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.
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
- bounding boxA bounding box is a coordinate-defined rectangular region in two or more dimensions that encloses or localizes an object, area, or set of points.
- linear layerA linear layer is a neural-network layer that applies a learned affine transformation to its input, typically using weights and a bias.
- object detection modelAn object detection model is a computer-vision model that identifies object instances and predicts their classes and spatial locations in visual data.
- ReLUReLU is an activation function that maps an input x to the greater of x and zero.
Related concepts
- RetinaNetincludes · RetinaNet is a one-stage object-detection architecture that uses convolutional feature pyramids with separate classification and bounding-box regression heads.
- YOLOincludes · YOLO is a family of single-stage object-detection models that predict object classes and locations directly from an image in one inference pass.
- object detection modelkind of · An object detection model is a computer-vision model that identifies object instances and predicts their classes and spatial locations in visual data.
- object detectionaddresses · Object detection is a computer-vision task that identifies object instances in visual data, assigns them categories, and estimates their locations.
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.

