Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks

By Minyoung Huh, Shao-Hua Sun, Ning Zhang. 2019

26 citations recorded by the source corpus.

We propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator. We formulate the generation task as a recurrent framework, in which the discriminator’s feedback is integrated into the feedforward path of the generation process. Specifically, the generator conditions on the discriminator’s spatial output response, and its previous generation to improve generation quality over time – allowing the generator to attend and fix its previous mistakes. To effectively utilize the feedback, we propose an adaptive spatial transform layer, which learns to spatially modulate feature maps from its previous generation and the error signal from the discriminator. We demonstrate that one can easily adapt FAL to existing adversarial learning frameworks on a wide range of tasks, including image generation, image-to-image translation, and voxel generation.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

A U-Net Based Discriminator for Generative Adversarial Networks (2020, background): “Other lines of work focused mainly on improving the discriminator by exploiting multiple [36, 13, 11] and multi-resolution [45, 42] discriminators, using spatial feedback of the discriminator [17], an auto-encoder architecture with the reconstructionbased feedback to the generator [52] or self-super”
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation (2019, methodology): “We investigate some representative modulation operations including attention-based (softmax) modulation [26, 47] and feature-wise linear modulation (FiLM) [31, 30, 13].”
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval (2021, methodology): “We are mostly inspired by recent image generation works [8, 3] that use the discriminator scores to iteratively improve generation quality.”