SRDC

2000년 도입 · 논문 1편에서 사용

Structurally Regularized Deep Clustering, or SRDC, is a deep network based discriminative clustering method for domain adaptation that minimizes the KL divergence between predictive label distribution of the network and an introduced auxiliary one. Replacing the auxiliary distribution with that formed by ground-truth labels of source data implements the structural source regularization via a simple strategy of joint network training.

출처: Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

소개 논문: Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering