▲esquire_9005 hours ago
[-] We've been running YOLO for a number of years (since v5) on soccer videos. None of the recent iterations have been significantly better, with v26 scoring worse then v9 and v11 on our tasks. Makes me wonder why this version is being pushed by roboflow and ultralytics.
reply▲Can't speak for 26, but a year ago I worked on a project that migrated from v5 to 11 because of improved image segmentation capabilities. My understanding is that the newer versions don't necessarily have better precision/recall, but they tend to be faster for equivalent results, and have increased capabilities.
reply▲teruakohatu4 hours ago
[-] When I was working with YOLO models it did seem like there was little practical improvements were between all of the spinoff models. It seemed people were pushing new models for personal recognition since the original creator stopped working on it.
That said, many of the claimed improvements in this model were are efficiency related.
What I find cool is not the model in itself, but the architectures / training methods found that make the model better. It gives out a new possibilites for other fields of AI. (Notably if you want to fine tune other CV models)
reply▲The original YOLO author has long quit due to ethical reasons.
reply▲Despite having a very memorable paper on the topic I believe they now work at Ai2.
reply▲Was evaluating YOLO26 within the last month for its on-device (iPhone 16 Pro) segmentation capabilities. Its decent, but its biggest limitation is that its only trained on 80 COCO classes (meaning pre-labeled images). If whatever is in your images isn't in the 80 classes, its invisible to YOLO26.
Conversely I have SAM2 running on-device and its my current workhorse. The biggest benefit with SAM2 for me is that it does fine-grained segmentation masks but isn't trained on labeled images. This was a specific requirement for the app I'm building. SAM2 isn't anywhere as speedy as the native Vision framework apis, but it is more capable across a vastly wider array of potential image targets.
reply▲I would prefer GroundingDINo which is a sort of SAM and Dino combo which does open vocabulary.
reply▲Doesn't work for my use-case. GroundingDINO is a text to bounding box model. SAM2 supports coordinate based masks (user taps or clicks somewhere in an image), which is what my research app needs.
reply▲alex_duf46 minutes ago
[-] I'm sure the model is capable, but I find it funny that the sample image that contains three bears gets detected as two elephants.
reply▲I found that while CLIPSeg is slower than YOLOn, it is still pretty fast and if gave me much much better results without training.
If you want to detect objects and speed is important so you can’t use a LLM architecture, you can give it a try too.
Can it measure the speed of a car on a video ?
reply▲Same question, same answer: In pixels/second? Sure!
What are you trying to accomplish by those questions? Are you genuinely asking, or just baiting? If the former, didnt answers to your previous question make it clear that your question makes less sense than you might assume?
One thing I don’t get I why the article is credited to ‘Contributing Author’.
Meanwhile their very own Peter Skalski already does super job with host write ups and examples of all YOLO sorts and is well respected.
Wow I'm old, I still remember working with YOLOv2.
reply▲With some previous versions of YOLO I‘ve found pages that run it in real-time locally on your browser, analyzing the webcam.
Is there a demo like that available for YOLO26?
I am curious why there is no desire to produce a paper showcasing key details.
reply▲Just a reminder that RF-DETR is better than yolo26
reply▲Ive used YOLO26 in one of my projects, It was very easy to train on our custom dataset and also very easy to deploy even on rust with AVX2 support. This model is indeed fast and can be used for almost real time inference.
reply