Table of Contents

Class DocBank<T>

Namespace
AiDotNet.Document.Analysis.PageSegmentation
Assembly
AiDotNet.dll

DocBank model for document page segmentation and layout analysis.

public class DocBank<T> : DocumentNeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable, IPageSegmenter<T>, IDocumentModel<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance
DocBank<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

DocBank is a benchmark and model for document layout analysis that can segment document pages into semantic regions including text, titles, figures, tables, and captions. It combines visual features with optional text features for robust segmentation.

For Beginners: DocBank divides document pages into different regions: - Paragraphs: Regular text content - Titles: Document headings and titles - Figures: Images and diagrams - Tables: Tabular data regions - Captions: Text describing figures/tables - Lists: Bulleted or numbered lists - Equations: Mathematical formulas - And more...

Example usage:

var docbank = new DocBank<float>(architecture);
var result = docbank.SegmentPage(documentImage);
foreach (var region in result.Regions)
{
    Console.WriteLine($"Found {region.RegionType} at {region.BoundingBox}");
}

Reference: "DocBank: A Benchmark Dataset for Document Layout Analysis" (COLING 2020) https://arxiv.org/abs/2006.01038

Constructors

DocBank(NeuralNetworkArchitecture<T>, int, int, int, int, bool, IOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?)

Creates a DocBank model using native layers for training and inference.

public DocBank(NeuralNetworkArchitecture<T> architecture, int imageSize = 1024, int backboneChannels = 256, int numClasses = 13, int hiddenDim = 256, bool useTextFeatures = false, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture.

imageSize int

Expected input image size (default: 1024).

backboneChannels int

Backbone output channels (default: 256).

numClasses int

Number of segmentation classes (default: 13 for DocBank).

hiddenDim int

Hidden dimension for segmentation head (default: 256).

useTextFeatures bool

Whether to use text features (default: false for image-only).

optimizer IOptimizer<T, Tensor<T>, Tensor<T>>

Optimizer for training (optional).

lossFunction ILossFunction<T>

Loss function (optional).

Remarks

Default Configuration (from COLING 2020 paper): - Backbone: ResNet-101 with FPN - Image size: 1024×1024 - Classes: 13 (paragraph, title, figure, table, etc.) - Can optionally incorporate text features from BERT

DocBank(NeuralNetworkArchitecture<T>, string, int, int, int, bool, IOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?)

Creates a DocBank model using a pre-trained ONNX model for inference.

public DocBank(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int imageSize = 1024, int backboneChannels = 256, int numClasses = 13, bool useTextFeatures = false, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture.

onnxModelPath string

Path to the ONNX model file.

imageSize int

Expected input image size (default: 1024).

backboneChannels int

Backbone output channels (default: 256).

numClasses int

Number of segmentation classes (default: 13 for DocBank).

useTextFeatures bool

Whether to use text features (default: false for image-only).

optimizer IOptimizer<T, Tensor<T>, Tensor<T>>

Optimizer for training (optional).

lossFunction ILossFunction<T>

Loss function (optional).

Exceptions

ArgumentNullException

Thrown if onnxModelPath is null.

FileNotFoundException

Thrown if ONNX model file doesn't exist.

Properties

ExpectedImageSize

Gets the expected input image size (assumes square images).

public int ExpectedImageSize { get; }

Property Value

int

Remarks

Common values: 224 (ViT base), 384, 448, 512, 768, 1024. Input images will be resized to [ImageSize x ImageSize] before processing.

NumClasses

Gets the number of segmentation classes.

public int NumClasses { get; }

Property Value

int

RequiresOCR

Gets whether this model requires OCR preprocessing.

public override bool RequiresOCR { get; }

Property Value

bool

Remarks

Layout-aware models (LayoutLM, etc.) require OCR to provide text and bounding boxes. OCR-free models (Donut, Pix2Struct) process raw pixels directly.

SupportedDocumentTypes

Gets the supported document types for this model.

public override DocumentType SupportedDocumentTypes { get; }

Property Value

DocumentType

SupportedRegionTypes

Gets the region types this segmenter can detect.

public IReadOnlyList<DocumentRegionType> SupportedRegionTypes { get; }

Property Value

IReadOnlyList<DocumentRegionType>

SupportsInstanceSegmentation

Gets whether this segmenter performs instance segmentation (separate instances of same type).

public bool SupportsInstanceSegmentation { get; }

Property Value

bool

Methods

ApplyDefaultPostprocessing(Tensor<T>)

Applies DocBank's industry-standard postprocessing: softmax over class dimension.

protected override Tensor<T> ApplyDefaultPostprocessing(Tensor<T> modelOutput)

Parameters

modelOutput Tensor<T>

Returns

Tensor<T>

ApplyDefaultPreprocessing(Tensor<T>)

Applies DocBank's industry-standard preprocessing: ImageNet normalization.

protected override Tensor<T> ApplyDefaultPreprocessing(Tensor<T> rawImage)

Parameters

rawImage Tensor<T>

Returns

Tensor<T>

Remarks

DocBank uses ImageNet normalization with mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

CreateNewInstance()

Creates a new instance of the same type as this neural network.

protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()

Returns

IFullModel<T, Tensor<T>, Tensor<T>>

A new instance of the same neural network type.

Remarks

For Beginners: This creates a blank version of the same type of neural network.

It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.

DeserializeNetworkSpecificData(BinaryReader)

Deserializes network-specific data that was not covered by the general deserialization process.

protected override void DeserializeNetworkSpecificData(BinaryReader reader)

Parameters

reader BinaryReader

The BinaryReader to read the data from.

Remarks

This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.

For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.

Dispose(bool)

Disposes of resources used by this model.

protected override void Dispose(bool disposing)

Parameters

disposing bool

True if disposing managed resources.

EncodeDocument(Tensor<T>)

Processes a document image and returns encoded features.

public Tensor<T> EncodeDocument(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor [batch, channels, height, width] or [channels, height, width].

Returns

Tensor<T>

Encoded document features suitable for downstream tasks.

Remarks

For Beginners: This method converts a document image into a numerical representation (feature vector) that captures the document's content and structure. These features can then be used for tasks like classification, QA, or information extraction.

GetModelMetadata()

Gets the metadata for this neural network model.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

A ModelMetaData object containing information about the model.

GetModelSummary()

Gets a summary of the model architecture.

public string GetModelSummary()

Returns

string

A string describing the model's architecture, parameters, and capabilities.

GetSegmentationMask(Tensor<T>)

Gets the pixel-level segmentation mask.

public Tensor<T> GetSegmentationMask(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document page image tensor.

Returns

Tensor<T>

Segmentation mask with class indices for each pixel.

InitializeLayers()

Initializes the layers of the neural network based on the architecture.

protected override void InitializeLayers()

Remarks

For Beginners: This method sets up all the layers in your neural network according to the architecture you've defined. It's like assembling the parts of your network before you can use it.

Predict(Tensor<T>)

Makes a prediction using the neural network.

public override Tensor<T> Predict(Tensor<T> input)

Parameters

input Tensor<T>

The input data to process.

Returns

Tensor<T>

The network's prediction.

Remarks

For Beginners: This is the main method you'll use to get results from your trained neural network. You provide some input data (like an image or text), and the network processes it through all its layers to produce an output (like a classification or prediction).

SegmentPage(Tensor<T>)

Segments a document page into semantic regions.

public PageSegmentationResult<T> SegmentPage(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document page image tensor.

Returns

PageSegmentationResult<T>

Segmentation result with labeled regions.

SegmentPage(Tensor<T>, double)

Segments a document page with a custom confidence threshold.

public PageSegmentationResult<T> SegmentPage(Tensor<T> documentImage, double confidenceThreshold)

Parameters

documentImage Tensor<T>

The document page image tensor.

confidenceThreshold double

Minimum confidence for region detection (0-1).

Returns

PageSegmentationResult<T>

Segmentation result with labeled regions.

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The BinaryWriter to write the data to.

Remarks

This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.

For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.

Train(Tensor<T>, Tensor<T>)

Trains the neural network on a single input-output pair.

public override void Train(Tensor<T> input, Tensor<T> expectedOutput)

Parameters

input Tensor<T>

The input data.

expectedOutput Tensor<T>

The expected output for the given input.

Remarks

This method performs one training step on the neural network using the provided input and expected output. It updates the network's parameters to reduce the error between the network's prediction and the expected output.

For Beginners: This is how your neural network learns. You provide: - An input (what the network should process) - The expected output (what the correct answer should be)

The network then:

  1. Makes a prediction based on the input
  2. Compares its prediction to the expected output
  3. Calculates how wrong it was (the loss)
  4. Adjusts its internal values to do better next time

After training, you can get the loss value using the GetLastLoss() method to see how well the network is learning.

UpdateParameters(Vector<T>)

Updates the network's parameters with new values.

public override void UpdateParameters(Vector<T> gradients)

Parameters

gradients Vector<T>

Remarks

For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.

This is typically used by optimization algorithms that calculate better parameter values based on training data.

ValidateInputShape(Tensor<T>)

Validates that an input tensor has the correct shape for this model.

public void ValidateInputShape(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The tensor to validate.

Exceptions

ArgumentException

Thrown if the tensor shape is invalid.

Edit this page