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

Source: [Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time](<https://www.sota2.com/research/paper/68fa72911e209131cea5726f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:31:06.454Z

Authors: Rudolf Herdt, Maximilian Schmidt, Daniel Otero Baguer, Jean Le'Clerc Arrastia, Peter Maass (1 and 2) \_\_INSTITUTION\_5\_\_ University of Bremen, (2) aisencia)

Published: 2023-02-04T15:28:49.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2302.02181>)

[PDF](<https://arxiv.org/pdf/2302.02181.pdf>)