arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.02181cs.CVcs.AIcs.LGeess.IV
收藏

模型拼接与可视化:GAN生成器如何实时反转网络

Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time

University of Bremen(不来梅大学)

Rudolf Herdt, Maximilian Schmidt, Daniel Otero Baguer, Jean Le'Clerc Arrastia, Peter Maass

AI总结:

提出通过1x1卷积将分类/分割网络与GAN生成器拼接,实现快速准确的激活重建,性能与梯度下降相当但速度快两个数量级。

摘要:

在这项工作中,我们提出了一种快速且准确的方法,通过利用1x1卷积将分类和语义分割网络与GAN生成器拼接,来重建这些网络的激活。我们在AFHQ野生数据集、ImageNet1K以及染色组织样本的真实数字病理扫描图像上测试了我们的方法。结果表明,我们的性能与既定的梯度下降方法相当,但处理速度快了两个数量级,这使得该方法在实际应用中具有前景。

英文摘要:

In this work, we propose a fast and accurate method to reconstruct activations of classification and semantic segmentation networks by stitching them with a GAN generator utilizing a 1x1 convolution. We test our approach on images of animals from the AFHQ wild dataset, ImageNet1K, and real-world digital pathology scans of stained tissue samples. Our results show comparable performance to established gradient descent methods but with a processing time that is two orders of magnitude faster, making this approach promising for practical applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑