paper-with-me

홈 › Papers

Demystifying Inter-Class Disentanglement

2019-06-27 · ICLR 2020 1 · Aviv Gabbay, Yedid Hoshen

Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disentanglement performance than both adversarial and non-adversarial methods that use the same level of supervision. We further introduce a clustering-based approach for extending our method for settings that exhibit in-class variation with promising results on the task of domain translation.

📄 PDF Abstract BibTeX arXiv:1906.11796

Code (2)

avivga/lord 공식 구현 tf
avivga/lord-pytorch pytorch

Tasks

ClusteringDisentanglementTranslationUnsupervised Image-To-Image Translation

Similar Papers 제목 키워드 기반

Demystifying Inductive Biases for $β$-VAE Based Architectures

2021-02-12 · Dominik Zietlow, Michal Rolinek, Georg Martius

The performance of $\beta$-Variational-Autoencoders ($\beta$-VAEs) and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments …

DisentanglementInductive Bias

Commutativity and Disentanglement from the Manifold Perspective

2022-10-14 · Frank Qiu

In this paper, we interpret disentanglement as the discovery of local charts of the data manifold and trace how this definition naturally leads to an equivalent condition for disentanglement: commutativity between factor…

Disentanglement

CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network

2021-03-05 · Jiangwei Zhao, Zejia Liu, Xiaohan Guo, Lili Pan

Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, …

Contrastive LearningDisentanglementGenerative Adversarial NetworkInterpretable Machine Learning

Demystifying Variational Diffusion Models

2024-01-11 · Fabio De Sousa Ribeiro, Ben Glocker

Despite the growing popularity of diffusion models, gaining a deep understanding of the model class remains somewhat elusive for the uninitiated in non-equilibrium statistical physics. With that in mind, we present what …

Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets

2021-06-07 · ACL (RepL4NLP) 2021 8 · Lan Zhang, Victor Prokhorov, Ehsan Shareghi

To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We ev…

DecoderDisentanglementInductive Bias