AI Paper Atlas

Research map / Benchmarks / VisDA-2017

VisDA-2017 leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VisDA-2017. Best accuracy: 98.4 (MOT, CVPR 2023).

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.

VisDA-2017 · accuracy

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

#accuracy ↑MethodPaperTopic
198.4MOT
ResNet-50
MOT: Masked Optimal Transport for Partial Domain Adaptation
CVPR 2023 · Table 3
Domain adaptation and generalization
289.7PDA
ViT
Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation
AAAI 2024 · Table: Comparisons with SOTA m
Domain adaptation and generalization
387.2DAC-MR (gamma=1, lambda=1)
ResNet-101
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
TPAMI 2026 · Table 5
Zero-/few-shot and meta-learning
486.1kSHOT UB sigma=0.0
ResNet-101
Prior Knowledge Guided Unsupervised Domain Adaptation
ECCV 2022 · Table 2
Domain adaptation and generalization
584.6LUHP
ResNet-101
Low Category Uncertainty and High Training Potential Instance Learning for Unsupervised Domain Adaptation
AAAI 2024 · Table 3
Domain adaptation and generalization
682.6CDAN+RBN
ResNet-101
Reducing Divergence in Batch Normalization for Domain Adaptation
AAAI 2025 · Table 4
Domain adaptation and generalization
782.3MDD+UTEP
ResNet-101
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
ECCV 2022 · Table 4
Domain adaptation and generalization
881.5GSDA
ResNet50
Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization
CVPR 2020 · Table 4
Domain adaptation and generalization
980.6DALN
ResNet-101
Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation
CVPR 2022 · Table 1
Domain adaptation and generalization
1079.5SEEBS+
ViT-B/16 (MAE)
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
ICCV 2023 · Table 3
Domain adaptation and generalization
7 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.