YOLO-World: Real-Time Open-Vocabulary Object Detection
148 points by greesil 1 month ago | 52 comments- AndrewKemendo 1 month agoWe’ve tested this in our production environment on mobile robots (think quadcopter and ground UGV) and it works really nicely
- TechDebtDevin 1 month agoIf this is military related, im terrified of the future. Sci-fi movies with crazy drones from back when are no longer that cute.
- echelon 1 month ago7 years ago, this felt like science fiction:
https://www.youtube.com/watch?v=HipTO_7mUOw
Now that we've seen the use of drones in the Ukraine war, 10k+ drone light shows, Waymo's autonomous cars, and tons of AI advancements in signals processing and planning, this seems obvious.
- yard2010 1 month agoThis is important.
I don't want to live on this planet anymore.
- yard2010 1 month ago
- jiggawatts 1 month agoThe truly scary part is that it’s a straightforward evolution from this to 1000 fps hyperspectral sensors.
There will be no hiding from these things and no possibility of evasion.
They’ll have agility exceeding champion drone pilots and be too small to even see or hear until it’s far too late.
Life in the Donbass trenches is already hell. We’ll find a way to make it worse.
- MoonGhost 1 month agoThen it should be possible to use them to counter and defend. Think of AI powered interceptor drones patrolling the area, anti-drone light machine guns.
- MoonGhost 1 month ago
- AndrewKemendo 1 month agoYou’re right to be terrified
- echelon 1 month ago
- bevenky 1 month agoIs this OSS?
- fc417fc802 1 month agoUnclear exactly what you're asking. The linked paper describes an algorithm (patent status unclear). That paper happens to link to a GPL licensed implementation whose authors explicitly solicit business licensing inquiries. The related model weights are available on Hugging Face (license unclear). Notably the HF readme file contains conflicting claims. The metadata block specifies apache while the body specifies GPL.
https://github.com/AILab-CVC/YOLO-World
https://huggingface.co/spaces/stevengrove/YOLO-World/tree/ma...
- sigmoid10 1 month agoThe paper says it is based on YOLOv8, which uses the even stricter AGPL-3.0. That means you can use it commercially, but all derived code (even in a cloud service) must be made open source as well.
- jimmydoe 1 month agoDoes GPL still mean anything if you can ask AI to read from code A and reimplement into code B?
- sigmoid10 1 month ago
- T-A 1 month ago
- fc417fc802 1 month ago
- TechDebtDevin 1 month ago
- ed 1 month agoNeat. Wonder how this compares to Segment Anything (SAM), which also does zero-shot segmentation and performs pretty well in my experience.
- RugnirViking 1 month agoYOLO is way faster. We used to run both, with YOLO finding candidate bounding boxes and SAM segmenting just those.
For what it's worth, YOLO has been a standard in image processing for ages at this point, with dozens of variations on the algorithm (yolov3, yolov5, yolov6, etc) and this is yet another new one. Looks great tho
SAM wouldn't run under 1000ms per frame for most reasonable image sizes
- euazOn 1 month agoJust as a quick demo, here is an example of YOLO-World combined with EfficientSAM: https://youtu.be/X7gKBGVz4vs?t=980
- aunty_helen 1 month agoWe used mobile Sam because of this, was about 250ms on cpu. Useful for our use case
- euazOn 1 month ago
- ipsum2 1 month agoSAM doesn't do open vocabulary i.e. it segments things without knowing the name of the object, so you can't ask it to do "highlight the grapes", you have to give it an example of a grape first.
- stevepotter 1 month ago
- ipsum2 1 month agoThis uses GroundingDINO for open vocabulary, separate model. Useful nonetheless, but means you're running a lot of model inference for a single image.
- ipsum2 1 month ago
- 1 month ago
- stevepotter 1 month ago
- RugnirViking 1 month ago
- silentsea90 1 month agoQ. Any of you know models that do well at deleting objects from an image i.e. inpainting with mask with intention to replace mask with background? Whatever I've tried so far leaves a smudge (eg. LaMa)
- jokethrowaway 1 month agoYou can build a pipeline where you use: GroundingDino (description to object detection) -> SAM (segmenting) -> Stable Diffusion model (inpainting, I do mainly real photo so I like to start with realisticVisionV60B1_v51HyperVAE-inpainting and then swap if I have some special use case)
For higher quality at a higher cost of VRAM, you can also use Flux.1 Fill to do inpainting.
Lastly, Flux.1 Kontext [dev] is going to be released soon and it promises to replace the entire flow (and with better prompt understanding). HN thread here: https://news.ycombinator.com/item?id=44128322
- silentsea90 3 weeks agoThanks! I do use GroundingDino + SAM2, but haven't tried realisticVisionV60B1_v51HyperVAE-inpainting! Will do! And will try flux kontext too. Thanks!
- silentsea90 3 weeks ago
- GaggiX 1 month agoThere are plenty of Stable Diffusion based models that are capable of inpainting, of course they are heavier to run than LaMa.
- silentsea90 1 month agoMy question wasn't about inpainting but eraser inpainting models. Most inpainting models replace objects instead of erasing them even though the prompt shares an intent to delete
- silentsea90 1 month ago
- 1 month ago
- jokethrowaway 1 month ago
- greesil 1 month agoI've got big plans for this for an automated geese scaring system
- mattlondon 1 month agoSame here but for urban foxes.
We had motion triggered sprinklers that worked great, but they did not differentiate between foxes and 4 year old children if I forgot to turn them off haha.
We have more or less 360 degrees CCTV coverage of the garden via 7 or 8 CCTV cameras so rough plan is to have basic motion pixel detection to detect frames with something happening then fire those frames off for inference (rather than trying to stream all video feeds through the algorithm 24/7) and turn the sprinklers on. Hope to get to about 500ms end-to-end latency from detection to sprinklers/tap activated to cement the "causality" of stepping into the garden and then ~immediately getting soaked and scared in the foxes brains. Most latency will be for the water to physically move and make the sprinklers start, but that is another issue really.
Probably will use a RPi 5 + AI Hat as the main local inference provider, and ZigBee controlled valve solenoid on the hose tap.
- joshwa 1 month agoLikewise but for raccoons. Are you precision targeting or just broad sprinkler coverage? I need to make sure my cat doesn’t get hosed :-/
I got a cheap MLX90640 off aliexpress for target detection and a grove vision AI V2 module to use with IR cam for classification/object tracking. Esp32 for fusion and servo/solenoid actuation.
Collab?
- akshitgaur2005 1 month agoBrb, using this for the local tigers
- joshwa 1 month ago
- zachflower 1 month agoFunnily enough, that was my computer science capstone project back in 2010!
I don’t know if our project sponsor ever got the company off the ground, but the basic idea was an automated system to scare geese off of golf courses without also activating in the middle of someone’s backswing.
- greesil 1 month agoIf someone can sell it for $100 they'd make some serious money. The birds are fouling my pool, and the plastic owl does nothing. Right now I'm thinking it should make a loud noise, or launch a tennis ball randomly. The best part is I can have it disarm if it sees a person.
- joshwa 1 month agoMy thought is just to rent it out for to rich folks with lawns for a few hundred bucks a week. My contraption will have thermal detection, AI target discrimination, and precision targeting with a laminar flow water stream. That’s the plan, anyways.
- joshwa 1 month ago
- greesil 1 month ago
- 1 month ago
- mattlondon 1 month ago
- saithound 1 month agoNeeds (2024) in the title.
- pavl 1 month agoThis looks so good! Will it be available on replicate?
- jimmydoe 1 month agothis is one year old. wonder why post now.
- MoonGhost 1 month agoOld stuff is often reposted here to attract attention. It mostly goes unnoticed.
- MoonGhost 1 month ago
- serf 1 month agonot to be a grump, but why was this posted recently? Has something changed? Yolo-world has been around for a bit now.
- 3vidence 1 month agoThe setback of YOLO architectures is that they use predefined object categories that are a part of the training process. If you want to adapt YOLO to a new domain you need to retrain it with your new category label.
This work presents a version of YOLO that can work on new categories without needing to retrain the algorithm, but instead having a real-time "dictionary" of examples that you can seemlessly update. Seems like a very useful algorithm to me.
Edit: apologies i misread your comment I thought it was asking why this is different that regular YOLO
- greesil 1 month agoIt was new to me, serf. And judging by the number of upvotes, it was new to a few other people too.
- 1 month ago
- 3vidence 1 month ago