Browse SoTA > Methodology > Domain Adaptation > Domain Generalization

Domain Generalization

61 papers with code · Methodology
Subtask of Domain Adaptation

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

Latest papers with code

DART: Open-Domain Structured Data Record to Text Generation

6 Jul 2020Yale-LILY/dart

We consider the structured data record input as a set of RDF entity-relation triples, a format widely used for knowledge representation and semantics description.

DOMAIN GENERALIZATION TEXT GENERATION

33
06 Jul 2020

Self-Challenging Improves Cross-Domain Generalization

5 Jul 2020DeLightCMU/RSC

We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.

DOMAIN GENERALIZATION IMAGE CLASSIFICATION

2
05 Jul 2020

Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains

4 Jul 2020liuquande/SAML

We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.

DOMAIN GENERALIZATION META-LEARNING

21
04 Jul 2020

In Search of Lost Domain Generalization

2 Jul 2020facebookresearch/DomainBed

As a first step, we realize that model selection is non-trivial for domain generalization tasks.

DOMAIN GENERALIZATION MODEL SELECTION

35
02 Jul 2020

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

29 Jun 2020hendrycks/imagenet-r

We introduce three new robustness benchmarks consisting of naturally occurring distribution changes in image style, geographic location, camera operation, and more.

DATA AUGMENTATION DOMAIN GENERALIZATION

37
29 Jun 2020

Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification

23 Jun 2020VideoObjectSearch/RandPerson

To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model.

DOMAIN GENERALIZATION GENERALIZABLE PERSON RE-IDENTIFICATION LARGE-SCALE PERSON RE-IDENTIFICATION

30
23 Jun 2020

Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment

23 Jun 2020JingWang18/Discriminative-Feature-Alignment

To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution.

DATA AUGMENTATION DOMAIN GENERALIZATION TRAFFIC SIGN RECOGNITION TRANSFER LEARNING UNSUPERVISED DOMAIN ADAPTATION

7
23 Jun 2020

A Universal Representation Transformer Layer for Few-Shot Image Classification

21 Jun 2020liulu112601/URT

We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources.

DOMAIN GENERALIZATION FEW-SHOT IMAGE CLASSIFICATION

9
21 Jun 2020

Frustratingly Simple Domain Generalization via Image Stylization

19 Jun 2020GT-RIPL/DomainGeneralization-Stylization

Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i. i. d.

DOMAIN GENERALIZATION IMAGE STYLIZATION

11
19 Jun 2020

Domain Generalization using Causal Matching

arXiv 2020 microsoft/robustdg

Learning invariant representations has been proposed as a key technique for ad-dressing the domain generalization problem.

DOMAIN GENERALIZATION

14
16 Jun 2020