Attentive Contractive Flow with Lipschitz-constrained Self-Attention

• URL: http://arxiv.org/abs/2109.12135v4
• Date: Wed, 6 Sep 2023 07:17:01 GMT
• Title: Attentive Contractive Flow with Lipschitz-constrained Self-Attention
• Authors: Avideep Mukherjee, Badri Narayan Patro, Vinay P. Namboodiri
• Abstract summary: We introduce a novel approach called Attentive Contractive Flow (ACF) ACF utilizes a special category of flow-based generative models - contractive flows. We demonstrate that ACF can be introduced into a variety of state of the art flow models in a plug-and-play manner.
• Score: 25.84621883831624
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normalizing flows provide an elegant method for obtaining tractable density estimates from distributions by using invertible transformations. The main challenge is to improve the expressivity of the models while keeping the invertibility constraints intact. We propose to do so via the incorporation of localized self-attention. However, conventional self-attention mechanisms don't satisfy the requirements to obtain invertible flows and can't be naively incorporated into normalizing flows. To address this, we introduce a novel approach called Attentive Contractive Flow (ACF) which utilizes a special category of flow-based generative models - contractive flows. We demonstrate that ACF can be introduced into a variety of state of the art flow models in a plug-and-play manner. This is demonstrated to not only improve the representation power of these models (improving on the bits per dim metric), but also to results in significantly faster convergence in training them. Qualitative results, including interpolations between test images, demonstrate that samples are more realistic and capture local correlations in the data well. We evaluate the results further by performing perturbation analysis using AWGN demonstrating that ACF models (especially the dot-product variant) show better and more consistent resilience to additive noise.

Related papers

• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling [49.46842536813477]
  We propose a novel data augmentation approach, DistractFlow, for training optical flow estimation models. We combine one of the frames in the pair with a distractor image depicting a similar domain, which allows for inducing visual perturbations congruent with natural objects and scenes. Our approach allows increasing the number of available training pairs significantly without requiring additional annotations.
  arXiv  Detail & Related papers  (2023-03-24T15:42:54Z)
• 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)
• Distilling the Knowledge from Normalizing Flows [22.578033953780697]
  Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. We propose a simple distillation approach and demonstrate its effectiveness on state-of-the-art conditional flow-based models for image super-resolution and speech synthesis.
  arXiv  Detail & Related papers  (2021-06-24T00:10:22Z)
• Generative Flows with Invertible Attentions [135.23766216657745]
  We introduce two types of invertible attention mechanisms for generative flow models. We exploit split-based attention mechanisms to learn the attention weights and input representations on every two splits of flow feature maps. Our method provides invertible attention modules with tractable Jacobian determinants, enabling seamless integration of it at any positions of the flow-based models.
  arXiv  Detail & Related papers  (2021-06-07T20:43:04Z)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models [11.206144910991481]
  We propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of sampling and evaluation of a lower bound on the likelihood. We demonstrate state-of-the-art performance on standard benchmarks of flow-based generative modeling.
  arXiv  Detail & Related papers  (2020-02-17T17:45:48Z)
• Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow [16.41460104376002]
  We introduce subset flows, a class of flows that can transform finite volumes and allow exact computation of likelihoods for discrete data. We identify ordinal discrete autoregressive models, including WaveNets, PixelCNNs and Transformers, as single-layer flows. We demonstrate state-of-the-art results on CIFAR-10 for flow models trained with dequantization.
  arXiv  Detail & Related papers  (2020-02-06T22:58:51Z)

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.