Please turn JavaScript on
Roboflow Blog icon

Roboflow Blog

follow.it gives you an easy way to subscribe to Roboflow Blog's news feed! Click on Follow below and we deliver the updates you want via email, phone or you can read them here on the website on your own news page.

You can also unsubscribe anytime painlessly. You can even combine feeds from Roboflow Blog with other site's feeds!

Title: Roboflow Blog

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.45 / day

Message History

ResNet is a family of convolutional neural networks that uses skip connections to train very deep models. This guide explains how residual blocks work and how ResNet-18 to ResNet-152 compare. It also shows where ResNet fits today and how to train and deploy it in Roboflow.

Read full story

LLMs with vision support (VLMs) are getting good at recognizing objects, drawing boxes around them, and outlining their shapes.

For example, GPT-6 Astra can find hot spots in a thermal image of solar panels. But turning those predictions into an inspection system take...


Read full story

Roboflow is building the visual cortex for artificial intelligence.

Every day, millions of developers around the globe and over half of the Fortune 100 use Roboflow to count cells to accelerate cancer research, improve


Read full story
SUMMARY

Build an AI agent for visual inspection by connecting defect detection, object tracking, visual reasoning, and review actions in Roboflow Workflows. Use RF-DETR to detect damage and Gemini to assess it, then send operators a structured report with image evidence to guide their next step.

...

Read full story
SUMMARY

Class imbalance in defect detection means the rare defect gets so little influence during training that overall mAP looks fine while the model misses the defects that matter most, so track per-class AP for the rare class instead.

Class imbalance in


Read full story