PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise

• URL: http://arxiv.org/abs/2403.08216v2
• Date: Tue, 23 Apr 2024 08:41:47 GMT
• Title: PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise
• Authors: Qinglong Meng, Chongkun Xia, Xueqian Wang,
• Abstract summary: We propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. We validate our method on the main benchmarks of unconditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper.
• Score: 4.762593660623934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution and the data distribution, flow-based models might perform badly. 2) Discrete data might make flow-based models collapse into a degenerate mixture of point masses. To sidestep such two issues, we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. To implement PaddingFlow, only the dimension of normalizing flows needs to be modified. Thus, our method is easy to implement and computationally cheap. Moreover, the padding-dimensional noise is only added to the padding dimension, which means PaddingFlow can dequantize without changing data distributions. Implementing existing dequantization methods needs to change data distributions, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for Variational Autoencoder (VAE) models, and the Inverse Kinematics (IK) experiments which are conditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper, which means PaddingFlow is widely suitable for various tasks. The code is available at: https://github.com/AdamQLMeng/PaddingFlow.

Related papers

• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling [49.215957313126324]
  Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details. We propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results.
  arXiv  Detail & Related papers  (2024-05-05T14:05:33Z)
• Comparative Study of Coupling and Autoregressive Flows through Robust Statistical Tests [0.0]
  We propose an in-depth comparison of coupling and autoregressive flows, both of the affine and rational quadratic type. We focus on a set of multimodal target distributions increasing dimensionality ranging from 4 to 400. Our results indicate that the A-RQS algorithm stands out both in terms of accuracy and training speed.
  arXiv  Detail & Related papers  (2023-02-23T13:34:01Z)
• VQ-Flows: Vector Quantized Local Normalizing Flows [2.7998963147546148]
  We introduce a novel statistical framework for learning a mixture of local normalizing flows as "chart maps" over a data manifold. Our framework augments the expressivity of recent approaches while preserving the signature property of normalizing flows, that they admit exact density evaluation.
  arXiv  Detail & Related papers  (2022-03-22T09:22:18Z)
• Discrete Denoising Flows [87.44537620217673]
  We introduce a new discrete flow-based model for categorical random variables: Discrete Denoising Flows (DDFs) In contrast with other discrete flow-based models, our model can be locally trained without introducing gradient bias. We show that DDFs outperform Discrete Flows on modeling a toy example, binary MNIST and Cityscapes segmentation maps, measured in log-likelihood.
  arXiv  Detail & Related papers  (2021-07-24T14:47:22Z)
• DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows [145.83812019515818]
  We propose DeFlow, a method for learning image degradations from unpaired data. We model the degradation process in the latent space of a shared flow-decoder network. We validate our DeFlow formulation on the task of joint image restoration and super-resolution.
  arXiv  Detail & Related papers  (2021-01-14T18:58:01Z)
• ShapeFlow: Dynamic Shape Interpreter for TensorFlow [10.59840927423059]
  We present ShapeFlow, a dynamic abstract interpreter for which quickly catches shape incompatibility errors. ShapeFlow constructs a custom shape computational graph, similar to the computational graph used by the programmer. We evaluate ShapeFlow on 52 programs collected by prior empirical studies to show how fast and accurately it can catch shape incompatibility errors.
  arXiv  Detail & Related papers  (2020-11-26T19:27:25Z)
• Self Normalizing Flows [65.73510214694987]
  We propose a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer's exact update from $mathcalO(D3)$ to $mathcalO(D2)$. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts.
  arXiv  Detail & Related papers  (2020-11-14T09:51:51Z)
• OneFlow: One-class flow for anomaly detection based on a minimal volume region [12.691473293758607]
  OneFlow is a flow-based one-class classifier for anomaly (outlier) detection. It is constructed in such a way that its result does not depend on the structure of outliers. The proposed model outperforms related methods on real-world anomaly detection problems.
  arXiv  Detail & Related papers  (2020-10-06T20:09:11Z)
• LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation [99.19322851246972]
  We introduce LiteFlowNet3, a deep network consisting of two specialized modules to address the problem of optical flow estimation. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
  arXiv  Detail & Related papers  (2020-07-18T03:30:39Z)
• SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds [15.476426879806134]
  Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. In this paper, we propose SoftFlow, a probabilistic framework for training normalizing flows on manifold. We experimentally show that SoftFlow can capture the innate structure of the manifold data and generate high-quality samples. We apply the proposed framework to 3D point clouds to alleviate the difficulty of forming thin structures for flow-based models.
  arXiv  Detail & Related papers  (2020-06-08T13:56:07Z)

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.