OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression

by   Chen Zhang, et al.

Explicit deep generative models (DGMs), e.g., VAEs and Normalizing Flows, have shown to offer an effective data modelling alternative for lossless compression. However, DGMs themselves normally require large storage space and thus contaminate the advantage brought by accurate data density estimation. To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch. We formalise this setting as that of One-Shot Online Adaptation (OSOA) of DGMs for lossless compression and propose a vanilla algorithm under this setting. Experimental results show that vanilla OSOA can save significant time versus training bespoke models and space versus using one model for all targets. With the same adaptation step number or adaptation time, it is shown vanilla OSOA can exhibit better space efficiency, e.g., 47% less space, than fine-tuning the pretrained model and saving the fine-tuned model. Moreover, we showcase the potential of OSOA and motivate more sophisticated OSOA algorithms by showing further space or time efficiency with multiple updates per batch and early stopping.


page 9

page 20


DOI: Divergence-based Out-of-Distribution Indicators via Deep Generative Models

To ensure robust and reliable classification results, OoD (out-of-distri...

Rewriting a Deep Generative Model

A deep generative model such as a GAN learns to model a rich set of sema...

Bias and Generalization in Deep Generative Models: An Empirical Study

In high dimensional settings, density estimation algorithms rely crucial...

Securing Deep Generative Models with Universal Adversarial Signature

Recent advances in deep generative models have led to the development of...

Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation

Adapting a neural text-to-speech (TTS) model to a target speaker typical...

One-Shot Generalization in Deep Generative Models

Humans have an impressive ability to reason about new concepts and exper...

Please sign up or login with your details

Forgot password? Click here to reset