart model K2 instead of the fully connected K1 model | Cyclo-octane model · Cyclo-octane | 2λ_lo: 3.45 -> 1.0 | Mixed |
| Use a model built from many local charts | Cyclo-octane model K2 · Cyclo-octane | homological matching scale 2λ_hi: 2λ_hi≈1.25 | Improved |
| Allow interpolation across longer edges using K1 | Cyclo-octane model K1 · Cyclo-octane bond lengths | mean bond length (Å): 1.2876 | Hurt |
| Use a hard cutoff at distance 1.0 from jar images | Utah jar classifier · Utah jar interpolation | interpolation acceptance | Hurt |
Closest papers by meaning
- MANTRA: The Manifold Triangulations Assemblage (ICLR 2025 · similarity 0.85)
- Alignment of CNN and Human Judgments of Geometric and Topological Concepts (AAAI 2025 · similarity 0.84)
- Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework (NeurIPS 2025 · similarity 0.84)
- GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training (ICLR 2025 · similarity 0.83)
- Towards Scalable Topological Regularizers (ICLR 2025 · similarity 0.83)
- Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity (ICLR 2025 · similarity 0.83)
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.
