Recent Posts
Archives
Tags
- Contrastive Domain Discrepancy
- 이것이 취업을 위한 코딩테스트다
- CodeUp6015
- Class Aware Sampling
- Feature Augmentation
- Pseudo Label
- CVPR2021
- ComputerVision
- Segmentation Map
- CodeUp6013
- Attention
- ICLR2021
- Semi Supervised Learning
- transformer
- ViT
- CodeUp6012
- Baekjoon
- 코드업
- Maximum Mean Discrepancy
- CodeUp6011
- Python
- 비전공자를 위한 HTML/CSS
- CodeUp6014
- Vision Transformer
- CodeUp
- 백준
- Computer Vision
- Domain Adaptation
- Consistency Regularization
- CodeUp6016
Link
목록Contrastive Domain Discrepancy (1)
IT 정리용 블로그!
[논문] Contrastive Adaptation Network for Unsupervised Domain Adaptation 설명, 정리
Contrastive Domain Discrepancy(CDD) : intra-class discrepancy는 줄이고 inter-class discrepancy는 늘린다. P(ϕ(Xs)|Ys)와 Q(ϕ(Xt)|Yt)의 차이를 측정한다. DH(P,Q). 평균값의 차를 이용. ˆDc1,c2(ˆyt1,ˆyt2,...,ˆytnt,ϕ)=e1+e2−2e3. c1=c2일 때는 intra-class discrepancy 측정. Ø는 feature representation. 첫 feature \(c_{1} \neq c_{..
Computer Vision
2021. 7. 16. 22:06