AI Paper Atlas

Research map / Benchmarks / MNIST → MNIST-M

MNIST → MNIST-M leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MNIST → MNIST-M. Best accuracy: 99.4 (SBADA-GAN, CVPR 2018).

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.

MNIST → MNIST-M · accuracy

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

#accuracy ↑MethodPaperTopic
199.4SBADA-GANFrom Source to Target and Back: Symmetric Bi-Directional Adaptive GAN
CVPR 2018 · Table 1
Domain adaptation and generalization
298.9DIRT-T
VADA
A DIRT-T Approach to Unsupervised Domain Adaptation
ICLR 2018 · Table 1
Domain adaptation and generalization
398.5Our ModelModel Adaptation: Unsupervised Domain Adaptation Without Source Data
CVPR 2020 · Table 1
Domain adaptation and generalization
498.03DANN-CAGotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
CVPR 2019 · Table: Evaluation on UDA tasks
Domain adaptation and generalization
595.6Ours with L_ATDeep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
ECCV 2018 · Table 1
Domain adaptation and generalization
694.9DASPOTOn Scalable and Efficient Computation of Large Scale Optimal Transport
ICML 2019 · Domain Adaptation Experiments
Optimal transport
794.62Class-guided OTNeural Optimal Transport with General Cost Functionals
ICLR 2024 · Table: Accuracy of the maps le
Optimal transport
894.12d-SNE, semi-supervisedd-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding
CVPR 2019 · Digits comparison table
Domain adaptation and generalization
994OursAsymmetric Tri-training for Unsupervised Domain Adaptation
ICML 2017 · Table 1
Domain adaptation and generalization
1079.1VADA + classifier orthogonalization
VADA
Controlling Directions Orthogonal to a Classifier
ICLR 2022 · domain adaptation table
Domain adaptation and generalization

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