Attribute-Specific Manipulation Based on Layer-Wise Channels

TL;DR

This paper introduces a gradient-based method to detect attribute-specific channels in StyleGAN's style space, enabling precise attribute manipulation with improved accuracy and scalability over existing techniques.

Contribution

It proposes a novel gradient analysis approach for identifying attribute-specific channels in pre-trained classifiers, enhancing control over generated image attributes.

Findings

Accurately detects relevant channels for numerous face attributes.

Outperforms state-of-the-art methods in generalization.

Enables effective single- and multi-channel attribute manipulation.

Abstract

Image manipulation on the latent space of the pre-trained StyleGAN can control the semantic attributes of the generated images. Recently, some studies have focused on detecting channels with specific properties to directly manipulate the latent code, which is limited by the entanglement of the latent space. To detect the attribute-specific channels, we propose a novel detection method in the context of pre-trained classifiers. We analyse the gradients layer by layer on the style space. The intensities of the gradients indicate the channel's responses to specific attributes. The latent style codes of channels control separate attributes in the layers. We choose channels with top-$k$ gradients to control specific attributes in the maximum response layer. We implement single-channel and multi-channel manipulations with a certain attribute. Our methods can accurately detect relevant channels for a large number of face attributes. Extensive qualitative and quantitative results demonstrate that the proposed methods outperform state-of-the-art methods in generalization and scalability.