GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification

• URL: http://arxiv.org/abs/2609.13518v1
• Date: Fri, 11 Sep 2026 20:38:54 GMT
• Title: GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
• Abstract summary: GeoTTER is a novel framework that redefines optimal transport in the realm of zero-shot classification.<n>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.
• Score: 6.57308991987631
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification [52.452902154360565]
  CuBAS is an information-geometric framework for adaptive data selection in supervised classification.<n>A labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geometric complexity of the data distribution.
  arXiv  Detail & Related papers  (2026-07-03T09:36:02Z)
• Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach [10.914852410153921]
  We propose FedEPD, a framework built on a dual decoupling paradigm that separates topological purification from semantic recalibration.<n>FedEPD achieves state-of-the-art performance across diverse long-tailed benchmarks, yielding absolute improvements of up to 4.97% in Accuracy and 5.48% in Macro-F1.
  arXiv  Detail & Related papers  (2026-06-23T07:25:40Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement [15.9788448312641]
  Cross-view geo-localization (CVGL) aims to accurately localize street-view images through retrieval of corresponding geo-tagged satellite images.<n>While prior works have achieved nearly perfect performance on certain standard datasets, their robustness in real-world corrupted environments remains under-explored.<n>We introduce MRGeo, the first systematic method designed for robust CVGL under corruption.
  arXiv  Detail & Related papers  (2026-03-13T02:37:43Z)
• Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining [10.091031517157411]
  TopoOT is a topology-aware optimal transport (OT) framework.<n>It integrates multi-filtration persistence diagrams (PDs) with test-time adaptation (TTA)<n>TopoOT achieves state-of-the-art performance across 2D and 3D anomaly detection benchmarks.
  arXiv  Detail & Related papers  (2026-01-28T07:49:28Z)
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation [109.13471554184554]
  We reformulate dataset distillation as an Optimal Transport (OT) distance minimization problem.<n>OT offers a geometrically faithful framework for distribution matching.<n>Our method consistently outperforms state-of-the-art approaches in an efficient manner.
  arXiv  Detail & Related papers  (2025-11-29T04:04:05Z)
• Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps [4.471962177124311]
  In distributed machine learning, linear variables across multiple agents with different data poses significant challenges. In this paper we show that a framework that achieves the Lagrangian convergence on the primal variable requires no inter-agent communication.
  arXiv  Detail & Related papers  (2024-07-02T22:14:54Z)
• InfoOT: Information Maximizing Optimal Transport [58.72713603244467]
  InfoOT is an information-theoretic extension of optimal transport. It maximizes the mutual information between domains while minimizing geometric distances. This formulation yields a new projection method that is robust to outliers and generalizes to unseen samples.
  arXiv  Detail & Related papers  (2022-10-06T18:55:41Z)
• Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning [58.79085525115987]
  Local methods are one of the promising approaches to reduce communication time. We show that the communication complexity is better than non-local methods when the local datasets is smaller than the smoothness local loss.
  arXiv  Detail & Related papers  (2022-02-12T15:12:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.