Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
में बचाया:
| में प्रकाशित: | arXiv.org (Mar 14, 2024), p. n/a |
|---|---|
| मुख्य लेखक: | |
| अन्य लेखक: | , , , , |
| प्रकाशित: |
Cornell University Library, arXiv.org
|
| विषय: | |
| ऑनलाइन पहुंच: | Citation/Abstract Full text outside of ProQuest |
| टैग: |
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2957595560 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2957595560 | ||
| 045 | 0 | |b d20240314 | |
| 100 | 1 | |a Zhan, Yufei | |
| 245 | 1 | |a Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring | |
| 260 | |b Cornell University Library, arXiv.org |c Mar 14, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpass the performance of task-specific experts in complex and dense scenarios. Such limitation further restricts the model's potential to achieve nuanced visual and language referring in domains such as GUI Agents, Counting and \etc. To address this issue, we introduce a unified high-resolution generalist model, Griffon v2, enabling flexible object referring with visual and textual prompts. To efficiently scaling up image resolution, we design a simple and lightweight down-sampling projector to overcome the input tokens constraint in Large Language Models. This design inherently preserves the complete contexts and fine details, and significantly improves multimodal perception ability especially for small objects. Building upon this, we further equip the model with visual-language co-referring capabilities through a plug-and-play visual tokenizer. It enables user-friendly interaction with flexible target images, free-form texts and even coordinates. Experiments demonstrate that Griffon v2 can localize any objects of interest with visual and textual referring, achieve state-of-the-art performance on REC, phrase grounding, and REG tasks, and outperform expert models in object detection and object counting. Data, codes and models will be released at https://github.com/jefferyZhan/Griffon. | |
| 653 | |a Language | ||
| 653 | |a Perception | ||
| 653 | |a Image resolution | ||
| 653 | |a Large language models | ||
| 653 | |a Constraint modelling | ||
| 653 | |a Object recognition | ||
| 653 | |a Free form | ||
| 653 | |a High resolution | ||
| 700 | 1 | |a Zhu, Yousong | |
| 700 | 1 | |a Zhao, Hongyin | |
| 700 | 1 | |a Yang, Fan | |
| 700 | 1 | |a Tang, Ming | |
| 700 | 1 | |a Wang, Jinqiao | |
| 773 | 0 | |t arXiv.org |g (Mar 14, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2957595560/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2403.09333 |