GeoTTER：利用最优传输的局部几何进行零样本分类
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
浏览论文内容
中文总结 AI 辅助
GeoTTER通过图拉普拉斯平滑和聚类引导成本融合，改进最优传输以解决零样本分类中的校准和适应性问题，在多个基准上中位提升6.82%。
中文摘要 AI 辅助
我们提出了GeoTTER，一种在零样本分类领域中重新定义最优传输的新框架。传统方法通常因依赖于仅从预训练模型嵌入中得出的固定成本矩阵而遭受校准不当和适应性不足的问题。相比之下，GeoTTER通过结合两项关键技术来解决这些局限。首先，为了缓解高频标签锯齿现象（即样本级流形抖动，将邻近嵌入分配到不同类别），GeoTTER通过图拉普拉斯平滑将局部几何结构整合到最优传输公式中，这是一种基于谱图理论的技术，用于强制邻域一致性。其次，为了校正相干角漂移（一种低频方向偏差，其中大组样本共享相对于其真实标签原型的相同角度偏移），我们将聚类引导的成本组件与全局调整的传输成本相融合，实现多目标优化，既尊重全局分布约束又尊重潜在数据结构。与零样本相比，中位数改进+6.82%，与OTTER相比改进+2.13%，GeoTTER在多种基准测试中显示出稳健的提升。
英文摘要
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.
发表机构
- SUNY Buffalo（纽约州立大学布法罗分校）
- Lawrence Livermore National Lab（劳伦斯利弗莫尔国家实验室）
机构由 AI 辅助整理，请以论文原文为准。
