An Approach to Labeling Audio Tags Based on Self-Attention Generative Adversarial Networks

Chen, Yuan; Zhang, Bin; Ma, Bing

doi:10.1145/3377713.3377772

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kurach et al [12] explored regularization and normalization in GANs, identifying techniques such as spectral normalization, orthogonal regularization, and a gradient penalty, which enhance the GAN's performance. Zhang et al proposed SAGAN [13], which integrates a self-attention mechanism to bolster the GAN's feature representation capabilities and a conditional batch normalization layer for controlling sample categories.…”

Section: Gan-based Image Synthesismentioning

confidence: 99%

Generating Artistic Portraits from Face Photos with Feature Disentanglement and Reconstruction

Guo,

Ma,

Chen

et al. 2024

Electronics

View full text Add to dashboard Cite

Generating artistic portraits from face photos presents a complex challenge that requires high-quality image synthesis and a deep understanding of artistic style and facial features. Traditional generative adversarial networks (GANs) have made significant strides in image synthesis; however, they encounter limitations in artistic portrait generation, particularly in the nuanced disentanglement and reconstruction of facial features and artistic styles. This paper introduces a novel approach that overcomes these limitations by employing feature disentanglement and reconstruction techniques, enabling the generation of artistic portraits that more faithfully retain the subject’s identity and expressiveness while incorporating diverse artistic styles. Our method integrates six key components: a U-Net-based image generator, an image discriminator, a feature-disentanglement module, a feature-reconstruction module, a U-Net-based information generator, and a cross-modal fusion module, working in concert to transform face photos into artistic portraits. Through extensive experiments on the APDrawing dataset, our approach demonstrated superior performance in visual quality, achieving a significant reduction in the Fréchet Inception Distance (FID) score to 61.23, highlighting its ability to generate more-realistic and -diverse artistic portraits compared to existing methods. Ablation studies further validated the effectiveness of each component in our method, underscoring the importance of feature disentanglement and reconstruction in enhancing the artistic quality of the generated portraits.

show abstract

Section: Gan-based Image Synthesismentioning

confidence: 99%

Generating Artistic Portraits from Face Photos with Feature Disentanglement and Reconstruction

Guo,

Ma,

Chen

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…After obtaining a more accurate contour through mask completion, it is necessary to recover the content of the object to obtain a complete expression of object features. There are many effective methods from mask to object generation [22][23][24][25][26]. However, in terms of the complete effect of occluded objects, existing methods have difficulty obtaining the same quality as the object generated directly from the complete mask.…”

Section: Introductionmentioning

confidence: 99%

GIGAN: Self‐supervised GAN for generating the invisible using cycle transformation and conditional normalization

Quan

Liu

2023

IET Image Processing

View full text Add to dashboard Cite

Objects in a real scene often occlude each other and inferring a complete appearance from the visible part is an important and challenging task. In this paper, the authors propose a self-supervised generative adversarial network GIGAN (GAN for generating the invisible), which can generate the complete appearance of objects without labelled invisible part information. The authors build two cycle transformation networks CycleIncomplete (CycleI) and CycleComplete (CycleC) that share parameters to improve the accuracy of mask completion. This design does not require well-matched training images and can make better use of the limited labelled samples. In addition, the authors propose a conditional normalization module and combine it with the inferred complete mask output. The combination not only enhances the content recovery ability and obtains more realistic outputs, but also improves the efficiency of the generation process. Experimental results show that compared with existing self-supervised learning models, our method achieves l 1 error, mean intersection-over-union (mIOU), and Fréchet inception distance (FID) improvements on the COCOA and KINS datasets.

show abstract

An Approach to Labeling Audio Tags Based on Self-Attention Generative Adversarial Networks

Cited by 2 publications

References 3 publications

Generating Artistic Portraits from Face Photos with Feature Disentanglement and Reconstruction

Generating Artistic Portraits from Face Photos with Feature Disentanglement and Reconstruction

GIGAN: Self‐supervised GAN for generating the invisible using cycle transformation and conditional normalization

Contact Info

Product

Resources

About