Regularized Vector Quantization for Tokenized Image Synthesis

• URL: http://arxiv.org/abs/2303.06424v2
• Date: Sat, 14 Oct 2023 06:17:12 GMT
• Title: Regularized Vector Quantization for Tokenized Image Synthesis
• Authors: Jiahui Zhang, Fangneng Zhan, Christian Theobalt, Shijian Lu
• Abstract summary: Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while quantization suffers from low codebook utilization and reconstruction objective. This paper presents a regularized vector quantization framework that allows to mitigate perturbed above issues effectively by applying regularization from two perspectives.
• Score: 126.96880843754066
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. Predominant approaches learn the discrete representation either in a deterministic manner by selecting the best-matching token or in a stochastic manner by sampling from a predicted distribution. However, deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while stochastic quantization suffers from low codebook utilization and perturbed reconstruction objective. This paper presents a regularized vector quantization framework that allows to mitigate above issues effectively by applying regularization from two perspectives. The first is a prior distribution regularization which measures the discrepancy between a prior token distribution and the predicted token distribution to avoid codebook collapse and low codebook utilization. The second is a stochastic mask regularization that introduces stochasticity during quantization to strike a good balance between inference stage misalignment and unperturbed reconstruction objective. In addition, we design a probabilistic contrastive loss which serves as a calibrated metric to further mitigate the perturbed reconstruction objective. Extensive experiments show that the proposed quantization framework outperforms prevailing vector quantization methods consistently across different generative models including auto-regressive models and diffusion models.

Related papers

• Quantization of Large Language Models with an Overdetermined Basis [73.79368761182998]
  We introduce an algorithm for data quantization based on the principles of Kashin representation. Our findings demonstrate that Kashin Quantization achieves competitive or superior quality in model performance.
  arXiv  Detail & Related papers  (2024-04-15T12:38:46Z)
• On Uniform Scalar Quantization for Learned Image Compression [17.24702997651976]
  We find two factors crucial: the discrepancy between the surrogate and rounding, leading to train-test mismatch, and gradient estimation risk due to the surrogate. Our analyses enlighten us as to two subtle tricks: one is to set an appropriate lower bound for the variance of the estimated quantized latent distribution, which effectively reduces the train-test mismatch. Our method with the tricks is verified to outperform the existing practices of quantization surrogates on a variety of representative image compression networks.
  arXiv  Detail & Related papers  (2023-09-29T08:23:36Z)
• Towards Accurate Post-training Quantization for Diffusion Models [73.19871905102545]
  We propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Our method outperforms the state-of-the-art post-training quantization of diffusion model by a sizable margin with similar computational cost.
  arXiv  Detail & Related papers  (2023-05-30T04:00:35Z)
• Bayesian Quantification with Black-Box Estimators [1.599072005190786]
  Approaches like adjusted classify and count, black-box shift estimators, and invariant ratio estimators use an auxiliary (and potentially biased) black-box classifier to estimate the class distribution and yield guarantees under weak assumptions. We demonstrate that all these algorithms are closely related to the inference in a particular Bayesian Chain model, approxing the assumed ground-truthgenerative process. Then, we discuss an efficient Markov Monte Carlo sampling scheme for the introduced model and show an consistency guarantee in the large-data limit.
  arXiv  Detail & Related papers  (2023-02-17T22:10:04Z)
• On double-descent in uncertainty quantification in overparametrized models [24.073221004661427]
  Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. We show a trade-off between classification accuracy and calibration, unveiling a double descent like behavior in the calibration curve of optimally regularized estimators. This is in contrast with the empirical Bayes method, which we show to be well calibrated in our setting despite the higher generalization error and overparametrization.
  arXiv  Detail & Related papers  (2022-10-23T16:01:08Z)
• Fast Estimation of Bayesian State Space Models Using Amortized Simulation-Based Inference [0.0]
  This paper presents a fast algorithm for estimating hidden states of Bayesian state space models. After pretraining, finding the posterior distribution for any dataset takes from hundredths to tenths of a second.
  arXiv  Detail & Related papers  (2022-10-13T16:37:05Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Deblurring via Stochastic Refinement [85.42730934561101]
  We present an alternative framework for blind deblurring based on conditional diffusion models. Our method is competitive in terms of distortion metrics such as PSNR.
  arXiv  Detail & Related papers  (2021-12-05T04:36:09Z)
• A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors [60.489902135153415]
  This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement.
  arXiv  Detail & Related papers  (2021-11-26T06:33:29Z)

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.