Average Incremental Accuracy: 72.45
Papers with Code · CC BY-SA 4.0
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.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
데이터셋
22개CIFAR-100 - 50 classes + 5 steps of 10 classesCIFAR-100 - 50 classes + 10 steps of 5 classesImageNet100 - 10 stepsCIFAR-100-B0(5steps of 20 classes)ImageNet - 10 stepsCIFAR100-B0(10steps of 10 classes)CIFAR-100 - 50 classes + 25 steps of 2 classesCIFAR100B020Step(5ClassesPerStep)ImageNet-100 - 50 classes + 10 steps of 5 classesImageNet-100 - 50 classes + 5 steps of 10 classesCIFAR-100 - 50 classes + 2 steps of 25 classesImageNet - 500 classes + 10 steps of 50 classes
논문
Average Incremental Accuracy: 60.18
Average Incremental Accuracy: 73.72
Average Incremental Accuracy: 70.94
Average Incremental Accuracy: 65.86
Average Incremental Accuracy: 67.95
Average Incremental Accuracy: 53.21
Average Incremental Accuracy: 63.19
Average Incremental Accuracy: 67.61
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.