预测函数而非特征：用于医学图像分割的具有函数空间联合嵌入预测学习的KANs
Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation
浏览论文内容
中文总结 AI 辅助
针对现有KAN分割模型边函数缺乏聚合前学习目标的局限，提出FS-JEPA框架，将预测学习迁移至KAN聚合前函数空间，在五个医学图像分割基准上实现最优平均戴斯系数，较最强KAN方法提升2.25个百分点。
中文摘要 AI 辅助
柯尔莫哥洛夫-阿诺尔德网络（KANs）通过将每个网络边参数化为可学习的单变量函数，引入了显式的函数表示。然而，现有的基于KAN的分割模型仅通过边聚合后定义的目标来优化边函数，使得单个函数缺乏显式的聚合前学习目标。为解决这一局限，我们提出用于医学图像分割的函数空间联合嵌入预测学习（FS-JEPA）。我们的FS-JEPA框架将预测学习迁移至KANs的聚合前函数空间。带掩码的在线分支预测由全上下文指数移动平均目标分支生成的采样KAN边函数的结构化特征，而共享边索引则保留预测与目标间的对应关系。我们并非预测孤立的边响应，而是使用由输入锚点周围的函数评估构成的多半径特征来表示每个采样边函数。该结构化表示捕捉了单一响应无法刻画的局部函数变化，提供了更具信息性的预测目标。函数空间目标在训练期间与分割损失联合优化，而推理时移除预测分支。在五个医学图像分割基准上的实验表明，我们的FS-JEPA取得了最优的平均戴斯系数，且比最强的竞争性基于KAN的方法高出2.25个百分点。
英文摘要
Kolmogorov--Arnold Networks (KANs) introduce explicit functional representations by parameterizing each network edge as a learnable univariate function. However, existing KAN-based segmentation models optimize edge functions only through objectives defined after edge aggregation, leaving individual functions without an explicit pre-aggregation learning target. To address this limitation, we propose Function-Space Joint-Embedding Predictive Learning (FS-JEPA) for medical image segmentation. Our FS-JEPA framework moves predictive learning into the pre-aggregation function space of KANs. A masked online branch predicts structured signatures of sampled KAN edge functions generated by a full-context exponential moving average target branch, while shared edge indices preserve correspondence between predictions and targets. Rather than predicting an isolated edge response, we represent each sampled edge function using a multi-radius signature composed of function evaluations around its input anchor. This structured representation captures local functional variations that cannot be characterized by a single response and provides a more informative predictive target. The function-space objective is jointly optimized with the segmentation loss during training, while the predictive branch is removed at inference. Experiments on five medical image segmentation benchmarks show that our FS-JEPA achieves the best average Dice and outperforms the strongest competing KAN-based method by +2.25 percentage points.
