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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 1371 papers

Title	Date	Tasks	Status	Hype
The Bayesian Approach to Continual Learning: An Overview	Jul 11, 2025	Bayesian Inferenceclass-incremental learning	—Unverified	0
Balancing the Past and Present: A Coordinated Replay Framework for Federated Class-Incremental Learning	Jul 10, 2025	class-incremental learningClass Incremental Learning	—Unverified	0
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts	Jul 9, 2025	Continual LearningIncremental Learning	CodeCode Available	0
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic	Jun 26, 2025	Autonomous DrivingAvg	—Unverified	0
Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation	Jun 12, 2025	class-incremental learningClass Incremental Learning	—Unverified	0
Hyperbolic Dual Feature Augmentation for Open-Environment	Jun 10, 2025	class-incremental learningClass Incremental Learning	—Unverified	0
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning	Jun 1, 2025	class-incremental learningClass Incremental Learning	CodeCode Available	0
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning	May 30, 2025	class-incremental learningClass Incremental Learning	CodeCode Available	1
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection	May 29, 2025	class-incremental learningClass Incremental Learning	—Unverified	0
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need	May 29, 2025	Allimage-classification	CodeCode Available	0

Show:10 25 50

← PrevPage 1 of 138Next →

All datasets CIFAR-100 - 50 classes + 5 steps of 10 classes CIFAR-100 - 50 classes + 10 steps of 5 classes ImageNet100 - 10 steps CIFAR-100-B0(5steps of 20 classes)ImageNet - 10 steps CIFAR100-B0(10steps of 10 classes)CIFAR-100 - 50 classes + 25 steps of 2 classes CIFAR100B020Step(5ClassesPerStep)ImageNet-100 - 50 classes + 10 steps of 5 classes ImageNet-100 - 50 classes + 5 steps of 10 classes CIFAR-100 - 50 classes + 2 steps of 25 classes ImageNet - 500 classes + 10 steps of 50 classes

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	View-Batch(TCIL)	Average Incremental Accuracy	79.23	—	Unverified
2	TCIL	Average Incremental Accuracy	77.72	—	Unverified
3	TCIL-Lite	Average Incremental Accuracy	76.96	—	Unverified
4	DER(w/o P)	Average Incremental Accuracy	76.8	—	Unverified
5	BiC	Average Incremental Accuracy	73.1	—	Unverified
6	WA	Average Incremental Accuracy	72.81	—	Unverified
7	iCaRL	Average Incremental Accuracy	71.14	—	Unverified
8	RPSNet	Average Incremental Accuracy	70.5	—	Unverified
9	PODNet	Average Incremental Accuracy	66.7	—	Unverified
10	UCIR	Average Incremental Accuracy	62.77	—	Unverified