• 6 min read
Vision Token Counts: What does it cost to process an image with a frontier vision model?
Understand the cost, per-provider tokenization rules, and a comparison across image sizes for Claude, GPT, and Gemini.
• 5 min read
AI Swimmer Tracking
Learn how to build an automated aquatic monitoring pipeline using RF-DETR and ByteTrack in Roboflow.
• 17 min read
Detecting Road Defects with Computer Vision
This tutorial shows how to build an automated road defect detection system using Roboflow with deployment strategies for UAV imagery and dashcam video, each generating structured inspection reports automatically.
• 8 min read
AI Crop Analysis with Roboflow
Learn how to combine RF-DETR and Claude Sonnet 4.5 in Roboflow Workflows to detect plant diseases.
• 9 min read
Trading Card Inventory Management with AI
Learn how to build an automated TCG inventory pipeline using RF-DETR and Gemini 2.5 Flash to extract card details and market values.
• 4 min read
Serverless GPU Inference Cost Comparison: Roboflow, GCP, AWS, Azure
In this blog post, we will explore how different cloud providers compare in running custom vision model inference.
Custom RF-DETR Model
If you need OCR, face detection/comparison, or general-purpose COCO-20 classification and detection, the major clouds already offer plenty of managed options, such as AWS Rekognition, GCP Vision, and
• 21 min read
DINOv3: An Advanced Self-Supervised Vision Foundation Model by Meta
Explore Meta's DINOv3, the state-of-the-art self-supervised vision foundation model. Learn how its SSL architecture works and how to train it on Roboflow.
• 10 min read
Automate Surgical Instrument Tracking with Computer Vision
See how to build a surgical instrument closing-count assistant with Roboflow.
• 8 min read
High-Precision OCR for Medical Device Labeling with RF-DETR and Gemini 2.5 Flash
Learn how to build a two-stage Vision Agent using RF-DETR and Gemini 2.5 Flash for medical device labeling.
• 7 min read
Turning Any Screen Into a Touchless Display with Egocentric Hand Keypoint Detection
In this guide, we’re moving beyond the glass to build a first-person interaction system. Using Roboflow Inference 1.0, RF-DETR Nano, and MediaPipe, you’ll learn how to anchor a gesture space to a physical screen and translate hand landmarks into OS-level commands like zooming and scrolling.
• 13 min read
Zero-Shot Auto Labeling with VLMs using Roboflow
Learn how to use Vision-Language Models like Florence-2 in Roboflow to auto-label datasets faster for production-ready models.
• 8 min read
Detect Small Objects with Roboflow Workflows
Learn how to use Roboflow Workflows to detect small objects with a computer vision model and the SAHI inference technique.
• 4 min read
New RF-DETR Segmentation Checkpoints from Nano to 2XLarge
RF-DETR-Seg brings real-time instance segmentation to the same level RF-DETR already reached in object detection, with strong accuracy across a full range of model sizes from Nano to 2XLarge.
• 14 min read
AI for Aerial Imagery: RF-DETR Delivers Best-in-Class Speed and Accuracy
Learn how models like RF-DETR deliver better accuracy when analyzing aerial imagery, and find out how computer vision is transforming operations across various sectors, including energy, industrial infrastructure, and defense.
• 9 min read
How to Train an RF-DETR Segmentation Model with a Custom Dataset
Learn how to train an RF-DETR Segmentation model with a custom dataset.
• 30 min read
Best Mobile Object Detection Models
Discover some of the best mobile object detection models, and how to easily build iOS app with Roboflow iOS SDK.
• 6 min read
How to Label and Train Instance Segmentation Data with RF-DETR
Instance segmentation lets AI models identify and outline each object in an image with pixel-perfect precision. In this tutorial, learn how to label segmentation data, and train a high-accuracy RF-DETR model.
• 8 min read
SOTA Instance Segmentation with RF-DETR
Today, we are excited to announce that we are expanding RF-DETR to support instance segmentation with the launch of RF-DETR Seg (Preview).
• 14 min read
What Is Neural Architecture Search (NAS)?
In this blog you will understand what is Neural Architecture Search (NAS), main components of NAS systems, How NAS works, what are the types of search spaces and strategies in NAS and why NAS is useful.
• 9 min read
How to Build an iOS App with Visual AI Capabilities
In this guide, we’ll walk through using a custom object detection model tailored to identify glasses and show you how to seamlessly integrate it into an iOS app for instant live detection — all with minimal latency and maximum convenience.
0:00
/0:13
1×
Millions of people rely on
• 5 min read
Advancing State of the Art Object Detection (Again) with RF-DETR
Learn how to use and train the three new state-of-the-art RF-DETR object detection model sizes.
• 6 min read
How to Deploy RF-DETR to an NVIDIA Jetson
Learn how to deploy RF-DETR to a Roboflow Jetson.
• 7 min read
Launch: Train and Deploy RF-DETR Models with Roboflow
Learn how to train RF-DETR models with Roboflow Train and deploy RF-DETR models with Roboflow Workflows and Inference.
• 11 min read
How to Train RF-DETR on a Custom Dataset
Learn how to train an RF-DETR model on a custom dataset.
Stay Connected