AI Paper Atlas

Research map / Benchmarks / Digits

Digits leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Digits. Best accuracy: 99.76 (GTWIDL, TPAMI 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.

Digits · accuracy

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

#accuracy ↑MethodPaperTopic
199.76GTWIDLGeneralized Time Warping Invariant Dictionary Learning for Time Series Classification and Clustering
TPAMI 2025 · Table 3
Foundation models for time series
298.25Bandit-BOBayesian Optimization for Categorical and Category-Specific Continuous Inputs
AAAI 2020 · Table: Classification accuracy
Bayesian optimization
397.6ALDA (δ=0.6)Adversarial-Learned Loss for Domain Adaptation
AAAI 2020 · Digits results table
Domain adaptation and generalization
497.1Jeffreys-DDOn $f$-Divergence Principled Domain Adaptation: An Improved Framework
NeurIPS 2024 · Digits results table
Domain adaptation and generalization
595.9IWCDAN
CDAN
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
NeurIPS 2020 · Table 1
Domain adaptation and generalization
694.4SLAPS (FP)SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
NeurIPS 2021 · Table 2
GNN architectures
793.2IDGL-Anch
GCN
Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
NeurIPS 2020 · Transductive results table
Graph self-supervised learning
892.5kNN-LDS
GCN
Learning Discrete Structures for Graph Neural Networks
ICML 2019 · Table 1
GNN architectures
990.42psi_OvA,hinge, FspwlinBayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
NeurIPS 2020 · Table 2
Prediction and decision losses
1085.34GRCL
LeNet-5
Gradient Regularized Contrastive Learning for Continual Domain Adaptation
AAAI 2021 · Table: ACC and BWT on three co
Domain and prompt-based
2 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.