DINO<T>

Models & Types · AiDotNet.SelfSupervisedLearning

DINO: Self-Distillation with No Labels - a self-supervised method for Vision Transformers.

Inheritance: ModelBase<T, Tensor<T>, Tensor<T>> → SelfSupervisedLearningMethodBase<T> → TeacherStudentSSL<T> → DINO<T>

For Beginners

DINO is a self-supervised method specifically designed for Vision Transformers (ViT). It learns by having a student network predict the output of a teacher network, where the teacher is an EMA of the student.

How It Works

Key innovations:

Architecture:

Reference: Caron et al., “Emerging Properties in Self-Supervised Vision Transformers” (ICCV 2021)

Best for: Vision Transformers, emergent attention properties.

Pros: Emergent attention maps, strong ViT performance.

Cons: Primarily designed for Vision Transformers.

Constructors

Constructor Summary
DINO(INeuralNetwork<T> studentEncoder, IMomentumEncoder<T> teacherEncoder, IProjectorHead<T> studentProjector, IProjectorHead<T> teacherProjector, int outputDim, SelfSupervisedLearningConfig<T> config) Initializes a new instance of the DINO class.

Properties

Property Summary
SelfSupervisedLearningMethodCategory Category { get; }
string Name { get; }

Methods

Method Summary
DINO<T> Create(INeuralNetwork<T> encoder, Func<INeuralNetwork<T>, INeuralNetwork<T>> createEncoderCopy, int encoderOutputDim, int projectionDim, int hiddenDim, int outputDim) Creates a DINO instance with default configuration.