AI Paper Atlas

Research map / Benchmarks / Office-31

Office-31 leaderboard

24 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Office-31. Best accuracy: 92.7 (CSR, AAAI 2024).

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.

Office-31 · accuracy

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

#accuracy ↑MethodPaperTopic
192.7CSR
ResNet-50
Cycle Self-Refinement for Multi-Source Domain Adaptation
AAAI 2024 · Table 1
Domain adaptation and generalization
292.44Ours
ResNet-50
Sample Selection for Universal Domain Adaptation
AAAI 2021 · Table 5
Domain adaptation and generalization
391.9DATE (SHOT)
SHOT
Discriminability and Transferability Estimation: A Bayesian Source Importance Estimation Approach for Multi-Source-Free Domain Adaptation
AAAI 2023 · Table 1
Domain adaptation and generalization
491.7Ours
ResNet50
Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
NeurIPS 2021 · Table 1
Domain adaptation and generalization
591.2DVD
ResNet-50
Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
NeurIPS 2025 · SFDA comparison table
Domain adaptation and generalization
691.2PDA
ViT-B/16
Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation
AAAI 2024 · Table: Comparisons with prompt
Domain adaptation and generalization
791.1RSDA-MSTN
MSTN
Spherical Space Domain Adaptation With Robust Pseudo-Label Loss
CVPR 2020 · Table 1
Domain adaptation and generalization
891.02HCLD²*
ResNet-50
UFDA: Universal Federated Domain Adaptation with Practical Assumptions
AAAI 2024 · Table 1
Domain adaptation and generalization
991CSCA
ResNet-50
Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation
AAAI 2025 · Table 1
Domain adaptation and generalization
1091DANN + MMI + COT
ResNet-50
COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport
CVPR 2023 · Table 1
Domain adaptation and generalization
14 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.