YOLO-World: Real-Time, Zero-Shot Object Detection Explained

In this video, you’ll learn how to use YOLO-World, a cutting-edge zero-shot object detection model. We'll cover its speed, compare it to other models, and run a live code demo for image AND video analysis.

Chapters:

- 00:00 Intro
- 00:42 YOLO-World vs. Traditional Object Detectors: Speed and Accuracy
- 02:26 YOLO-World Architecture - prompt-then-detect
- 03:59 Setting Up and Running YOLO-World
- 05:33 Prompt Engineering and Detections Post-Processing
- 09:20 Video Processing with YOLO-World
- 13:16 Important Considerations for Using YOLO-World
- 15:08 Beyond the Basics: Advanced use cases and future potential
- 16:37 Outro

Resources:

[Sawaedo]

Great Video! I didn't have time to read the YOLO World paper completely, or even test it, but with the video I can understand a lot of its architecture, and it's performance! Thank you Peter for explaining in such a great way!

[abdshomad]

As always, the content is well delivered. Thank you for always share the knowledge 👍

[uttamdwivedi]

Great work !!! Could you provide a tutorial on how to train (finetune) this YOLO-World model on specific type of data?

[KarenWeissKarwei]

Great video, informative and understandable. Thank you!

[elvenkim]

Hi Pieter! Great delivery, love the final video on YOLO + SAM. May I check with you on how do we extract the coordinate of the bounding box?

[sumukharaghavanm]

Great solution for students
Thanks a lot!!!!

[Codewello]

Awesome as always! I have learned a lot from you, especially about supervision Also, I love the thumbnail.
You look like you're saying 'come at me, bro 😁😁

[nazaruddinnurcharis]

Good information, whether this Yolo can be used to detect objects in realtime using a camera?, because I am in a project to develop Yolo for use in realtime cameras that I plan to use on my farm to detect predators.

[froukehermens]

Can you use YOLO-world + SAM to annotate images for training a (faster) object detector? (or image segmentation - maybe even pose estimation?).

[richarddjarbeng]

Cool tutorial. I have 2 questions.

1. Is there a list of classes that the model can detect? For instance if I want to detect 'yellow tricycles' but I am not sure if the model knows tricycles where can I check this.

2. How do you use this for semantic segmentation? You showed this briefly for the suitcases and croissants but you didn't go into the details.

[nidalidais]

hi man, good work, what the difference between YOLO-World and T-REX model, and how to compare between models usually

[misaeldavidlinareswarthon]

Impressive !!!! ... I have a quiestion
So for maximun speed I still have to use Yolov8 or yolo-world have less latency with coustom dataset

[qwikfacts]

Thank you for the video. I learnt a lot. I am just beginning my journey of object detection. If you have a minute to give me some direction, this is what I want to achieve. I want to develop object detection to be able to identify plumbing parts. sometimes they look quite similar. I want to be able to identify the same part in 3-4 different sizes (25mm, 32mm, 40mm) and for the object detection to tell me the part number for different size. Second phase. If I show the camera 3 of one size and 2 of another size, then I want it to tell me that i have 3 of part number XYZ and 2 of ABC. Thank you. I appreciate any guidance on how to go about it. Ideally, I won't have to train the model and I can use the zero-shot model. I am a novice but I am determined to teach myself. I will give your video instructions a try now to see how I go! Thank you

[jimshtepa]

have you done any video on training a model for custom dataset?

[develop]

Thank you for the video! I have a question. What do you call the technology that uses YOLO-world + Efficient SAM in the back of the video to switch from detection to segmentation along the baseline? Or is there a way to implement it?

[avamaeva]

This is a game changer, but it needs to work on mobile to be of real use in my setting? Two questions please:

1 - Can quantizisation be used on this model to make it much quicker, perhaps to a level where it will work in real time (at least 10fps) on state of the art phones (eg iPhone 15)?

2 - Can the model be run through the TFLite Converter? If not, any ideas whether that facility might be introduced?

Many Thanks

[nourabdou]

Thank you, very informative. I've a question regarding the prompts, Does it support and understands things like "Red Zones" or "Grey Areas" ?
I've tried to use it on maps and I was trying to identify grey areas or red areas but it doesn't work. Is there any workaround? thank you again!

[vipulpardeshi]

Hey, I just want to know, Is there any method to use Roboflow models on Offline Projects . Because by using API inferencing is very slow and I want fast detections.Is there any way to save the model .pt file and use it later without alsways importing Roboflow workspace. Thanks❤

[iconolk]

I want to use this project. It works on the hugging face, but strangely it doesn't fit my environment, it doesn't work on my PC.
I want to "clone" that on the hugging face, is there a way?

[rajeshktym]

Hi, is it a good suggestion to use YOLO-World for apple grade detection? A global shutter 2MP camera will capture 5 apples in the same position in a single frame (apple cup conveyor with trigger). We need to find bounding box of each apple and the classification result like grade A or grade B. What may be the maximum time required to obtain grade and boundary box information for each apple using jetson Nano.