Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

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.

5-Datasets

원본 태스크: Continual Learning

평가 기록 1건

AIDS

원본 태스크: Continual Learning

평가 기록 1건

cifar100

원본 태스크: Continual Learning / Class Incremental Learning / Non-exemplar-based Class Incremental Learning

평가 기록 1건

Cityscapes

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

평가 기록 1건

Cityscapes

원본 태스크: Continual Learning / Class Incremental Learning / Class-Incremental Semantic Segmentation / Overlapped 14-1

평가 기록 1건

conll2003

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

평가 기록 1건

ImageNetSubset

원본 태스크: Continual Learning / Class Incremental Learning / Non-exemplar-based Class Incremental Learning

평가 기록 1건

miniImagenet

원본 태스크: Continual Learning

평가 기록 1건

MLT17

원본 태스크: Continual Learning

평가 기록 1건

OntoNotes 5.0

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

평가 기록 1건

Rotated MNIST

원본 태스크: Continual Learning

평가 기록 1건

TinyImageNet

원본 태스크: Continual Learning / Class Incremental Learning / Non-exemplar-based Class Incremental Learning

평가 기록 1건

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