← 研踪 PaperTrailarXiv:2609.35174 · v2
ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models
首次提交 2026-09-28 21:41
版本更新 2026-11-19 16:18
雷达观测 2026-11-20 19:58
摘要
We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls toward the prototype of its class with a classification loss of evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and vision transformer backbones, lifted training improves test accuracy by up to six percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 16:18 · 最新观测版本
ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models
We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls toward the prototype of its class with a classification loss of evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and vision transformer backbones, lifted training improves test accuracy by up to six percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.
查看此版本解读 →查看此版本原文 ↗