Papers with Code 아카이브
cross-domain few-shot learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
Its essence is transfer learning. The model needs to be trained in the source domain and then migrated to the target domain. Compliant with (1) the category in the target domain has never appeared in the source domain (2) the data distribution of the target domain is inconsistent with the source domain (3) each class in the target domain has very few labels
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Open-Debin/MetaQDA_Pub
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
https://github.com/hushell/pmf_cvpr22
https://github.com/jimzai/deta
https://github.com/leezhp1994/TMHFS
A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning
https://github.com/nobody-1617/deta
https://github.com/phecy/SSL-FEW-SHOT
https://github.com/sungnyun/cd-fsl
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
https://github.com/yangyucheng000/MSpaper/tree/main/unisiam
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.