liveBook · Manning

Dilated convolution

As explained in Fight Fraud with Machine Learning

Atrous convolution is an image convolution operation that spaces kernel elements apart to expand the input area covered without increasing the number of kernel parameters.

Dilated, or atrous, convolution spreads a kernel across an image by inserting gaps between kernel values. A dilation rate of 2 skips one pixel, enlarging the field of view without adding parameters. section 6.2.2

This wider context is useful for image segmentation, where each pixel must be classified while preserving information from surrounding regions. DeepLabV3 uses dilated convolutions to segment forged and genuine receipt pixels. section 6.2 section 6.2.2

In receipt-forgery detection, dilated convolution supports:

  • A broader image context without increasing convolutional parameter count. section 6.2.2
  • Pixel-wise localization of small forged regions instead of only classifying an entire receipt. section 6.2
  • Context-aware segmentation within DeepLabV3, alongside 1x1 convolution and atrous spatial pyramid pooling. section 6.5

Segmenting a forged receipt

Represent a receipt as a pixel-segmentation problem with forged and genuine classes. A DeepLabV3 model uses dilated convolutions to gather wider visual context while producing pixel-wise detections that reveal manipulated regions. section 6.2 section 6.5

Figure 6.8 Architecture of the DeepLabV3 segmentation model that uses atrous convolution, 1x1 convolution, and atrous spatial pyramidal pooling as some distinct features that help in accurate image segmentation. (source: https://learnopencv.com/deeplabv3-ultimate-guide/)

Inspect the DeepLabV3 architecture and its combination of atrous convolution, 1x1 convolution, and atrous spatial pyramid pooling. section 6.2

How Fight Fraud with Machine Learning covers it

How deep it goes
Explains kernel spacing, dilation rates, field-of-view expansion, and parameter efficiency without detailing kernel arithmetic or implementation code.
Examples
Uses forged-receipt pixel masks and the DeepLabV3 architecture as concrete applications.
What you can do after
Apply it via DeepLabV3 to capture wider image context for pixel-wise document-forgery segmentation.
How it connects
Connects dilated convolution to image segmentation, convolutional neural networks, DeepLabV3, 1x1 convolution, and atrous spatial pyramid pooling.

Also explained in

Compare how 2 books explain dilated convolution →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Fight Fraud with Machine Learning. The section links point to the parts of the book it draws on.