paper-with-me

홈 › Papers

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

2020-08-24 · ECCV 2020 8 · William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba

Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a generative model with respect to its input to be diagonal. We introduce a model-agnostic, unbiased stochastic approximation of this term based on Hutchinson's estimator to compute it efficiently during training. Our method can be applied to a wide range of deep generators with just a few lines of code. We show that training with the Hessian Penalty often causes axis-aligned disentanglement to emerge in latent space when applied to ProGAN on several datasets. Additionally, we use our regularization term to identify interpretable directions in BigGAN's latent space in an unsupervised fashion. Finally, we provide empirical evidence that the Hessian Penalty encourages substantial shrinkage when applied to over-parameterized latent spaces.

📄 PDF Abstract BibTeX arXiv:2008.10599

Code (1)

wpeebles/hessian_penalty 공식 구현 tf

Tasks

Disentanglement

Methods 이 논문이 사용한 방법론

WGAN-GP Loss Wasserstein Gradient Penalty Loss, or WGAN-GP Loss, is a loss used for generative adversarial networks that augments the Wasserstein loss with a gradient norm penalty for…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ProGAN 설명 없음

Similar Papers 제목 키워드 기반

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

2021-08-17 · ICCV 2021 10 · Yuxiang Wei, Yupeng Shi, Xiao Liu, Zhilong Ji 외

Unsupervised disentanglement learning is a crucial issue for understanding and exploiting deep generative models. Recently, SeFa tries to find latent disentangled directions by performing SVD on the first projection of a…

DisentanglementImage Generation

Weakly Supervised Disentanglement by Pairwise Similarities

2019-06-03 · Junxiang Chen, Kayhan Batmanghelich

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of in…

Disentanglement

Weakly Supervised Disentanglement with Guarantees

2019-10-22 · ICLR 2020 1 · Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon 외

Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning di…

Disentanglement

SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping

2022-09-21 · Jiageng Zhu, Hanchen Xie, Wael Abd-Almageed

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been …

DisentanglementRepresentation Learning

A Causal Ordering Prior for Unsupervised Representation Learning

2023-07-11 · Avinash Kori, Pedro Sanchez, Konstantinos Vilouras, Ben Glocker 외

Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a datas…

Causal DiscoverycounterfactualRepresentation LearningVariational Inference