AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Liu, Songhua; Lin, Tianwei; He, Dongliang; Li, Fu; Wang, Meiling; Li, Xin; Sun, Zhengxing; Li, Qian; Ding, Errui

doi:10.1109/iccv48922.2021.00658

Cited by 248 publications

(174 citation statements)

References 28 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…For the latter, self-attention mechanism in style transfer gives outstanding performance in assigning different style patterns to different regions in an image. SANet [28], SAFIN [10], AdaAttN [26] are examples. SANet [28] firstly introduced the first attention method for feature embedding in style transfer.…”

Section: Related Workmentioning

confidence: 99%

“…SANet [28], SAFIN [10], AdaAttN [26] are examples. SANet [28] firstly introduced the first attention method for feature embedding in style transfer. SAFIN [10] extended SANet [28] by using a self-attention module to learn how to create the parameters for our spatially adaptive normalization module, which makes normalization more spatially flexible and semantically aware.…”

Section: Related Workmentioning

confidence: 99%

“…SANet [28] firstly introduced the first attention method for feature embedding in style transfer. SAFIN [10] extended SANet [28] by using a self-attention module to learn how to create the parameters for our spatially adaptive normalization module, which makes normalization more spatially flexible and semantically aware. AdaAttN [26] calculated attention scores using both shallow and deep features, as well as properly normalizing content features so that feature statistics are well aligned with attention-weighted mean and variance maps of style features on a per-point basis.…”

Section: Related Workmentioning

confidence: 99%

“…Since the learned model can only synthesize for one specific style, this method and the following works [4], [11]- [17] are known as Per-Style-Per-Model method. Furthermore, these works [18]- [21] are categorized to Multiple-Style-Per-Model method and Arbitrary-Style-Per-Model [3], [5], [6], [8], [10], [22]- [26], [28], [30]. These findings address some of the style transfer issues, such as balancing content structure and style patterns while maintaining global and local style patterns.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Feature Rotation for Multimodal Image Style Transfer

Nguyen,

Tuyen,

Phuc

2022

Preprint

View full text Add to dashboard Cite

Recently, style transfer is a research area that attracts a lot of attention, which transfers the style of an image onto a content target. Extensive research on style transfer has aimed at speeding up processing or generating high-quality stylized images. Most approaches only produce an output from a content and style image pair, while a few others use complex architectures and can only produce a certain number of outputs. In this paper, we propose a simple method for representing style features in many ways called Deep Feature Rotation (DFR), while not only producing diverse outputs but also still achieving effective stylization compared to more complex methods. Our approach is representative of the many ways of augmentation for intermediate feature embedding without consuming too much computational expense. We also analyze our method by visualizing output in different rotation weights. Our code is available at https://github.com/sonnguyen129/deep-feature-rotation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Feature Rotation for Multimodal Image Style Transfer

Nguyen,

Tuyen,

Phuc

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…ResNeSt applies channel attention to different network branches, succeeding in crossfeature interaction. Furthermore, attention mechanisms [14][15][16] are also introduced into image classification tasks. The attention mechanism focuses on important information with high weight, ignores irrelevant information with low weight, and learn independently, and can continuously adjust the weight.…”

Section: Introductionmentioning

confidence: 99%

Mathematical Formula Image Screening Based on Feature Correlation Enhancement

et al. 2022

View full text Add to dashboard Cite

There are mathematical formula images or other images in scientific and technical documents or on web pages, and mathematical formula images are classified as either containing only mathematical formulas or formulas interspersed with other elements, such as text and coordinate diagrams. To screen and collect images containing mathematical formulas for others to study or for further research, a model for screening images of mathematical formulas based on feature correlation enhancement is proposed. First, the Feature Correlation Enhancement (FCE) module was designed to improve the correlation degree of mathematical formula features and weaken other features. Then, the strip multi-scale pooling (SMP) module was designed to solve the problem of non-uniform image size, while enhancing the focus on horizontal formula features. Finally, the loss function was improved to balance the dataset. The accuracy of the experiment was 89.50%, which outperformed the existing model. Using the model to screen images enables the user to screen out images containing mathematical formulas. The screening of images containing mathematical formulas helps to speed up the creation of a database of mathematical formula images.

show abstract

FAEC‐GAN: An unsupervised face‐to‐anime translation based on edge enhancement and coordinate attention

Lin

Liu

2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Animation is a widely loved artistic form with high abstraction and powerful expression. The task of image translation from face to anime involves complex geometric and texture transformations, and requires the generated images with clear lines. The existing unsupervised image translation frameworks are often ineffective for this task. According to the characteristics of animation image, we propose an animation translation method based on edge enhancement and coordinate attention, which is called FAEC‐GAN. We design a novel edge discrimination network to identify the edge features of images, so that the generated anime images can present clear and coherent lines. And the coordinate attention module is introduced in the encoder to adapt the model to the geometric changes in translation, so as to produce more realistic animation images. In addition, our method combines the focal frequency loss and pixel loss, which can pay attention to both the frequency domain information and pixel information of the generated image to improve the visual effect of the image. The experimental results demonstrate that FAEC‐GAN is superior to the state‐of‐the‐art methods in the task of face‐to‐animation image translation.

show abstract

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Cited by 248 publications

References 28 publications

Deep Feature Rotation for Multimodal Image Style Transfer

Deep Feature Rotation for Multimodal Image Style Transfer

Mathematical Formula Image Screening Based on Feature Correlation Enhancement

FAEC‐GAN: An unsupervised face‐to‐anime translation based on edge enhancement and coordinate attention

Contact Info

Product

Resources

About