SOTAVerified

Incremental Learning

Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.

Papers

Showing 1–10 of 1371 papers

TitleStatusHype
The Bayesian Approach to Continual Learning: An Overview—0
Balancing the Past and Present: A Coordinated Replay Framework for Federated Class-Incremental Learning—0
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative ExpertsCode0
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic—0
Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation—0
Hyperbolic Dual Feature Augmentation for Open-Environment—0
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental LearningCode0
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental LearningCode1
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection—0
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You NeedCode0
Show:102550
← PrevPage 1 of 138Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1View-Batch(DER)Average Incremental Accuracy76.95—Unverified
2TCIL-LiteAverage Incremental Accuracy75.47—Unverified
3TCILAverage Incremental Accuracy75.11—Unverified
4DER(ResNet-18)Average Incremental Accuracy73.98—Unverified
5FOSTERAverage Incremental Accuracy70.65—Unverified