Pinned Loading

1. Object-detection-for-Domain-adpatation- Object-detection-for-Domain-adpatation- Public

   Object detection for Domain adaptation with The Pascal VOC 2012 dataset (DANN)

   Jupyter Notebook

2. CycleGAN-W-Domain-Adaptation CycleGAN-W-Domain-Adaptation Public

   using CycleGAN to address domain shift and fine-tuning a classifier on the adapted dataset is a highly effective method for bridging gaps between source and target domains

   Jupyter Notebook

3. Semi-Supervised-Domain-Adaptation-SSDA-with-Correlation-Alignment-CORAL- Semi-Supervised-Domain-Adaptation-SSDA-with-Correlation-Alignment-CORAL- Public

   Semi-Supervised Domain Adaptation (SSDA) with Correlation Alignment (CORAL). In this Tutorial we are using MNIST(Source Domain) and SVHN (Target Domain) datasets

   Jupyter Notebook

4. PseudoLabeling-CNN-DominAdaptation PseudoLabeling-CNN-DominAdaptation Public

   This tutorial on pseudo-labeling for domain adaptation using the DomainNet dataset!

   Jupyter Notebook 1

5. Denoising-Autoencoders-DAEs-for-Domain-Adaptation Denoising-Autoencoders-DAEs-for-Domain-Adaptation Public

   Denoising Autoencoders (DAEs) for Domain Adaptation using DAEs to find the invariant features for classification

   Jupyter Notebook

6. Self-supervised-Rotation-Prediction Self-supervised-Rotation-Prediction Public

   enable the model to learn meaningful and generalizable visual representations of images without requiring labeled data

   Jupyter Notebook