StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond

• URL: http://arxiv.org/abs/2405.21013v3
• Date: Tue, 4 Jun 2024 09:14:39 GMT
• Title: StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
• Authors: Pengyuan Lyu, Yulin Li, Hao Zhou, Weihong Ma, Xingyu Wan, Qunyi Xie, Liang Wu, Chengquan Zhang, Kun Yao, Errui Ding, Jingdong Wang,
• Abstract summary: We have crafted an efficient vision-language model, StrucTexTv3, tailored to tackle various intelligent tasks for text-rich images. We enhance the perception and comprehension abilities of StrucTexTv3 through instruction learning. Our method achieved SOTA results in text-rich image perception tasks, and significantly improved performance in comprehension tasks.
• Score: 68.0107158115377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images play crucial roles in information transmission but are accompanied by diverse challenges. Therefore, the efficient and effective understanding of text-rich images is a crucial litmus test for the capability of Vision-Language Models. We have crafted an efficient vision-language model, StrucTexTv3, tailored to tackle various intelligent tasks for text-rich images. The significant design of StrucTexTv3 is presented in the following aspects: Firstly, we adopt a combination of an effective multi-scale reduced visual transformer and a multi-granularity token sampler (MG-Sampler) as a visual token generator, successfully solving the challenges of high-resolution input and complex representation learning for text-rich images. Secondly, we enhance the perception and comprehension abilities of StrucTexTv3 through instruction learning, seamlessly integrating various text-oriented tasks into a unified framework. Thirdly, we have curated a comprehensive collection of high-quality text-rich images, abbreviated as TIM-30M, encompassing diverse scenarios like incidental scenes, office documents, web pages, and screenshots, thereby improving the robustness of our model. Our method achieved SOTA results in text-rich image perception tasks, and significantly improved performance in comprehension tasks. Among multimodal models with LLM decoder of approximately 1.8B parameters, it stands out as a leader, which also makes the deployment of edge devices feasible. In summary, the StrucTexTv3 model, featuring efficient structural design, outstanding performance, and broad adaptability, offers robust support for diverse intelligent application tasks involving text-rich images, thus exhibiting immense potential for widespread application.

Related papers

• Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks [62.758680527838436]
  Leopard is a vision-language model for handling vision-language tasks involving multiple text-rich images. First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios. Second, we developed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length.
  arXiv  Detail & Related papers  (2024-10-02T16:55:01Z)
• LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models [60.67899965748755]
  We present LLaVA-Read, a multimodal large language model that utilizes dual visual encoders along with a visual text encoder. Our research suggests visual text understanding remains an open challenge and an efficient visual text encoder is crucial for future successful multimodal systems.
  arXiv  Detail & Related papers  (2024-07-27T05:53:37Z)
• VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models [76.94378391979228]
  We introduce a new, more demanding task known as Interleaved Image-Text (IITC) This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA)
  arXiv  Detail & Related papers  (2024-06-14T17:59:40Z)
• TRINS: Towards Multimodal Language Models that Can Read [61.17806538631744]
  TRINS is a Text-Rich image INStruction dataset. It contains 39,153 text-rich images, captions, and 102,437 questions. We introduce a Language-vision Reading Assistant (LaRA) which is good at understanding textual content within images.
  arXiv  Detail & Related papers  (2024-06-10T18:52:37Z)
• InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition [111.65584066987036]
  InternLM-XComposer is a vision-language large model that enables advanced image-text comprehension and composition. It can effortlessly generate coherent and contextual articles that seamlessly integrate images. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates.
  arXiv  Detail & Related papers  (2023-09-26T17:58:20Z)

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.