liveBook · Manning

Single-stage detector

An object-detection architecture that predicts object locations and class labels directly in one integrated model pass without a separate region-proposal stage.

How 2 Manning books explain it

Deep Learning with R, Third Edition

A single-stage object detector predicts object locations and categories directly in one integrated model pass rather than first generating region proposals.

How it is used
Supports efficient object detection for real-time and resource-constrained applications.
How deep it goes
Explains proposal avoidance, direct outputs, grid prediction, and multi-scale features, while simplifying YOLO to one box per grid cell.
Examples
Uses a simplified YOLO grid, pretrained ResNet, 448 × 448 inputs, and RetinaNet inference on a COCO-trained painting example.
What you can do after
Build it from scratch with a convolutional backbone and prediction head, or apply it through a pretrained RetinaNet detector.

Read how Deep Learning with R, Third Edition explains single-stage detector →

Deep Learning with Python, Third Edition

An object-detection architecture that predicts bounding boxes and class labels in one pass with a single model, rather than using separate proposal and classification stages.

How it is used
Deploys object detection when fast, efficient localization and classification matter more than pixel-level masks.
How deep it goes
Explains joint outputs, grid prediction, confidence, and backbones through a simplified YOLO build, without developing the full original architecture.
Examples
Uses counting, tracking, and cropping applications plus a grid-based YOLO model with ResNet and KerasHub.
What you can do after
Build a simplified YOLO detector from scratch using a pretrained ConvNet backbone and separate box and class outputs.

Read how Deep Learning with Python, Third Edition explains single-stage detector →

What to know first

Related concepts

Questions about single-stage detector

What is single-stage detector?

An object-detection architecture that predicts object locations and class labels directly in one integrated model pass without a separate region-proposal stage.

Which Manning books explain single-stage detector?

Deep Learning with R, Third Edition and Deep Learning with Python, Third Edition.

What should I know before learning single-stage detector?

Manning books that teach single-stage detector usually introduce bounding box, linear layer, object detection model and ReLU first.

What is the difference between single-stage detector and two-stage detector?

An object-detection architecture that predicts object locations and class labels directly in one integrated model pass without a separate region-proposal stage. A two-stage detector is an object-detection model that first generates candidate region proposals and then classifies or refines them.

What kinds of single-stage detector are there?

Kinds of single-stage detector include RetinaNet, SSD and YOLO.

What is single-stage detector a kind of?

Single-stage detector is a kind of object detection model. An object detection model is a computer-vision model that identifies object instances and predicts their classes and spatial locations in visual data.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.