SOTAVerified

Class Incremental Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–225 of 634 papers

TitleStatusHype
Toward industrial use of continual learning : new metrics proposal for class incremental learning—0
Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark—0
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision TransformersCode1
Future-Proofing Class Incremental Learning—0
Pre-trained Vision and Language Transformers Are Few-Shot Incremental LearnersCode2
Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning—0
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformerCode1
Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach—0
OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental LearningCode1
Towards Non-Exemplar Semi-Supervised Class-Incremental Learning—0
Generative Multi-modal Models are Good Class-Incremental LearnersCode1
Recommendation of data-free class-incremental learning algorithms by simulating future data—0
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental LearningCode0
Enhancing Visual Continual Learning with Language-Guided Supervision—0
Exemplar-Free Class Incremental Learning via Incremental Representation—0
GACL: Exemplar-Free Generalized Analytic Continual LearningCode1
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental LearningCode1
Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature RichnessCode0
Defying Imbalanced Forgetting in Class Incremental Learning—0
A Bag of Tricks for Few-Shot Class-Incremental Learning—0
Text-Enhanced Data-free Approach for Federated Class-Incremental LearningCode1
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning—0
NTK-Guided Few-Shot Class Incremental LearningCode1
Confidence Self-Calibration for Multi-Label Class-Incremental Learning—0
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental LearningCode2
Show:102550
← PrevPage 9 of 26Next →
All datasetscifar100CIFAR-100 - 50 classes + 10 steps of 5 classesCIFAR-100 - 50 classes + 5 steps of 10 classesCifar100-B0(10 tasks)-no-exemplarsCifar100-B0(20 tasks)-no-exemplarsCIFAR100-B0(50 tasks)-no-exemplars

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1S&B10-stage average accuracy68.18—Unverified
2SCR10-stage average accuracy65.98—Unverified
3iCaRL10-stage average accuracy63.24—Unverified
4LUCIR10-stage average accuracy56.53—Unverified
5ABD10-stage average accuracy54.44—Unverified
6EWC10-stage average accuracy50.53—Unverified
7EMR10-stage average accuracy48.66—Unverified
8A-GEM10-stage average accuracy45.76—Unverified
#ModelMetricClaimedVerifiedStatus
1PPCA-SWSLFinal Accuracy77.07—Unverified
2PPCA-CLIPFinal Accuracy69.71—Unverified
#ModelMetricClaimedVerifiedStatus
1PPCA-SWSLFinal Accuracy77.07—Unverified
2PPCA-CLIPFinal Accuracy69.71—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy61.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy56.2—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy42.6—Unverified