SOTAVerified

Class Incremental Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 476–500 of 634 papers

TitleStatusHype
Semantic-visual Guided Transformer for Few-shot Class-incremental Learning—0
Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning—0
Similarity-based context aware continual learning for spiking neural networks—0
Singular Value Fine-tuning for Few-Shot Class-Incremental Learning—0
Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning—0
S-LoRA: Scalable Low-Rank Adaptation for Class Incremental Learning—0
Space-time Prompting for Video Class-incremental Learning—0
SRIL: Selective Regularization for Class-Incremental Learning—0
StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning—0
Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning—0
Striking a Balance Between Stability and Plasticity for Class-Incremental Learning—0
Susceptibility of Continual Learning Against Adversarial Attacks—0
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces—0
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts—0
TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning—0
Taxonomic Class Incremental Learning—0
T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning—0
Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection—0
The Bayesian Approach to Continual Learning: An Overview—0
The Championship-Winning Solution for the 5th CLVISION Challenge 2024—0
The impact of model size on catastrophic forgetting in Online Continual Learning—0
TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning—0
TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning—0
Topology-Preserving Class-Incremental Learning—0
Toward industrial use of continual learning : new metrics proposal for class incremental learning—0
Show:102550
← PrevPage 20 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