paper-with-me

홈 › Papers

PIE: Pseudo-Invertible Encoder

2021-10-31 · ICLR 2019 5 · Jan Jetze Beitler, Ivan Sosnovik, Arnold Smeulders

We consider the problem of information compression from high dimensional data. Where many studies consider the problem of compression by non-invertible transformations, we emphasize the importance of invertible compression. We introduce new class of likelihood-based autoencoders with pseudo bijective architecture, which we call Pseudo Invertible Encoders. We provide the theoretical explanation of their principles. We evaluate Gaussian Pseudo Invertible Encoder on MNIST, where our model outperforms WAE and VAE in sharpness of the generated images.

📄 PDF Abstract BibTeX arXiv:2111.00619

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LIA: Latently Invertible Autoencoder with Adversarial Learning

2019-09-25 · Jiapeng Zhu, Deli Zhao, Bolei Zhou, Bo Zhang

Deep generative models such as Variational AutoEncoder (VAE) and Generative Adversarial Network (GAN) play an increasingly important role in machine learning and computer vision. However, there are two fundamental issues…

DecoderGenerative Adversarial NetworkVariational Inference

Disentangled Inference for GANs with Latently Invertible Autoencoder

2019-06-19 · Jiapeng Zhu, Deli Zhao, Bo Zhang, Bolei Zhou

Generative Adversarial Networks (GANs) play an increasingly important role in machine learning. However, there is one fundamental issue hindering their practical applications: the absence of capability for encoding real-…

Decoder

Augmented Invertible Koopman Autoencoder for long-term time series forecasting

2025-03-17 · Anthony Frion, Lucas Drumetz, Mauro Dalla Mura, Guillaume Tochon 외

Following the introduction of Dynamic Mode Decomposition and its numerous extensions, many neural autoencoder-based implementations of the Koopman operator have recently been proposed. This class of methods appears to be…

Time SeriesTime Series Forecasting

Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows

2025-05-21 · Anqiao Ouyang, Hongyi Ke, Qi Wang

Invertible neural architectures have recently attracted attention for their compactness, interpretability, and information-preserving properties. In this work, we propose the Fourier-Invertible Neural Encoder (FINE), whi…

Dimensionality ReductionPhysics-informed machine learningRepresentation Learning

Benchmarking Invertible Architectures on Inverse Problems

2021-01-26 · Jakob Kruse, Lynton Ardizzone, Carsten Rother, Ullrich Köthe

Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten invertible architectures and related models far…

Benchmarking