# Adversarial Feedback Loop

arXiv: https://arxiv.org/abs/1811.08126 · HTML: https://mlsanity.com/paper/1811.08126/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval](https://mlsanity.com/paper/2103.13990/) (2021)
- [Cross-View Panorama Image Synthesis](https://mlsanity.com/paper/2203.11832/) (2022)
- [Cross-View Exocentric to Egocentric Video Synthesis](https://mlsanity.com/paper/2107.03120/) (2021)
- [Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies](https://mlsanity.com/paper/2203.13716/) (2022)
- [Towards the Unseen: Iterative Text Recognition by Distilling from Errors](https://mlsanity.com/paper/2107.12081/) (2021)
- [Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations](https://mlsanity.com/paper/2110.11998/) (2021)
- [Learning With Context Feedback Loop for Robust Medical Image Segmentation](https://mlsanity.com/paper/2103.02844/) (2021)
- [Diverse Single Image Generation with Controllable Global Structure](https://mlsanity.com/paper/2102.04780/) (2021)

## Abstract (arXiv)

Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a discriminator is trained to learn the real data distribution. To date, it has been used only for training purposes, where it's utilized to train the generator to provide real-looking outputs. In this paper we propose a novel method that makes an explicit use of the discriminator in test-time, in a feedback manner in order to improve the generator results. To the best of our knowledge it is the first time a discriminator is involved in test-time. We claim that the discriminator holds significant information on the real data distribution, that could be useful for test-time as well, a potential that has not been explored before. The approach we propose does not alter the conventional training stage. At test-time, however, it transfers the output from the generator into the discriminator, and uses feedback modules (convolutional blocks) to translate the features of the discriminator layers into corrections to the features of the generator layers, which are used eventually to get a better generator result. Our method can contribute to both conditional and unconditional GANs. As demonstrated by our experiments, it can improve the results of state-of-the-art networks for super-resolution, and image generation.