SOTAVerified

Class Incremental Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 634 papers

TitleStatusHype
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental LearningCode4
External Knowledge Injection for CLIP-Based Class-Incremental LearningCode2
Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter FusionCode2
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language ModelsCode2
Pre-trained Vision and Language Transformers Are Few-Shot Incremental LearnersCode2
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental LearningCode2
Class-incremental Learning for Time Series: Benchmark and EvaluationCode2
PILOT: A Pre-Trained Model-Based Continual Learning ToolboxCode2
Class-Incremental Learning: A SurveyCode2
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental LearningCode2
Supervised Contrastive LearningCode2
Three scenarios for continual learningCode2
Learning without ForgettingCode2
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental LearningCode1
PrePrompt: Predictive prompting for class incremental learningCode1
Adaptive Decision Boundary for Few-Shot Class-Incremental LearningCode1
Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-TrainingCode1
Reducing Class-wise Confusion for Incremental Learning with Disentangled ManifoldsCode1
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental LearningCode1
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental LearningCode1
Task-Agnostic Guided Feature Expansion for Class-Incremental LearningCode1
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity GroupingCode1
Navigating Semantic Drift in Task-Agnostic Class-Incremental LearningCode1
Continuous Knowledge-Preserving Decomposition for Few-Shot Continual LearningCode1
MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware ClassificationCode1
Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality CalibrationCode1
Revisiting Generative Replay for Class Incremental Object DetectionCode1
Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental LearningCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental LearningCode1
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting ApproachCode1
CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental LearningCode1
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental LearningCode1
A preliminary study on continual learning in computer vision using Kolmogorov-Arnold NetworksCode1
AIR: Analytic Imbalance Rectifier for Continual LearningCode1
Mitigating Background Shift in Class-Incremental Semantic SegmentationCode1
Exemplar-free Continual Representation Learning via Learnable Drift CompensationCode1
Rethinking Few-shot Class-incremental Learning: Learning from YourselfCode1
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental LearningCode1
OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental LearningCode1
TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental LearningCode1
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental LearningCode1
Revisiting Neural Networks for Continual Learning: An Architectural PerspectiveCode1
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision TransformersCode1
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformerCode1
Generative Multi-modal Models are Good Class-Incremental LearnersCode1
OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental LearningCode1
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental LearningCode1
GACL: Exemplar-Free Generalized Analytic Continual LearningCode1
Text-Enhanced Data-free Approach for Federated Class-Incremental LearningCode1
Show:102550
← PrevPage 1 of 13Next →
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