Completed
00:00 Introduction: Do VLMs Struggle to Generalize on Object Detection Tasks?
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Gemini 2.5 Pro and Qwen 2.5 VL for Object Detection - Benchmarking LLMs for Vision Tasks with RF100-VL
Automatically move to the next video in the Classroom when playback concludes
- 1 00:00 Introduction: Do VLMs Struggle to Generalize on Object Detection Tasks?
- 2 03:28 Understanding Pre-Trained VLMs vs. Task-Specific Vision Models
- 3 04:54 Why Even Use VLMs for Object Detection?
- 4 09:48 Can We Leverage VLMs Pre-Training Data for Zero-Shot Detections?
- 5 12:18 Introducing RF100-VL: Object Detection Benchmark for VLMs
- 6 17:52 How to Evaluate Object Detection Capabilities in VLMs
- 7 21:46 Example: Comparing Evaluation Performance
- 8 25:34 Prompting Strategies for Object Detection Tests
- 9 30:10 Results! Comparing VLMs Object Detection Scores
- 10 37:43 Conclusion, Takeaways, and Looking Forward
