Browse SoTA > Methodology > Domain Adaptation > Domain Generalization

Domain Generalization

61 papers with code ยท 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 without code

Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring

4 Aug 2020

Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay.

AUTOMATED ESSAY SCORING DOMAIN GENERALIZATION TRANSFER LEARNING

SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data

30 Jul 2020

Additionally, we present our model's 3D surface normal predictions on the MSCOCO dataset that lacks any real 3D surface normal labels.

DOMAIN GENERALIZATION MULTI-TASK LEARNING POSE ESTIMATION

Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors

28 Jul 2020

Features extracted from this source domain are learned using a generative model whose latent space is used as a sampler to retrieve the nearest neighbors for the target data points.

DOMAIN GENERALIZATION

Dual Distribution Alignment Network for Generalizable Person Re-Identification

27 Jul 2020

Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.

DOMAIN GENERALIZATION GENERALIZABLE PERSON RE-IDENTIFICATION

Robust and Generalizable Visual Representation Learning via Random Convolutions

25 Jul 2020

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust.

DOMAIN GENERALIZATION REPRESENTATION LEARNING

Self-Supervised Learning Across Domains

24 Jul 2020

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own.

DOMAIN GENERALIZATION OBJECT RECOGNITION PARTIAL DOMAIN ADAPTATION SELF-SUPERVISED LEARNING

Towards Recognizing Unseen Categories in Unseen Domains

23 Jul 2020

The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories generated by mixing up the multiple source domains and categories available during training.

DOMAIN GENERALIZATION ZERO-SHOT LEARNING

Domain Generalization with Optimal Transport and Metric Learning

21 Jul 2020

Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.

ADVERSARIAL TRAINING DOMAIN GENERALIZATION METRIC LEARNING

Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

18 Jul 2020

To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains.

DOMAIN GENERALIZATION METRIC LEARNING MULTI-TASK LEARNING OBJECT RECOGNITION

Learning to Learn with Variational Information Bottleneck for Domain Generalization

15 Jul 2020

Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift.

DOMAIN GENERALIZATION META-LEARNING