paper-with-me

홈 › Papers

On the Transformation of Latent Space in Autoencoders

2019-01-24 · Jaehoon Cha, Kyeong Soo Kim, Sanghyuk Lee

Noting the importance of the latent variables in inference and learning, we propose a novel framework for autoencoders based on the homeomorphic transformation of latent variables, which could reduce the distance between vectors in the transformed space, while preserving the topological properties of the original space, and investigate the effect of the latent space transformation on learning generative models and denoising corrupted data. The experimental results demonstrate that our generative and denoising models based on the proposed framework can provide better performance than conventional variational and denoising autoencoders due to the transformation, where we evaluate the performance of generative and denoising models in terms of the Hausdorff distance between the sets of training and processed i.e., either generated or denoised images, which can objectively measure their differences, as well as through direct comparison of the visual characteristics of the processed images.

📄 PDF Abstract BibTeX arXiv:1901.08479

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Similar Papers 제목 키워드 기반

No Representation without Transformation

2019-12-09 · Giorgio Giannone, Saeed Saremi, Jonathan Masci, Christian Osendorfer

We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order …

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

2025-02-13 · Theodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent…

Image Generation

Uniform Transformation: Refining Latent Representation in Variational Autoencoders

2024-07-02 · Ye Shi, C. S. George Lee

Irregular distribution in latent space causes posterior collapse, misalignment between posterior and prior, and ill-sampling problem in Variational Autoencoders (VAEs). In this paper, we introduce a novel adaptable three…

Density EstimationDisentanglementRepresentation Learning

On interpretability and proper latent decomposition of autoencoders

2022-11-15 · Luca Magri, Anh Khoa Doan

The dynamics of a turbulent flow tend to occupy only a portion of the phase space at a statistically stationary regime. From a dynamical systems point of view, this portion is the attractor. The knowledge of the turbulen…

Disentangling Autoencoders (DAE)

2022-02-20 · Jaehoon Cha, Jeyan Thiyagalingam

Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations in group-theor…

Disentanglement