MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917628392505344 |
|---|---|
| author | Tian, Changyao Zhu, Xizhou Xiong, Yuwen Wang, Weiyun Chen, Zhe Wang, Wenhai Chen, Yuntao Lu, Lewei Lu, Tong Zhou, Jie Li, Hongsheng Qiao, Yu Dai, Jifeng |
| author_facet | Tian, Changyao Zhu, Xizhou Xiong, Yuwen Wang, Weiyun Chen, Zhe Wang, Wenhai Chen, Yuntao Lu, Lewei Lu, Tong Zhou, Jie Li, Hongsheng Qiao, Yu Dai, Jifeng |
| contents | Developing generative models for interleaved image-text data has both research and practical value. It requires models to understand the interleaved sequences and subsequently generate images and text. However, existing attempts are limited by the issue that the fixed number of visual tokens cannot efficiently capture image details, which is particularly problematic in the multi-image scenarios. To address this, this paper presents MM-Interleaved, an end-to-end generative model for interleaved image-text data. It introduces a multi-scale and multi-image feature synchronizer module, allowing direct access to fine-grained image features in the previous context during the generation process. MM-Interleaved is end-to-end pre-trained on both paired and interleaved image-text corpora. It is further enhanced through a supervised fine-tuning phase, wherein the model improves its ability to follow complex multi-modal instructions. Experiments demonstrate the versatility of MM-Interleaved in recognizing visual details following multi-modal instructions and generating consistent images following both textual and visual conditions. Code and models are available at \url{https://github.com/OpenGVLab/MM-Interleaved}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10208 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer Tian, Changyao Zhu, Xizhou Xiong, Yuwen Wang, Weiyun Chen, Zhe Wang, Wenhai Chen, Yuntao Lu, Lewei Lu, Tong Zhou, Jie Li, Hongsheng Qiao, Yu Dai, Jifeng Computer Vision and Pattern Recognition Computation and Language Developing generative models for interleaved image-text data has both research and practical value. It requires models to understand the interleaved sequences and subsequently generate images and text. However, existing attempts are limited by the issue that the fixed number of visual tokens cannot efficiently capture image details, which is particularly problematic in the multi-image scenarios. To address this, this paper presents MM-Interleaved, an end-to-end generative model for interleaved image-text data. It introduces a multi-scale and multi-image feature synchronizer module, allowing direct access to fine-grained image features in the previous context during the generation process. MM-Interleaved is end-to-end pre-trained on both paired and interleaved image-text corpora. It is further enhanced through a supervised fine-tuning phase, wherein the model improves its ability to follow complex multi-modal instructions. Experiments demonstrate the versatility of MM-Interleaved in recognizing visual details following multi-modal instructions and generating consistent images following both textual and visual conditions. Code and models are available at \url{https://github.com/OpenGVLab/MM-Interleaved}. |
| title | MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2401.10208 |