Gemini 2.5 Pro and Qwen 2.5 VL for Object Detection | Benchmark LLMs for Vision Tasks with RF100-VL скачать в хорошем качестве

Gemini 2.5 Pro and Qwen 2.5 VL for Object Detection | Benchmark LLMs for Vision Tasks with RF100-VL

How do vision-language models (VLMs) perform on object detection tasks? In this video, Machine Learning Engineer Matvei Popov explores findings from research into the object detection capabilities of large, pre-trained VLMs like Gemini 2.5 Pro, Qwen 2.5 VL, GroundingDINO, and more. What you'll see: 00:00 Introduction: Do VLMs Struggle to Generalize on Object Detection Tasks? 03:28 Understanding Pre-Trained VLMs vs. Task-Specific Vision Models 04:54 Why Even Use VLMs for Object Detection? 09:48 Can We Leverage VLMs Pre-Training Data for Zero-Shot Detections? 12:18 Introducing RF100-VL: Object Detection Benchmark for VLMs 17:52 How to Evaluate Object Detection Capabilities in VLMs 21:46 Example: Comparing Evaluation Performance 25:34 Prompting Strategies for Object Detection Tests 30:10 Results! Comparing VLMs Object Detection Scores 37:43 Conclusion, Takeaways, and Looking Forward 💡 Learn more about RF100-VL: https://rf100-vl.org/