| 860 |
ImageNet contains naturally occurring Apple NeuralHash collisions |
2021-08-19 |
| 380 |
First Impressions with GPT-4V(ision) |
2023-09-27 |
| 251 |
GPT-4 vision prompt injection |
2023-10-18 |
| 234 |
Using computer vision to help win $1M in Mountain Dew's Super Bowl contest |
2021-02-08 |
| 121 |
PaliGemma: Open-Source Multimodal Model by Google |
2024-05-15 |
| 83 |
First Impressions with Google Gemini |
2023-12-13 |
| 83 |
Zero Shot Object Tracking |
2021-08-26 |
| 51 |
Using Computer Vision to Win at Duck Hunt |
2021-08-27 |
| 49 |
YOLOv7 – A breakdown of how it works |
2022-07-17 |
| 32 |
Video segmentation with Segment Anything 2 (SAM2) |
2024-08-01 |
| 14 |
YOLOv5 v6.0 is here – new Nano model at 1666 FPS |
2021-10-13 |
| 11 |
Show HN: Protecting My Garden from Rabbits with Computer Vision |
2021-07-21 |
| 11 |
Distill Large Vision Models into Smaller, Efficient Models with Autodistill |
2023-06-08 |
| 10 |
WTF Coco – The Weird Images That Underpin Modern Computer Vision Models |
2022-09-01 |
| 8 |
Roboflow Annotate is now powered by the Segment Anything model |
2023-04-13 |
| 8 |
How to try CLIP: OpenAI's new universal zero-shot image classifier |
2021-01-08 |
| 7 |
How to Train SegFormer on a Custom Dataset |
2022-07-22 |
| 7 |
What's New in YOLOv8 |
2023-01-11 |
| 7 |
Using computer vision to get notifications of when public tennis courts are open |
2022-09-08 |
| 7 |
The Engineer's Guide to Figma |
2021-10-07 |
| 6 |
How we built paint.wtf, an AI game with 150k submissions that judges your art |
2021-03-16 |
| 6 |
What Is Segment Anything (Sam)? A Breakdown |
2023-04-10 |
| 5 |
The crazy story of how we got our .com domain |
2020-08-21 |
| 5 |
GPT-4o: Explanation and use cases |
2024-05-14 |
| 5 |
CVPR 2023 Highlights |
2023-06-23 |
| 5 |
Roboflow and Ultralytics Partner to Streamline YOLOv5 MLOps |
2021-10-01 |
| 5 |
Mitigating the Collision of Apple's CSAM NeuralHash |
2021-08-18 |
| 5 |
Scaled-YOLOv4 Sets New Standard in Object Detection – Topping EfficientDet |
2020-12-03 |
| 4 |
GPT-4 Vision Alternatives |
2023-11-23 |
| 4 |
How to Train YOLO-NAS on a Custom Dataset |
2023-05-17 |
| 4 |
Speculating on How GPT-4 Changes Computer Vision |
2023-03-16 |
| 4 |
Florence-2: MIT Open Source Vision Foundation Model by Microsoft |
2024-06-20 |
| 4 |
First Impressions with Gemini Advanced |
2024-02-08 |
| 4 |
ChatGPT Code Interpreter for Computer Vision |
2023-07-13 |
| 4 |
How to Deploy a YOLOv8 Model to a Raspberry Pi |
2023-01-25 |
| 4 |
Florence: Microsoft’s new foundation model for computer vision |
2021-12-10 |
| 4 |
How we used OpenAI's CLIP to build an infinite art competition |
2021-03-19 |
| 4 |
Training a YOLOv3 Object Detection Model with a Custom Dataset |
2020-12-21 |
| 3 |
How to Estimate Speed with Computer Vision |
2024-01-20 |
| 3 |
NeurIPS 2023 Papers Highlights |
2023-12-21 |
| 3 |
How CLIP and GPT-4V Compare for Classification |
2023-11-15 |
| 3 |
Experiments with GPT-4V for Object Detection |
2023-11-07 |
| 3 |
First Impressions with LLaVA-1.5 |
2023-10-10 |
| 3 |
How to Use the Segment Anything Model (Sam) |
2023-04-14 |
| 3 |
Track Football Players with YOLOv5 and ByteTRACK |
2022-12-09 |
| 3 |
How to know which computer vision deployment method to use |
2022-02-28 |
| 3 |
The Future of Football: AI-Assisted Coaches |
2021-10-26 |
| 3 |
Designing for Augmented Reality |
2020-11-20 |
| 2 |
Train Collision Prevention Use Case for Computer Vision |
2023-09-26 |
| 2 |
Fine-Tune SAM-2.1 on a Custom Dataset |
2024-11-15 |
| 2 |
How to Evaluate Cameras for Computer Vision |
2024-10-22 |
| 2 |
Camera Calibration in Sports with Keypoints |
2024-08-08 |
| 2 |
How to Fine-Tune PaliGemma for Object Detection |
2024-05-17 |
| 2 |
Realtime Video Stream Analysis with Computer Vision |
2024-05-03 |
| 2 |
YOLO-World: Real-Time, Zero-Shot Object Detection |
2024-02-15 |
| 2 |
How to Use FastViT |
2023-10-20 |
| 2 |
Comparing AI-Labeled Data to Human-Labeled Data |
2023-06-29 |
| 2 |
YOLOv5: State-of-the-art object detection at 140 FPS (2020) |
2022-06-11 |
| 2 |
Using Computer Vision to Play Dreidel |
2021-12-04 |
| 2 |
Transformers Take Over Object Detection |
2021-08-10 |
| 2 |
How to Train Yolox on a Custom Dataset |
2021-08-02 |
| 2 |
Experimenting with CLIP+VQGAN to create AI generated art |
2021-07-26 |
| 2 |
PP-YOLO Strikes Again – Record Object Detection at 68.9FPS |
2021-05-11 |
| 2 |
ELI5 Clip: A Beginner's Guide to the Clip Model |
2021-03-10 |
| 2 |
Apple's M1 is up to 3.6x as fast at training machine learning models |
2020-12-16 |
| 1 |
Dino-GPT4-V: Use GPT-4V in a Two-Stage Detection Model |
2023-11-07 |
| 1 |
Generate Synthetic Computer Vision Data with Stable Diffusion Image-to-Image |
2023-03-10 |
| 1 |
Fine-Tune GPT-4o for Object Detection |
2024-10-07 |
| 1 |
Evaluating Euro Cup and COPA America Cup Jersey Color Accessibility |
2024-07-22 |
| 1 |
First Impressions with the Claude 3 Opus Vision API |
2024-03-05 |
| 1 |
From Idea to Reality: Building a Computer Vision Scavenger Hunt for SXSW |
2023-05-10 |
| 1 |
Grounding Dino: SOTA Zero-Shot Object Detection |
2023-03-31 |
| 1 |
Track and Count Objects Using YOLOv8 |
2023-02-01 |
| 1 |
Collaborative Annotations When Building Computer Vision Models |
2022-03-01 |
| 1 |
How to Avoid Bias in Computer Vision Models |
2022-02-28 |
| 1 |
OpenAI's CLIP is this year’s most important new computer vision model [Opinion] |
2021-09-13 |
| 1 |
Prompt engineering: the magic words to using OpenAI's CLIP |
2021-05-18 |
| 127 |
Dataset and Model for “I built a system to take photos of planes over my house” |
2022-01-29 |
| 10 |
Show HN: 90k Computer Vision Datasets and 7k Pre-Trained Models |
2022-06-28 |
| 7 |
Show HN: A computer vision model to help identify Valentine's chocolates |
2022-02-14 |
| 6 |
Counting US Dollars with Computer Vision |
2023-11-02 |
| 3 |
PolygonZone – Calculate Coordinates for Computer Vision Polygons and Lines |
2023-02-14 |
| 2 |
Curious ML dataset for detecting Russian suicide drones |
2022-10-21 |
| 1 |
Roboflow Launch Week |
2023-03-30 |
| 1 |
Chess Pieces Dataset |
2020-12-21 |
| 4 |
Putting the New M4 Macs to the Test |
2024-12-13 |
| 3 |
OpenAI O3 Mini: Vision and Multimodal Features |
2025-02-13 |