Semi-Supervised StyleGAN for Disentanglement Learning
- URL: http://arxiv.org/abs/2003.03461v3
- Date: Wed, 25 Nov 2020 23:06:53 GMT
- Title: Semi-Supervised StyleGAN for Disentanglement Learning
- Authors: Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath, Anjul Patney,
Ankit B. Patel, Anima Anandkumar
- Abstract summary: Current disentanglement methods face several inherent limitations.
We design new architectures and loss functions based on StyleGAN for semi-supervised high-resolution disentanglement learning.
- Score: 79.01988132442064
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Disentanglement learning is crucial for obtaining disentangled
representations and controllable generation. Current disentanglement methods
face several inherent limitations: difficulty with high-resolution images,
primarily focusing on learning disentangled representations, and
non-identifiability due to the unsupervised setting. To alleviate these
limitations, we design new architectures and loss functions based on StyleGAN
(Karras et al., 2019), for semi-supervised high-resolution disentanglement
learning. We create two complex high-resolution synthetic datasets for
systematic testing. We investigate the impact of limited supervision and find
that using only 0.25%~2.5% of labeled data is sufficient for good
disentanglement on both synthetic and real datasets. We propose new metrics to
quantify generator controllability, and observe there may exist a crucial
trade-off between disentangled representation learning and controllable
generation. We also consider semantic fine-grained image editing to achieve
better generalization to unseen images.
Related papers
- InfRS: Incremental Few-Shot Object Detection in Remote Sensing Images [11.916941756499435]
In this paper, we explore the intricate task of incremental few-shot object detection in remote sensing images.
We introduce a pioneering fine-tuning-based technique, termed InfRS, designed to facilitate the incremental learning of novel classes.
We develop a prototypical calibration strategy based on the Wasserstein distance to mitigate the catastrophic forgetting problem.
arXiv Detail & Related papers (2024-05-18T13:39:50Z) - Towards Improved Semiconductor Defect Inspection for high-NA EUVL based on SEMI-SuperYOLO-NAS [0.9997798039664684]
This research aims to propose a scale-invariant ADCD framework capable to upscale images.
We propose an improvised ADCD framework as SEMI-SuperYOLO-NAS, which builds upon the baseline YOLO-NAS architecture.
arXiv Detail & Related papers (2024-04-08T20:51:30Z) - Bilevel Fast Scene Adaptation for Low-Light Image Enhancement [50.639332885989255]
Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision.
Main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes.
We introduce the bilevel paradigm to model the above latent correspondence.
A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes.
arXiv Detail & Related papers (2023-06-02T08:16:21Z) - Generative Modeling Helps Weak Supervision (and Vice Versa) [87.62271390571837]
We propose a model fusing weak supervision and generative adversarial networks.
It captures discrete variables in the data alongside the weak supervision derived label estimate.
It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels.
arXiv Detail & Related papers (2022-03-22T20:24:21Z) - Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly
Supervised Semantic Segmentation [16.560870740946275]
Explicit Pseudo-pixel Supervision (EPS) learns from pixel-level feedback by combining two weak supervisions.
We devise a joint training strategy to fully utilize the complementary relationship between both information.
Our method can obtain accurate object boundaries and discard co-occurring pixels, thereby significantly improving the quality of pseudo-masks.
arXiv Detail & Related papers (2021-05-19T07:31:11Z) - Mixed supervision for surface-defect detection: from weakly to fully
supervised learning [5.69361786082969]
In this work, we relax heavy requirements of fully supervised learning methods and reduce the need for highly detailed annotations.
By proposing a deep-learning architecture, we explore the use of annotations of different details ranging from weak (image-level) labels through mixed supervision to full (pixel-level) annotations on the task of surface-defect detection.
The proposed method outperforms all related approaches in fully supervised settings and also outperforms weakly-supervised methods when only image-level labels are available.
arXiv Detail & Related papers (2021-04-13T10:00:10Z) - Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object
Detection [66.10057490293981]
We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection.
Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
arXiv Detail & Related papers (2021-03-29T09:27:23Z) - Towards Unsupervised Deep Image Enhancement with Generative Adversarial
Network [92.01145655155374]
We present an unsupervised image enhancement generative network (UEGAN)
It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner.
Results show that the proposed model effectively improves the aesthetic quality of images.
arXiv Detail & Related papers (2020-12-30T03:22:46Z) - ErGAN: Generative Adversarial Networks for Entity Resolution [8.576633582363202]
A major challenge in learning-based entity resolution is how to reduce the label cost for training.
We propose a novel deep learning method, called ErGAN, to address the challenge.
We have conducted extensive experiments to empirically verify the labeling and learning efficiency of ErGAN.
arXiv Detail & Related papers (2020-12-18T01:33:58Z) - High-Fidelity Synthesis with Disentangled Representation [60.19657080953252]
We propose an Information-Distillation Generative Adrial Network (ID-GAN) for disentanglement learning and high-fidelity synthesis.
Our method learns disentangled representation using VAE-based models, and distills the learned representation with an additional nuisance variable to the separate GAN-based generator for high-fidelity synthesis.
Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation.
arXiv Detail & Related papers (2020-01-13T14:39:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.