Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Regularized Vector Quantization for Tokenized Image Synthesis

About

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.

Jiahui Zhang, Fangneng Zhan, Christian Theobalt, Shijian Lu• 2023

Related benchmarks

TaskDatasetResultRank
Image ReconstructionCelebA-HQ (test)
FID (Reconstruction)10.09
50
Semantic Image SynthesisADE20K (val)
FID34.47
47
Text-to-Image SynthesisCUB-200-2011 (test)--
20
Semantic SynthesisCelebA-HQ
FID15.34
10
Text-to-Image SynthesisMS-COCO 2017 (test)
FID19.91
7
Image ReconstructionADE20K semantic labels (val)
FID (Reconstruction)23.69
4
Image ReconstructionCUB-200 (test)
FID (Reconstruction)10.84
4
Image ReconstructionMS-COCO 2017 (test)
FID13.76
4
Semantic Image SynthesisCelebA-HQ (test)
FID (G)15.34
4
Showing 9 of 9 rows

Other info

Follow for update