AI Paper Atlas

Research map / Benchmarks / Office-31 A→W

Office-31 A→W leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Office-31 A→W. Best accuracy: 98.6 (GCA, AAAI 2026).

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 A→W · accuracy

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

#accuracy ↑MethodPaperTopic
198.6GCAGCA: Geometry-aware Conditional Alignment for Partial Domain Adaptation with Coding Rate Reduction
AAAI 2026 · Table 1
Domain adaptation and generalization
297.8RLGLC
ResNet-50
On the Transferability and Discriminability of Representation Learning in Unsupervised Domain Adaptation
TPAMI 2025 · Table (Office-31)
Domain adaptation and generalization
397.6CoVi
ResNet-50
Contrastive Vicinal Space for Unsupervised Domain Adaptation
ECCV 2022 · Table 1
Domain adaptation and generalization
496.4STAFF
ResNet-50
Structure-Aware Feature Fusion for Unsupervised Domain Adaptation
AAAI 2020 · Table 2
Domain adaptation and generalization
595.5Ours (Affine)
ResNet-50
Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization Bounds
ICML 2026 · Table 1
Domain adaptation and generalization
695.1HMA(CAN)
ResNet-50
Homeomorphism Alignment for Unsupervised Domain Adaptation
ICCV 2023 · Table 6
Domain adaptation and generalization
794.3TADA (local+global)
ResNet-50
Transferable Attention for Domain Adaptation
AAAI 2019 · Table 1
Domain adaptation and generalization
893.6BDG
ResNet-50
Bi-Directional Generation for Unsupervised Domain Adaptation
AAAI 2020 · Table 1
Domain adaptation and generalization
992.5Transfer Score regularizer
ResNet-50
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
ICLR 2024 · Table: Evaluation using TS as
Domain adaptation and generalization
1092.5TAT
ResNet-50
Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
ICML 2019 · Table 1
Domain adaptation and generalization
11 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.