• 5 min read
How to Load Image Embeddings into Pinecone
In this guide, learn how to calculate CLIP embeddings with Roboflow Inference and save the results in a Pinecone vector database.
• 5 min read
Launch: Synthetic Image Generation with DALL-E and GPT-4 Vision
In this guide, learn how to use Roboflow to generate synthetic data with DALL-E and GPT-4 Vision for use in training vision models.
• 3 min read
Roboflow Video Inference with Custom Annotators
Performing real-time video inference is crucial for many applications like autonomous vehicles, security systems, logistics, and more. However, setting up a robust video inference pipeline can be time consuming. You need a trained computer vision model, inference code, and visualization tools to annotate each frame. This is a lot of
• 5 min read
How to Load CLIP Image Embeddings into LanceDB
Learn how to calculate CLIP embeddings using Roboflow Inference and save them into LanceDB.
• 7 min read
GPT-4 Vision Alternatives
Explore alternatives to GPT-4 Vision with Large Multimodal Models such as Qwen-VL and CogVLM, and fine-tuned detection models.
• 4 min read
How to Search Video Frames with Roboflow
Build a search engine that lets you find frames in a video with text queries using Roboflow Inference.
• 7 min read
What Is Optical Character Recognition (OCR)?
Learn what Optical Character Recognition is, what problems can be solved with OCR, and explore the approaches used by OCR algorithms to identify characters.
• 5 min read
What is Object Recognition?
In this guide, we discuss what object recognition is, how it works, and how to start using object recognition to solve problems.
• 5 min read
What is Retrieval Augmented Generation?
Learn what Retrieval Augmented Generation (RAG) is, how it works, and how RAG can be used in computer vision applications.
• 5 min read
What is Zero-Shot Classification?
Learn what zero-shot classification is, what zero-shot classification is used for, and how to use zero-shot classification to solve computer vision problems.
• 6 min read
What is an Image Embedding?
Learn what image embeddings are and explore four use cases for embeddings: classifying images and video, clustering images, and image search.
• 4 min read
What is Zero-Shot Object Detection?
Learn what zero-shot object detection is, applications for zero-shot object detection, and how to get started with Grounding DINO, a zero-shot model.
• 4 min read
How to Use Roboflow with GPT-4 Vision
Explore ways you can use Roboflow with GPT-4 Vision to solve computer vision problems.
• 4 min read
Distilling GPT-4 for Classification with an API
In this guide, learn how to distill GPT-4V to train an image classification model.
• 4 min read
DINO-GPT4-V: Use GPT-4V in a Two-Stage Detection Model
In this guide, we introduce DINO-GPT4V, a model that uses Grounding DINO to detect general objects and GPT-4V to refine labels.
• 5 min read
How CLIP and GPT-4V Compare for Classification
In this post, we analyze how CLIP and GPT-4V compare for classification.
• 5 min read
Experiments with GPT-4V for Object Detection
See our experiments that explore GPT-4V's object detection capabilities.
• 5 min read
How to Use MetaCLIP
Learn what MetaCLIP is, how the model performs on benchmarks, and how to use MetaCLIP.
• 3 min read
How to Provide Detailed Labeling Instructions to Outsourced Labelers
In this guide, we walk through a few tips and best practices showing how to provide detailed, useful labeling instructions to outsourced labelers.
• 8 min read
How to Detect Text in Images with OCR
This guide shows how to use the Roboflow OCR API as part of a two-stage detection system that identifies regions of interest and reads text in them.
• 6 min read
How to Detect Segments in Videos with Computer Vision
Learn how to detect segments in videos using and an interactive web tool powered by the cLIP computer vision model.
• 6 min read
What is Keypoint Detection?
In this guide, we discuss what keypoint detection is, common architectures used for keypoint detection, and the high-level steps to build a keypoint detection model.
• 5 min read
Launch: Advanced Dataset Search Filters, Operators, and Logic
Learn how to use the new advanced dataset search filters, operators, and logic available in the Roboflow dataset management tool.
• 6 min read
Launch: Roboflow Logistics Pre-trained Object Detection Model
The Roboflow Logistics Model, trained on 99,238 images across 20 classes, offers a domain-specific advantage for logistics vision use cases.
Stay Connected