Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909138624184320 |
|---|---|
| author | Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Arrastia, Jean Le'Clerc Maass, Peter |
| author_facet | Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Arrastia, Jean Le'Clerc Maass, Peter |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_02181 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Arrastia, Jean Le'Clerc Maass, Peter Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing 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. |
| title | Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2302.02181 |