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

Zisheng Chen, Chunwei Wang, Runhui Huang, Hongbin Xu, Xiuwei Chen, Jun Zhou, Jianhua Han, Hang Xu, Xiaodan Liang

Keywords: unified image tokenizer, multimodal learning

TL;DR: This paper introduces a unified image tokenizer, named SemHiTok, which achieve a better trade-off between semantic information and texture information, and obtains competitive performance on the unified MLLM based on this training.

Abstract:

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.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 2345