About

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

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Deep Residual Learning for Image Recognition

CVPR 2016 tensorflow/models

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

DOMAIN GENERALIZATION FINE-GRAINED IMAGE CLASSIFICATION IMAGE-TO-IMAGE TRANSLATION OBJECT DETECTION PEDESTRIAN ATTRIBUTE RECOGNITION PEDESTRIAN TRAJECTORY PREDICTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

ICLR 2020 rwightman/pytorch-image-models

We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.

DOMAIN GENERALIZATION IMAGE CLASSIFICATION

mixup: Beyond Empirical Risk Minimization

ICLR 2018 rwightman/pytorch-image-models

We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.

DOMAIN GENERALIZATION SEMI-SUPERVISED IMAGE CLASSIFICATION

Posterior Differential Regularization with f-divergence for Improving Model Robustness

23 Oct 2020namisan/mt-dnn

Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework.

DOMAIN GENERALIZATION

A Closer Look at Few-shot Classification

ICLR 2019 wyharveychen/CloserLookFewShot

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.

DOMAIN GENERALIZATION FEW-SHOT IMAGE CLASSIFICATION

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

ICLR 2019 rgeirhos/texture-vs-shape

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.

Ranked #3 on Domain Generalization on ImageNet-C (using extra training data)

DOMAIN GENERALIZATION IMAGE CLASSIFICATION OBJECT DETECTION

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

ICLR 2019 hendrycks/robustness

Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.

ADVERSARIAL DEFENSE DOMAIN GENERALIZATION

Improved Regularization of Convolutional Neural Networks with Cutout

15 Aug 2017uoguelph-mlrg/Cutout

Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.

DOMAIN GENERALIZATION IMAGE AUGMENTATION SEMI-SUPERVISED IMAGE CLASSIFICATION