ImageNet Top-1 Accuracy: 67.6
Papers with Code · CC BY-SA 4.0
Contrastive Learning
Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.
It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.
<span style="color:grey; opacity: 0.6">(Image credit: Schroff et al. 2015)</span>
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
4개논문
ImageNet Top-1 Accuracy: 69.3
ImageNet Top-1 Accuracy: 63.8
ImageNet Top-1 Accuracy: 71.1
ImageNet Top-1 Accuracy: 61.3
ImageNet Top-1 Accuracy: 60.2
ImageNet Top-1 Accuracy: 73.6
ImageNet Top-1 Accuracy: 60.6
ImageNet Top-1 Accuracy: 61.5
ImageNet Top-1 Accuracy: 63.6
ImageNet Top-1 Accuracy: 73
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.