Domain Generalization Datasets

Domain generalization datasets are collections of data from multiple sources designed to train machine learning models that generalize well to unseen data distributions. Current research focuses on developing methods to learn invariant representations across domains, employing techniques like contrastive learning, active learning, and leveraging large language models for data augmentation and extrapolation beyond existing domains. This work is crucial for improving the robustness and reliability of machine learning models in real-world applications where data distributions are inherently variable, impacting fields like computer vision and beyond. The development of improved benchmarks, such as NICO++, is also a key area of focus to ensure fair and accurate evaluation of domain generalization algorithms.

Papers

March 10, 2024

Domain Adversarial Active Learning for Domain Generalization Classification
Jianting Chen, Ling Ding, Yunxiao Yang, Zaiyuan Di, Yang Xiang
Domain Generalization Domain Adversarial Domain Generalization Datasets

March 8, 2024

Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation
Yijiang Li, Sucheng Ren, Weipeng Deng, Yuzhi Xu, Ying Gao, Edith Ngai, Haohan Wang
Strong Generalization Domain Generalization Extrapolation Framework Finite Data Domain Generalization Datasets Domain Augmentation Free Domain Generalization

September 23, 2023

Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head
Alan Q. Wang, Minh Nguyen, Mert R. Sabuncu
Human Head Unseen Domain Invariant Representation Invariant Feature Novel Causal Model Nonparametric Modeling Domain Generalization Datasets

August 28, 2023

Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
Aristotelis Ballas, Christos Diou
Contrastive Learning Deep Convolutional Neural Network Domain Generalization Robust Representation Learning Domain Generalization Datasets

June 19, 2023

Shape Guided Gradient Voting for Domain Generalization
Jiaqi Xu, Yuwang Wang, Xuejin Chen
Strong Generalization Domain Generalization Domain Generalization Datasets

April 2, 2023

A principled approach to model validation in domain generalization
Boyang Lyu, Thuan Nguyen, Matthias Scheutz, Prakash Ishwar, Shuchin Aeron
Model Selection Design Principle Domain Discrepancy Model Validation Generalization Technique Domain Generalization Datasets

February 12, 2023

Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters
Yawen Cui, Zitong Yu, Rizhao Cai, Xun Wang, Alex C. Kot, Li Liu
Continual LEArning Domain Generalization Continual Learning Domain Invariant Representation Adapter Module Domain Generalization Datasets

April 17, 2022

NICO++: Towards Better Benchmarking for Domain Generalization
Xingxuan Zhang, Yue He, Renzhe Xu, Han Yu, Zheyan Shen, Peng Cui
Strong Generalization Domain Generalization Benchmark Platform Concept Shift Novel Generalization Domain Generalization Datasets