AI Paper Atlas

Research map / Benchmarks / Omniglot

Omniglot leaderboard

19 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Omniglot. Best accuracy: 99.4 (SEN WRN PN, ECCV 2020).

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.

Omniglot · accuracy

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

#accuracy ↑MethodPaperTopic
199.4SEN WRN PN
WRN
SEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks
ECCV 2020 · Table 1
Zero-/few-shot and meta-learning
295.71Ours (M = 5)Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies
CVPR 2023 · Table 1
Neural architecture search
394.4URTA Universal Representation Transformer Layer for Few-Shot Image Classification
ICLR 2021 · Meta-Dataset results table
Zero-/few-shot and meta-learning
489.62Res. adapt. decay
ResNet28
Learning multiple visual domains with residual adapters
NeurIPS 2017 · Table 1
Human and embodied modeling
589.61MetaAugment
WRN-28-10
MetaAugment: Sample-Aware Data Augmentation Policy Learning
AAAI 2021 · Table: Omniglot
Visual and representation RL
689.25Parallel SVD
ResNet-26
Efficient Parametrization of Multi-Domain Deep Neural Networks
CVPR 2018 · Table 1
Pruning and efficient tuning
788.91Ours
ResNet-26
Incremental Multi-Domain Learning with Network Latent Tensor Factorization
AAAI 2020 · Table: Comparison to the state
Domain and prompt-based
888.5PACOH-NN
BNN
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
ICML 2021 · Table 3
Uncertainty and Gaussian processes
988.4CNAPS
ResNet18
Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes
NeurIPS 2019 · Table 1
Test-time adaptation
1087.46AdaFilter
ResNet-50 (ImageNet)
AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning
AAAI 2020 · Table 2
Pruning and efficient tuning
9 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.