AI Paper Atlas

Research map / Benchmarks / DomainNet average

DomainNet average leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DomainNet average. Best accuracy: 82.14 (TIDE, CVPR 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

DomainNet average · accuracy

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
182.14TIDE
ResNet-18
TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction
CVPR 2025 · Table 1d
Test-time adaptation
263.6UniMoS
CLIP ViT-B
Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
CVPR 2024 · Table 3
CLIP and zero-shot
362.8SLACK
ResNet-18
SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization
CVPR 2023 · Table: DomainNet
Visual and representation RL
453SIG
ResNet101
Subspace Identification for Multi-Source Domain Adaptation
NeurIPS 2023 · Table 3
Domain adaptation and generalization
551.1FedWon
AlexNet
FedWon: Triumphing Multi-domain Federated Learning Without Normalization
ICLR 2024 · Table 1
Personalized and heterogeneous FL
651.1KD3A
ResNet101
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
ICML 2021 · DomainNet results table
Domain adaptation and generalization
748.08FedOTP
ViT B16
Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
CVPR 2024 · Table 2
Personalized and heterogeneous FL
847.4LtC-MSDALearning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
ECCV 2020 · Table 3
Domain adaptation and generalization
941.9MiRe
ResNet-18
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
NeurIPS 2022 · DomainNet results table
Domain adaptation and generalization
1034.16SCI-PD
ResNet18
PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
CVPR 2024 · Table 3
Domain adaptation and generalization
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.