Domain Generalization
633 papers with code • 19 benchmarks • 25 datasets
The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning
Benchmarks
These leaderboards are used to track progress in Domain Generalization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Domain Generalization models and implementationsDatasets
Fashion-MNIST
Office-Home
DomainNet
PACS
ImageNet-C
ImageNet-R
ImageNet-A
ImageNet-Sketch
Stylized ImageNet
WildDash
Most implemented papers
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
clovaai/CutMix-PyTorch
•
•
ICCV 2019
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Improved Regularization of Convolutional Neural Networks with Cutout
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
XingangPan/IBN-Net
•
•
ECCV 2018
IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances.
RandAugment: Practical automated data augmentation with a reduced search space
rwightman/pytorch-image-models
•
•
NeurIPS 2020
Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size.
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
google-research/augmix
•
•
ICLR 2020
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Invariant Risk Minimization
facebookresearch/InvariantRiskMinimization
•
•
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions.
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
hendrycks/robustness
•
•
ICLR 2019
Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.
A Closer Look at Few-shot Classification
wyharveychen/CloserLookFewShot
•
•
ICLR 2019
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
Learning to Prompt for Vision-Language Models
kaiyangzhou/coop
•
•
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks.
