SOTAVerified

Class Incremental Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 634 papers

TitleStatusHype
PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental LearningCode0
CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental LearningCode1
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental LearningCode4
Class Balance Matters to Active Class-Incremental LearningCode0
Integrating Dual Prototypes for Task-Wise Adaption in Pre-Trained Model-Based Class-Incremental Learning—0
Soft-TransFormers for Continual LearningCode0
Class-Incremental Learning for Sound Event Localization and Detection—0
Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning—0
Inductive Graph Few-shot Class Incremental Learning—0
An Efficient Memory Module for Graph Few-Shot Class-Incremental LearningCode0
Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis—0
Covariance-based Space Regularization for Few-shot Class Incremental LearningCode0
Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection—0
EXACFS -- A CIL Method to mitigate Catastrophic Forgetting—0
Similarity-based context aware continual learning for spiking neural networksCode0
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative ModelingsCode0
Plastic Learning with Deep Fourier Features—0
Closed-form merging of parameter-efficient modules for Federated Continual Learning—0
TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning—0
Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning—0
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting ApproachCode1
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free AdaptorCode0
CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental LearningCode1
Brain-inspired continual pre-trained learner via silent synaptic consolidation—0
Fair Class-Incremental Learning using Sample Weighting—0
Show:102550
← PrevPage 5 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