AI Paper Atlas

Research map / Benchmarks / DomainNet

DomainNet leaderboard

68 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DomainNet. Best accuracy: 84.63 (pFedSeq, AAAI 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 · accuracy

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

#accuracy ↑MethodPaperTopic
184.63pFedSeq
ViT-B/16 + LoRA
Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning
AAAI 2025 · Table 1
Personalized and heterogeneous FL
282LUHP
ResNet-50
Low Category Uncertainty and High Training Potential Instance Learning for Unsupervised Domain Adaptation
AAAI 2024 · Table 4
Domain adaptation and generalization
381.41Bella SVGD (n=5)
CLIP ViT-B/32
Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks
AAAI 2025 · Table: vision benchmarks
Uncertainty and Gaussian processes
478.1CLIP-IRMv2
CLIP ViT-L/14
A Causal Marriage between VLM and IRM from Understanding to Reasoning
CVPR 2026 · Table 1
Multimodal LLMs
571.97LoFT (r=16)
ViT-Base
LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
ICLR 2026 · Table 2
Pruning and efficient tuning
667.65MosTMany-Objective Multi-Solution Transport
ICLR 2025 · Table: multi-task learning
Combinatorial and search optimization
766.5SFT
ViT-L/14
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
CVPR 2025 · Table 2
Domain adaptation and generalization
863.11Ours
CLIP ViT-B/16
Domain Generalization in CLIP via Learning with Diverse Text Prompts
CVPR 2025 · Table 1
Domain adaptation and generalization
963.1QT-DoG
CLIP ViT-B/16
QT-DoG: Quantization-Aware Training for Domain Generalization
ICML 2025 · Performance comparison with CL
Quantization
1062.3MoE2 (ours)
CLIP ViT-B/16
MoE^2: A Mixture-of-Mixtures of Experts for Ensemble-Free Domain Generalization
AAAI 2026 · Table 1
Domain adaptation and generalization
42 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

DomainNet · average accuracy

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

#average accuracy ↑MethodPaperTopic
180.48SGPT
ImageNet-21K pre-trained ViT-B-16
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
CVPR 2024 · Table 2
Personalized and heterogeneous FL
276.56BiLoRA (k=3000)
ViT-B/16
BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning
CVPR 2025 · Table 5
Continual fine-tuning of LLMs
371.1ForkMerge
ResNet-101
ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
NeurIPS 2023 · Table 2
Recognition and long-tail
467.78S-liPrompts
ViT-B/16
S-Prompts Learning with Pre-trained Transformers: An Occam’s Razor for Domain Incremental Learning
NeurIPS 2022 · Table 3
Domain and prompt-based
567.16DUCT
ViT-B/16 IN1K
Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
CVPR 2025 · Table 1
Domain and prompt-based
666.6RanPAC
ViT-B/16
RanPAC: Random Projections and Pre-trained Models for Continual Learning
NeurIPS 2023 · Table 3
Continual fine-tuning of LLMs
765.2FedDAP
ResNet-10
FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift
CVPR 2026 · Table 1
Personalized and heterogeneous FL
864.3DCE
ViT-B/16 IN1K
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
ICML 2025 · Table 1
Domain and prompt-based
960.13DualCP
ViT-B/16
DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
AAAI 2025 · Table 1
Domain and prompt-based
1054.68FedAFAn Aggregation-Free Federated Learning for Tackling Data Heterogeneity
CVPR 2024 · Table 2
Personalized and heterogeneous FL
6 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.