Wow I'm old, I still remember working with YOLOv2.
An Introduction to YOLO26
11–20 of 38 posts
Re: An Introduction to YOLO26
#12Was 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.
Re: An Introduction to YOLO26
#13Reminder that Ultralytics is pushing AGPL in a very overreaching way with their models that's why they are not available in Frigate
Re: An Introduction to YOLO26
#14One 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.
Re: An Introduction to YOLO26
#15Was 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 doe…
I would prefer GroundingDINo which is a sort of SAM and Dino combo which does open vocabulary.
Re: An Introduction to YOLO26
#16Is the license for this AGPL? Can someone please confirm?
Re: An Introduction to YOLO26
#17We'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.
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.
Re: An Introduction to YOLO26
#18We'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.
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)
Re: An Introduction to YOLO26
#19With 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?
Re: An Introduction to YOLO26
#20FWIW there are today many more alternatives with better license. Here is a good meta repo for object detection with different model variants: