Homepage
Open in app
Sign in
Get started
Voxel51
News, tutorials, tips, and big ideas in computer vision and data-centric machine learning, from the company behind open source FiftyOne. Learn more at https://voxel51.com
About
Tips and Tricks
All Stories
ML@Voxel51
Voxel51
Follow
UnCommon Objects in 3D
UnCommon Objects in 3D
Meet the Most Comprehensive Real-World 3D Dataset Ever Created
Harpreet Sahota
Jun 20
Van der Maaten’s Three-System Roadmap to AGI Is Brilliantly Pragmatic
Van der Maaten’s Three-System Roadmap to AGI Is Brilliantly Pragmatic
The Future of AI is Networked Intelligence
Harpreet Sahota
Jun 18
Latest Stories
Rethinking How We Evaluate Multimodal AI
Rethinking How We Evaluate Multimodal AI
CVPR 2025 reveals why spatial reasoning and subjective ‘vibes’ are redefining how we benchmark AI systems
Harpreet Sahota
Jun 14
Composed Image Retrieval at CVPR 2025
Composed Image Retrieval at CVPR 2025
The Evolution of Image Search
Harpreet Sahota
Jun 9
Visual Agents at CVPR 2025
Visual Agents at CVPR 2025
AI Systems that See, Understand, and Act
Harpreet Sahota
May 29
Visualizing Model Certainty in the Unknown
Visualizing Model Certainty in the Unknown
Visualize model certainty on unlabeled data with our new open source tool. Efficiently predict model performance & identify high-value…
Brent Griffin, Ph.D.
Apr 1
Introducing FiftyOne Enterprise Workflows to Accelerate Visual AI Innovation
Introducing FiftyOne Enterprise Workflows to Accelerate Visual AI Innovation
FiftyOne Enterprise data and model workflows are here to streamline and scale your AI/ML processes. Learn more!
Brian Moore
Mar 25
This Visual Illusions Benchmark Makes Me Question the Power of VLMs
This Visual Illusions Benchmark Makes Me Question the Power of VLMs
Exploring how well modern AI systems can spot visual deceptions
Harpreet Sahota
Mar 3
Memes Are the VLM Benchmark We Deserve
Memes Are the VLM Benchmark We Deserve
Seriously, Memes Are All We Need
Harpreet Sahota
Feb 20
Can VLMs Hear What They See?
Can VLMs Hear What They See?
Exploring the Intersection of Vision Language Models and Audio Data
Harpreet Sahota
Feb 20
WebUOT-1M: A Dataset for Underwater Object Tracking
WebUOT-1M: A Dataset for Underwater Object Tracking
How 1.1 Million Frames Are Transforming Object Tracking
Harpreet Sahota
Feb 17
Beyond the Microscope: Diving into BIOSCAN-5M, a New Dataset for Insect Biodiversity Research
Beyond the Microscope: Diving into BIOSCAN-5M, a New Dataset for Insect Biodiversity Research
Exploring the World’s Largest Insect Dataset with a Modern Toolkit for Visual AI
Harpreet Sahota
Feb 13
AIMv2 Outperforms CLIP on Synthetic Dataset ImageNet-D
AIMv2 Outperforms CLIP on Synthetic Dataset ImageNet-D
Testing Vision Model Robustness: A hands-on tutorial for evaluating vision model performance on synthetic data using embedding analysis and…
Harpreet Sahota
Feb 12
Visual Understanding with AIMv2
Visual Understanding with AIMv2
Move over, CLIP — you’ve been dethroned!
Harpreet Sahota
Feb 11
ImageNet-D: a new synthetic test set designed to rigorously evaluate the robustness of neural…
ImageNet-D: a new synthetic test set designed to rigorously evaluate the robustness of neural…
How well does your model understand what it “sees”?
Harpreet Sahota
Feb 11
Gaussian Splatting: From Research to Reality
Gaussian Splatting: From Research to Reality
Author: Paula Ramos, PhD
Paula Ramos, PhD.
Feb 7
Understanding Dataset Difficulty with Class-Wise Autoencoders
Understanding Dataset Difficulty with Class-Wise Autoencoders
New metric called Reconstruction Error Ratios (RERs) provides a fast & scalable way to assess dataset difficulty & detect mislabeled…
Jason Corso
Feb 4
Supercharge Your Visual AI Workflow: FiftyOne’s New Plugin for Janus-Pro
Supercharge Your Visual AI Workflow: FiftyOne’s New Plugin for Janus-Pro
Author: Paula Ramos, PhD
Paula Ramos, PhD.
Jan 28
How to Tame Your (Data) Dragon
How to Tame Your (Data) Dragon
Explore Zero-Shot Coreset Selection (ZCore) for identifying valuable data subsets without labels, data-specific training or domain…
Brent Griffin, Ph.D.
Jan 21
Voxel51 Filtered Views Newsletter — January 17, 2025
Voxel51 Filtered Views Newsletter — January 17, 2025
🔎 Elderly Action Recognition Challenge — WACV 2025
Dillon Pinto
Jan 17
The Frontier of Visual AI in Medical Imaging
The Frontier of Visual AI in Medical Imaging
Artificial intelligence (AI) is reshaping the sciences, with groundbreaking advancements in fields like physics and chemistry. For…
Daniel Gural
Jan 15
How to Make the Best Self-Driving Dataset
How to Make the Best Self-Driving Dataset
Hey there! Dan Gural here from Voxel51, and I recently gave an in-person workshop on How to Unlock More in Self-Driving Datasets. I’m super…
Daniel Gural
Jan 14
Bias in Data: What Embeddings Reveal About Real vs Synthetic Data Distribution
Bias in Data: What Embeddings Reveal About Real vs Synthetic Data Distribution
Explore biases in visual data, how to use synthetic data to offset bias, and how to use FiftyOne to identify gaps in real vs fake data
Manushree Gangwar
Jan 7
Why 2024 Was the Best Year for Visual AI (So Far)
Why 2024 Was the Best Year for Visual AI (So Far)
In 2024, Visual AI didn’t just advance-it redefined the world around us. Learn why 2024 was the best year for Visual AI so far!
Daniel Gural
Dec 20, 2024
What AI Means for Science in 2025
What AI Means for Science in 2025
Why I believe AI played distinct roles in the 2024 Chemistry & Physics awards, and how these awards reflect AI’s impact on natural sciences
Jacob Marks, Ph.D.
Dec 17, 2024
Recapping the AI, Machine Learning and Computer Meetup — December 12, 2024
Recapping the AI, Machine Learning and Computer Meetup — December 12, 2024
We just wrapped up the December ’24 AI, Machine Learning and Computer Vision Meetup, and if you missed it or want to revisit it, here’s a…
Jimmy Guerrero
Dec 12, 2024
About Voxel51
Latest Stories
Archive
About Medium
Terms
Privacy
Teams
