Correlation Alignment for Unsupervised Domain Adaptation

6 Dec 2016Baochen SunJiashi FengKate Saenko

In this chapter, we present CORrelation ALignment (CORAL), a simple yet effective method for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Domain Adaptation Office-Caltech CORAL[[Sun, Feng, and Saenko2017]] Average Accuracy 84.7 # 8