Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement

Ren, Xuanchi; Yang, Tao; Zeng, Wenjun; Wang, Yuwang

doi:10.1109/iccvw54120.2021.00209

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and Lee et al [ 99 ] proposed to separate an image into two spaces, a content space and an attribute space. Another type of disentanglement was proposed by [ 8 , 100 ], who considered the important features as content and the remaining ones as style features.…”

Section: Guidancementioning

confidence: 99%

“…Ren et al [ 100 ] began their paper by stating that most content-style disentanglement methods depend on supervision to guide the disentanglement. They followed the work of Gabbay et al [ 102 ] and proposed an unsupervised content-style disentanglement module (C-S DisMo), which tries to isolate the most important features for the reconstruction from less important features.…”

Section: Guidancementioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Image-to-Image Translation: A Review

Hoyez

Schockaert

Rambach

et al. 2022

Sensors

View full text Add to dashboard Cite

Supervised image-to-image translation has been proven to generate realistic images with sharp details and to have good quantitative performance. Such methods are trained on a paired dataset, where an image from the source domain already has a corresponding translated image in the target domain. However, this paired dataset requirement imposes a huge practical constraint, requires domain knowledge or is even impossible to obtain in certain cases. Due to these problems, unsupervised image-to-image translation has been proposed, which does not require domain expertise and can take advantage of a large unlabeled dataset. Although such models perform well, they are hard to train due to the major constraints induced in their loss functions, which make training unstable. Since CycleGAN has been released, numerous methods have been proposed which try to address various problems from different perspectives. In this review, we firstly describe the general image-to-image translation framework and discuss the datasets and metrics involved in the topic. Furthermore, we revise the current state-of-the-art with a classification of existing works. This part is followed by a small quantitative evaluation, for which results were taken from papers.

show abstract

Section: Guidancementioning

confidence: 99%

Section: Guidancementioning

confidence: 99%

Unsupervised Image-to-Image Translation: A Review

Hoyez

Schockaert

Rambach

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…We encode the contrast information into a low-dimensional vector by a shared encoder E C . We employ an information bottleneck loss [2,19] here to limit the information capacity of c and avoid informative leakage:…”

Section: Contrast Encodermentioning

confidence: 99%

DisQ: Disentangling Quantitative MRI Mapping of the Heart

Yang¹,

Zhao²,

Huang³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Quantitative MRI (qMRI) of the heart has become an important clinical tool for examining myocardial tissue properties. Because heart is a moving object, it is usually imaged with electrocardiogram and respiratory gating during acquisition, to "freeze" its motion. In reality, gating is more-often-than-not imperfect given the heart rate variability and nonideal breath-hold. qMRI of the heart, consequently, is characteristic of varying image contrast as well as residual motion, the latter compromising the quality of quantitative mapping. Motion correction is an important step prior to parametric mapping, however, a long-standing difficulty for registering the dynamic sequence is that the contrast across frames varies wildly: depending on the acquisition scheme some frames can have extremely poor contrast, which fails both traditional optimization-based and modern learning-based registration methods. In this work, we propose a novel framework named DisQ, which Disentangles Quantitative mapping sequences into the latent space of contrast and anatomy, fully unsupervised. The disentangled latent spaces serve for the purpose of generating a series of images with identical contrast, which enables easy and accurate registration of all frames. We applied our DisQ method to the modified Look-Locker inversion recovery (MOLLI) sequence, and demonstrated improved performance of T1 mapping. In addition, we showed the possibility of generating a dynamic series of baseline images with exactly the same shape, strictly registered and perfectly "frozen". Our proposed DisQ methodology readily extends to other types of cardiac qMRI such as T2 mapping and perfusion.

show abstract

Disentanglement and Local Directions of Variance

Rakowski

Lippert

2021

Machine Learning and Knowledge Discovery in Databases. Research Track

View full text Add to dashboard Cite

Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement

Cited by 6 publications

References 21 publications

Unsupervised Image-to-Image Translation: A Review

Unsupervised Image-to-Image Translation: A Review

DisQ: Disentangling Quantitative MRI Mapping of the Heart

Disentanglement and Local Directions of Variance

Contact Info

Product

Resources

About