Delving into Rectifiers in Style-Based Image Translation

TL;DR

This paper investigates how rectifier activation functions influence style control in image translation, proposing adaptive techniques to enhance controllability and diversity of generated images.

Contribution

It introduces AdaReLU and structural adaptive functions that improve style controllability in image translation by manipulating activation slopes and feature map structures.

Findings

Enhanced controllability of style-based image translation.

Increased diversity of generated images.

Effective manipulation of feature maps using proposed methods.

Abstract

While modern image translation techniques can create photorealistic synthetic images, they have limited style controllability, thus could suffer from translation errors. In this work, we show that the activation function is one of the crucial components in controlling the direction of image synthesis. Specifically, we explicitly demonstrated that the slope parameters of the rectifier could change the data distribution and be used independently to control the direction of translation. To improve the style controllability, two simple but effective techniques are proposed, including Adaptive ReLU (AdaReLU) and structural adaptive function. The AdaReLU can dynamically adjust the slope parameters according to the target style and can be utilized to increase the controllability by combining with Adaptive Instance Normalization (AdaIN). Meanwhile, the structural adaptative function enables rectifiers to manipulate the structure of feature maps more effectively. It is composed of the proposed structural convolution (StruConv), an efficient convolutional module that can choose the area to be activated based on the mean and variance specified by AdaIN. Extensive experiments show that the proposed techniques can greatly increase the network controllability and output diversity in style-based image translation tasks.