Tag: Computer Vision
Data Augmentation is Still Data Curation
In this post we introduce the process of data augmentation, highlight a few common failure modes in computer vision,…
Exploring GradCam and More with FiftyOne
How to leverage CAM (Class Activation Mapping) methods with FiftyOne to unlock a whole new understanding of your…
Video Understanding with FiftyOne and Steamboat Willie
A quick comparison of VQA vs Action Recognition for general understanding using FiftyOne and a Steamboat Willie cartoon.
How to Build a Semantic Search Engine for Emojis
Learn how to build an open-source semantic emoji search engine, with both UI-centric and CLI versions.
Computer Vision and FiftyOne Community Year in Review 2023
Welcome to the final community update for 2023! In this blog we’ll bring you up to speed on recent happenings…
Why 2023 was the most exciting year in computer vision history (so far)
Computer vision had a banner year in 2023. From new foundation models to accurate real-time detection! We’ve…
Announcing the Voxel51 & V7 Partnership
The new integration between FiftyOne and V7 Darwin helps you create carefully curated datasets for smarter annotation.
Understanding LLaVA: Large Language and Vision Assistant
Learn more in this post how LLaVA aims to create a novel end-to-end trained large multimodal model that could compete…
NeurIPS 2023 Survival Guide
NeurIPS is the biggest machine learning conference and it is underway! Here’s a “Survival Guide” including…