PK PyTorchKR Papers
Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋
하위 태스크
5
평가표
33
보존된 평가 기록
133

Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.

Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review

평가 결과

데이터셋과 평가 조건을 선택해 성능·논문·코드를 비교하세요. 보존된 Papers with Code 기록으로, 최신 순위는 아닙니다.

ASC (19 tasks)

원본 태스크: Continual Learning

평가 기록 15건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 10-1

평가 기록 13건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 15-5

평가 기록 13건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 15-1

평가 기록 13건

mini-Imagenet

원본 태스크: Continual Learning / Class Incremental Learning / Few-Shot Class-Incremental Learning

평가 기록 12건

CIFAR-100

원본 태스크: Continual Learning / Class Incremental Learning / Few-Shot Class-Incremental Learning

평가 기록 11건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Disjoint 15-1

평가 기록 9건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Disjoint 15-5

평가 기록 9건

ADE20K

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 100-5

평가 기록 8건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Disjoint 10-1

평가 기록 8건

ADE20K

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 100-50

평가 기록 7건

ADE20K

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 50-50

평가 기록 7건

cifar100

원본 태스크: Continual Learning / Class Incremental Learning

평가 기록 7건

ADE20K

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 100-10

평가 기록 6건

CUB-200-2011

원본 태스크: Continual Learning / Class Incremental Learning / Few-Shot Class-Incremental Learning

평가 기록 6건

DSC (10 tasks)

원본 태스크: Continual Learning

평가 기록 6건

PASCAL VOC 2012

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 5-3

평가 기록 4건

TiROD

원본 태스크: Continual Learning / TiROD

평가 기록 4건

Permuted MNIST

원본 태스크: Continual Learning

평가 기록 3건

2010 i2b2/VA

원본 태스크: Continual Learning / Continual Named Entity Recognition / FG-1-PG-1

평가 기록 1건

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.