Metraipolis › archive › dc_e4ef16716e1c
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification — arXiv:2609.13518
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13518
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:10:18.660Z
- SHA-256 of the archived text
9060d3e1b4c3806e26e1c8f779532c2d5bb4df6af9749486db57fa5c3d779c22- Stable URL of this page
https://metraipolis.com/documento/dc_e4ef16716e1c
How to cite
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification — arXiv:2609.13518 — arXiv (en), https://arxiv.org/abs/2609.13518 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4ef16716e1c (Metraipolis archive dc_e4ef16716e1c, sha256 9060d3e1b4c3806e26e1c8f779532c2d5bb4df6af9749486db57fa5c3d779c22)
BibTeX
@misc{dce4ef16716e1c,
title = {GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification — arXiv:2609.13518},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13518},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4ef16716e1c; sha256 9060d3e1b4c3806e26e1c8f779532c2d5bb4df6af9749486db57fa5c3d779c22},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13518. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present GeoTTER, a novel framework that redefines optimal transport in the realm of zero-shot classification. Conventional methods often suffer from miscalibration and a lack of adaptability, as they rely on fixed cost matrices derived solely from pre-trained model embeddings. In contrast, GeoTTER addresses these limitations by incorporating two key techniques. First, to alleviate high-frequency label jaggedness (sample-level manifold jitter that assigns neighboring embeddings to different classes), GeoTTER integrates local geometric structure into the optimal transport formulation via graph-Laplacian smoothing, a technique grounded in spectral graph theory that enforces neighborhood consistency. Second, to correct coherent angular drift (a low-frequency orientation bias in which large groups of samples share the same angular offset from their true label prototypes), we fuse clustering-guided cost components with a globally adjusted transport cost, achieving a multi-objective optimization that respects both global distribution constraints and latent data structure. With a median improvement of +6.82% compared to zero-shot and +2.13% compared to OTTER, GeoTTER shows robust improvements across a diverse set of benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.13518 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.619Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).