SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Zisheng, Wang, Chunwei, Huang, Runhui, Xu, Hongbin, Chen, Xiuwei, Zhou, Jun, Han, Jianhua, Xu, Hang, Liang, Xiaodan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918360474714112
author Chen, Zisheng
Wang, Chunwei
Huang, Runhui
Xu, Hongbin
Chen, Xiuwei
Zhou, Jun
Han, Jianhua
Xu, Hang
Liang, Xiaodan
author_facet Chen, Zisheng
Wang, Chunwei
Huang, Runhui
Xu, Hongbin
Chen, Xiuwei
Zhou, Jun
Han, Jianhua
Xu, Hang
Liang, Xiaodan
contents In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understanding and generation. Recently, unified image tokenizers have sparked exploration within the research community, which is designed to capture high-level semantic features for understanding and retaining low-level pixel features for generation. Previous works attempt to train a unified image tokenizer by combining loss for semantic distillation and pixel reconstruction. However, due to the differing levels of features prioritized by multimodal understanding and generation, joint training methods face significant challenges in achieving a good trade-off. SemHiTok addresses this challenge through a novel semantic-guided hierarchical codebook, which builds pixel sub-codebooks on a pretrained semantic codebook. This design decouples the semantic and pixel in terms of structure and training strategy, enabling the tokenizer to capture pixel features while retaining its ability to comprehend high-level semantic information. Our experiments demonstrate that SemHiTok achieves leading performance in image reconstruction and multimodal understanding under the LLaVA-v1.5 setting. Further, we develop a unified MLLM with SemHiTok, which exhibits superior performance across multimodal understanding and generation tasks. Extensive experiments confirm our analysis, showing that our unified image tokenizer architecture achieves a better trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation
Chen, Zisheng
Wang, Chunwei
Huang, Runhui
Xu, Hongbin
Chen, Xiuwei
Zhou, Jun
Han, Jianhua
Xu, Hang
Liang, Xiaodan
Computer Vision and Pattern Recognition
Artificial Intelligence
In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understanding and generation. Recently, unified image tokenizers have sparked exploration within the research community, which is designed to capture high-level semantic features for understanding and retaining low-level pixel features for generation. Previous works attempt to train a unified image tokenizer by combining loss for semantic distillation and pixel reconstruction. However, due to the differing levels of features prioritized by multimodal understanding and generation, joint training methods face significant challenges in achieving a good trade-off. SemHiTok addresses this challenge through a novel semantic-guided hierarchical codebook, which builds pixel sub-codebooks on a pretrained semantic codebook. This design decouples the semantic and pixel in terms of structure and training strategy, enabling the tokenizer to capture pixel features while retaining its ability to comprehend high-level semantic information. Our experiments demonstrate that SemHiTok achieves leading performance in image reconstruction and multimodal understanding under the LLaVA-v1.5 setting. Further, we develop a unified MLLM with SemHiTok, which exhibits superior performance across multimodal understanding and generation tasks. Extensive experiments confirm our analysis, showing that our unified image tokenizer architecture achieves a better trade-off.
title SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.06764