Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.12488 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913441246085120 |
|---|---|
| author | Wu, Yixuan Wang, Yizhou Tang, Shixiang Wu, Wenhao He, Tong Ouyang, Wanli Torr, Philip Wu, Jian |
| author_facet | Wu, Yixuan Wang, Yizhou Tang, Shixiang Wu, Wenhao He, Tong Ouyang, Wanli Torr, Philip Wu, Jian |
| contents | We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. Specifically, the prompts in the toolkit are designed to guide the MLLM to focus on regional information (e.g., zooming in), read coordinates according to measure standards (e.g., overlaying rulers and compasses), and infer from the contextual information (e.g., overlaying scene graphs). Building upon these tools, the new detection chain-of-thought can automatically decompose the task into simple subtasks, diagnose the predictions, and plan for progressive box refinements. The effectiveness of our framework is demonstrated across a spectrum of detection tasks, especially hard cases. Compared to existing state-of-the-art methods, GPT-4V with our DetToolChain improves state-of-the-art object detectors by +21.5% AP50 on MS COCO Novel class set for open-vocabulary detection, +24.23% Acc on RefCOCO val set for zero-shot referring expression comprehension, +14.5% AP on D-cube describe object detection FULL setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12488 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM Wu, Yixuan Wang, Yizhou Tang, Shixiang Wu, Wenhao He, Tong Ouyang, Wanli Torr, Philip Wu, Jian Computer Vision and Pattern Recognition Artificial Intelligence We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. Specifically, the prompts in the toolkit are designed to guide the MLLM to focus on regional information (e.g., zooming in), read coordinates according to measure standards (e.g., overlaying rulers and compasses), and infer from the contextual information (e.g., overlaying scene graphs). Building upon these tools, the new detection chain-of-thought can automatically decompose the task into simple subtasks, diagnose the predictions, and plan for progressive box refinements. The effectiveness of our framework is demonstrated across a spectrum of detection tasks, especially hard cases. Compared to existing state-of-the-art methods, GPT-4V with our DetToolChain improves state-of-the-art object detectors by +21.5% AP50 on MS COCO Novel class set for open-vocabulary detection, +24.23% Acc on RefCOCO val set for zero-shot referring expression comprehension, +14.5% AP on D-cube describe object detection FULL setting. |
| title | DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.12488 |