Vision Field Notes

YOLO and Detection Basics

17 articles

YOLO and Detection Basics

Anchor-Free vs Anchor-Based Object Detectors

Anchor-free vs anchor-based detectors: what anchors are, why newer YOLO versions dropped them, and what the change means for training and deployment.

7 min read
YOLO and Detection Basics

Nano, Small, Medium: How to Choose a YOLO Model Size

Choosing a YOLO model size and input resolution: a method that starts from your hardware budget and accuracy needs, not a guess at nano, small or medium.

7 min read
YOLO and Detection Basics

Classification vs Detection vs Segmentation: Pick the Right Task

Classification vs detection vs segmentation: how to choose the right task for your project, with a decision guide, cost trade-offs and examples.

6 min read
YOLO and Detection Basics

Comparing Two Detectors Fairly

Before calling one detector better, hold data, settings and training budget equal, and check the gap is larger than test-set and seed noise.

5 min read
YOLO and Detection Basics

Confidence Thresholds: Tuning a Detector to Cut False Alarms

Tuning a confidence threshold for a detector: read the precision-recall curve, tune per class, and cut false alarms without missing real events.

7 min read
YOLO and Detection Basics

Why a Detector's Confidence Is Not a Probability

A box scored 0.8 is not right 80% of the time. What confidence scores are, why they shift between models and classes, and what that means for thresholds.

5 min read
YOLO and Detection Basics

Input Resolution or Model Size: Which to Increase for Small Objects

When a detector misses small objects, a bigger model and a bigger input both cost compute. Why input size usually helps more, and when it does not.

5 min read
YOLO and Detection Basics

IoU and Non-Maximum Suppression, Explained with Examples

Intersection over Union and non-maximum suppression explained step by step, with worked examples, code, and typical threshold choices for detectors.

7 min read
YOLO and Detection Basics

mAP, Precision and Recall: How to Read Detection Results

Learn how to read precision, recall, mAP50 and mAP50-95 in object detection results, and which metric matters most for your own use case and camera setup.

7 min read
YOLO and Detection Basics

Single-Class or Multi-Class: When to Merge or Split Detection Classes

Should car, van and truck be one class or three? How to decide a detector's classes, and why labelling fine and training coarse keeps options open.

5 min read
YOLO and Detection Basics

Preprocessing Mismatches That Silently Cost Accuracy

A model only works on inputs prepared the way it was trained. Resize method, colour order, normalisation and padding mismatches, and how to catch them.

6 min read
YOLO and Detection Basics

What Is YOLO? Object Detection Explained Without the Math

What is YOLO? A plain explanation of how it finds objects in a single pass, what its output means, and where it fits in a project.

7 min read
YOLO and Detection Basics

What mAP Hides: Seven Things a Single Score Won't Tell You

mAP is a useful summary, but it hides the operating threshold, object size, error types and how the number was computed. Here is what to check next to it.

6 min read
YOLO and Detection Basics

YOLO Licenses Explained: AGPL, GPL and Commercial Use

YOLO licenses explained: what AGPL-3.0 and GPL-3.0 mean for YOLO projects, options for commercial products and safe habits. Not legal advice.

7 min read
YOLO and Detection Basics

YOLO27 Announced: What to Check Before You Switch

Ultralytics announced YOLO27 in September 2026. What was actually said, what is still unknown, and how to evaluate it on your own data when it ships.

5 min read
YOLO and Detection Basics

YOLOv5 vs YOLOv8 vs YOLO11: Which Should You Use?

YOLOv5 vs YOLOv8 vs YOLO11 compared in practice: workflow, accuracy and speed trade-offs, export support and licence, plus a simple way to decide.

7 min read
YOLO and Detection Basics

How YOLOv7 Gets Real-Time Speed with Re-parameterization

How YOLOv7 uses re-parameterization: training-time and inference-time structure, how layers merge, and what it means when you export and deploy the model.

7 min read