Welcome to domainlab’s documentation!

Contents:

• domainlab
  • domainlab package
    • Subpackages
    • Submodules
    • domainlab.arg_parser module
    • domainlab.cli module
    • domainlab.mk_exp module
    • Module contents
• Model HDUVA
  • HDUVA: HIERARCHICAL VARIATIONAL AUTO-ENCODING FOR UNSUPERVISED DOMAIN GENERALIZATION
  • Model Overview
  • Evidence lower bound and overall loss
  • Hyperparameters loss function
  • Model hyperparameters
  • Hyperparameter for warmup
  • Examples
    • hduva use custom net for sandwich encoder
    • hduva use custom net for topic encoder
    • hduva use custom net for classification encoder
    • use hduva on color mnist, train on 2 domains
    • hduva is domain-unsupervised, so it works also with a single domain
    • hduva with implemented neural network
    • hduva use alex net
• Model DANN
  • Domain Adversarial Neural Network
• Model JiGen
  • Model parameters
  • Examples
    • model jigen with implemented neural network
    • sannity check with jigen tile shuffling
• Model DIVA
  • Domain Invariant Variational Autoencoders
    • Model parameters
  • Examples
    • model diva with implemented neural network
    • model diva with custom neural network
    • generation of images
  • Colored version of MNIST
    • leave one domain out
    • choose train and test
• Trainer MatchDG
  • Domain Generalization using Causal Matching
  • Motivation: causality theory
  • Network
  • Training
  • Examples
    • trainer matchdg with custom neural network
    • training hduva with matchdg
    • training implemented neural network with matchdg
    • trainer matchdg with mnist
• Trainer DIAL
  • Domain Invariant Adversarial Learning
  • generating the adversarial domain
  • network structure
  • loss function and gradient reversal layer
  • Examples
    • Train DIVA model with DIAL trainer
    • Set hyper-parameters for trainer as well
• Trainer Fishr
  • Invariant Gradient Variances for Out-of-distribution Generalization
    • Quantifying inconsistency between domains
    • Matching the Variances during training
    • Implementation
  • Examples
• Trainer MLDG
  • Meta Learning Domain Generalization
  • Examples
• Trainer IRM
  • Invariant Risk Minimization
  • IRMv1
  • Examples
• Trainer SMV
  • Simple Moving Average
• Trainer CORAL
  • Deep CORAL: Correlation Alignment for Deep Domain Adaptation
  • Examples
• Trainer Causal IRL
  • Invariant Causal Mechanisms through Distribution Matching
  • Example
• MIRO: Mutual-Information Regularization
  • Mutual Information Regularization with Oracle (MIRO).
    • Pre-requisite: Variational lower bound on mutual information
  • MIRO

Indices and tables

• Index

• Module Index

• Search Page