跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv: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
arXiv ↗PDF ↗

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 N=N2∘N1N=N_2\circ N_1 is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls N1(x)N_1(x) toward the prototype of its class with a classification loss of N2N_2 evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network N2∘N1N_2\circ N_1 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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

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 N=N2∘N1N=N_2\circ N_1 is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls N1(x)N_1(x) toward the prototype of its class with a classification loss of N2N_2 evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network N2∘N1N_2\circ N_1 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 ↗