当前位置: X-MOL 学术arXiv.cs.LG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fast Fr\'echet Inception Distance
arXiv - CS - Machine Learning Pub Date : 2020-09-29 , DOI: arxiv-2009.14075
Alexander Mathiasen, Frederik Hvilsh{\o}j

The Fr\'echet Inception Distance (FID) has been used to evaluate thousands of generative models. We present a novel algorithm, FastFID, which allows fast computation and backpropagation for FID. FastFID can efficiently (1) evaluate generative model *during* training and (2) construct adversarial examples for FID.

中文翻译:

快速 Fr\'echet 起始距离

Fr\'echet 初始距离 (FID) 已被用于评估数以千计的生成模型。我们提出了一种新算法 FastFID,它允许 FID 的快速计算和反向传播。FastFID 可以有效地 (1) 在 * 训练期间评估生成模型和 (2) 为 FID 构建对抗性示例。
更新日期:2020-09-30
down
wechat
bug