Reproduce “Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Li Zhong, Zhen Fang, Feng Liu, Bo Yuan, Guangquan Zhang, Jie Lu
The authors develop an unsupervised open-set domain adaptation method for classifying known and pooled unknown target images. It floors the open-set risk term and uses class-aware adversarial alignment between source examples and high-confidence target examples predicted as known. On Office-31, it reports a six-task average of 92.3% OS accuracy, versus 89.1% for SCA-SCM; individual directions vary.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.