English

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

Computer Vision and Pattern Recognition 2024-03-19 v2 Artificial Intelligence Machine Learning Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2302.02181,
  title  = {Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time},
  author = {Rudolf Herdt and Maximilian Schmidt and Daniel Otero Baguer and Jean Le'Clerc Arrastia and Peter Maass},
  journal= {arXiv preprint arXiv:2302.02181},
  year   = {2024}
}
R2 v1 2026-06-28T08:32:01.389Z