Top Object Detection Models in 2023 | Model Selection Guide sponsored by Intel

Description:

Discover the top object detection models in 2023 in this comprehensive video. We compare models like YOLOv8, YOLOv7, RTMDet, DETA, DINO, and GroundingDINO based on metrics like Mean Average Precision, community support, packaging, and licensing for you to decide which is best for your production AI applications. The video also details the challenges in comparing model speed and highlights important nuances within the realm of object detection, like choosing the right model for the right hardware and use case. It's an essential watch for anyone interested in computer vision and model selection. This research was sponsored by Intel.

#ObjectDetection #ComputerVision

Chapters:

- 00:00 Introduction
- 00:35 Object Detection
- 01:42 Mean Average Precision
- 02:28 Speed
- 03:40 Paper, Packaging, and License
- 04:35 YOLOv8
- 05:21 YOLOv7
- 06:06 YOLOv6-v3
- 07:01 RTMDet
- 07:46 RT-DETR
- 08:50 DETA
- 10:02 GroundingDINO
- 10:37 Model Community Comparison
- 11:46 Conclusion

Resources:

Remember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀

[AlainPilon]

Thanks for the work! I am wondering if the COCO metric is actually useful. It is an interesting comparison point but I am not sure how it translates in practice given that most people only train detector for a very few set of classes. Community support, documentation and how the model integrates in the current ecosystem is much more impactful and I am glad you added these to your chart.

[rperezalejo]

Great video, right now I am working on a real time sport object detection and this video comes like a charm for me. I can test other posibilities I did not had in mind.

[juanolano]

Will go with Yolo8 for my current microbes identification project :) Thank you Piotr!

[satellite-image-deep-learning]

Fantastic summary, thank you for the effort that went into this! MMdetection has come up before and I would love an intro video on it 😊

[hawkingradiation]

would also like to see a video for comparison for segmentation tasks as well.

[johannesmokami]

Thanks for the info
I will definitely try them as well.

[fjzzmir]

I was looking for performance over the time inference for edge devices. I was trying to use Yolov8 for edge deployment into STM32 but at the end, i realized this model was too big for this card. What do you think is a good model for a good ratio between inference time / model size? Thanks for your response

[seanolivieri]

Do you have a video on licenses? I dont understand any of those and which one should I use if I want to be able to sell my program or call it my own

[Seethis-HD]

Excellent video. Thanks for the efforts. I was wondering why you didn't consider YOLO-NAS in the list?

[rxwdxnc]

can we use yolov8 pretrained weights for commercial use?

[EliSpizzichino]

We need a platform to fully compare them on real datasets on real training on the same device.
Is also important to keep track if a version change produce worsening quality. I've noticed for example that between one minor version and another of the ultralitics codebase the quality of the final trained model worsened by a lot.

[pleison]

I have a question, I am working on a OCR project, I am using a fastrcnn with resnet50 as object detector, and then I need something like a conv + GRU or ViT to decode the text, do you have some suggestions regarding OCR?

[shubh]

I am doing an object detection task and get 97.4% accuracy on the dataset using yolov5 and will be running it on an edge device. Is yolov5 too old and Should I train a yolov8 model for faster inference? As I think accuracy will be almost similar as it’s already 97.4%. Or is it task specific. If yolov5 is performing good then is there any need to change. If anyone can suggest please

[zskater]

I’m currently porting GroundingDINO to the transformers library so buckle up

[tyronetyrone]

Which framework is better to use in embedded chips?

[satyajitpanigrahy]

Kindly, Update the ultralytics package for YOLOv4 model

[eck]

Where is DETA video? Couldn't find DETA with 100k stars... Could you please add github link here.

[titusfx]

In 2:28 why not just do asymptotic analysis (computational complexity analysis).

[sanchaythalnerkar]

Can you show actual code and real time comparison of these?

[eck]

Found only DETA with 198 stars, not 100k like in your table...