Feature pyramid network
A feature pyramid network is a neural network architecture that combines semantically rich low-resolution features with spatially detailed high-resolution features across multiple scales.
Deep Learning with R, Third Edition
A feature pyramid network is a neural-network architecture that combines semantically rich low-resolution features with spatially detailed high-resolution features at multiple scales.
- How it is used
- Improves object detection across different object sizes by providing effective features at multiple spatial scales.
- How deep it goes
- Explains feature fusion through upsampling and lateral additions, without deriving training objectives or implementation internals.
- Examples
- Uses pretrained RetinaNet inference on a Pointillist painting, with bounding-box visualization and COCO labels.
- What you can do after
- Operate/configure a pretrained RetinaNet detector through KerasHub and inspect its multiscale detection outputs.
Read how Deep Learning with R, Third Edition explains feature pyramid network →
Deep Learning with Python, Third Edition
An architecture that merges multi-scale feature maps from different depths to support detection of objects at multiple sizes.
- How it is used
- Supports object detection across small and large objects by combining feature maps from multiple ConvNet depths.
- How deep it goes
- Explains upsampling and lateral summation, but stops short of mathematical derivation or detailed layer design.
- Examples
- Uses RetinaNet COCO inference on a Pointillist painting, with predicted boxes, labels, confidence scores, and plotted detections.
- What you can do after
- Apply it via KerasHub by loading a RetinaNet preset, predicting detections, and visualizing labeled bounding boxes.
Read how Deep Learning with Python, Third Edition explains feature pyramid network →
Related concepts
- RetinaNetused by · RetinaNet is a one-stage object-detection architecture that uses convolutional feature pyramids with separate classification and bounding-box regression heads.
- feature mapuses · A feature map is a spatially organized array of neural-network activations representing the presence or strength of learned features at different locations.
- Conv2DTransposeuses · Conv2DTranspose is a neural-network layer that applies a learned two-dimensional transposed convolution to increase the spatial resolution of feature maps.
- upsamplingimplements · Upsampling is a process that increases the number, density, or spatial or temporal resolution of samples or values in a dataset or representation by adding, duplicating, or estimating them.
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.