SOTAVerified

Multi-class Classification

Multi-class classification is a type of supervised learning where the goal is to assign an input to one of three or more distinct classes. Unlike binary classification (which has only two classes), multi-class classification handles multiple labels and uses algorithms like logistic regression, decision trees, random forests, SVMs, or neural networks to predict the correct category based on the features of the input data.

Papers

Showing 401410 of 903 papers

TitleStatusHype
Self-Supervision and Multi-Task Learning: Challenges in Fine-Grained COVID-19 Multi-Class Classification from Chest X-rays0
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and AdaptivityCode0
The SAMME.C2 algorithm for severely imbalanced multi-class classification0
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class AnnealingCode0
Contrastive Learning for Fair Representations0
Flat and Nested Negation and Uncertainty Detection with PubMed BERT0
Logically at Factify 2022: Multimodal Fact Verification0
Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning ModelsCode0
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep ClassifiersCode0
ARGUABLY at ComMA@ICON: Detection of Multilingual Aggressive, Gender Biased, and Communally Charged Tweets Using Ensemble and Fine-Tuned IndicBERT0
Show:102550
← PrevPage 41 of 91Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1COVID-CXNetAccuracy (%)94.2Unverified
#ModelMetricClaimedVerifiedStatus
1COVID-ResNetF1 score0.9Unverified
#ModelMetricClaimedVerifiedStatus
1SVM (tficf)Macro F173.9Unverified
#ModelMetricClaimedVerifiedStatus
1Extra TreesF1-Score93.36Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Model EnsembleMean AUC0.99Unverified