008 20151221 Return of Frustrating Easy Domain AdaptationHa Phuong
The document proposes a simple and effective method called CORrelation ALignment (CORAL) for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of the source and target distributions without requiring any target labels. The method whitens the source distribution and recolors it with the target covariance matrix. Experiments on object recognition and sentiment analysis tasks show CORAL outperforms other unsupervised domain adaptation methods.
008 20151221 Return of Frustrating Easy Domain AdaptationHa Phuong
The document proposes a simple and effective method called CORrelation ALignment (CORAL) for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of the source and target distributions without requiring any target labels. The method whitens the source distribution and recolors it with the target covariance matrix. Experiments on object recognition and sentiment analysis tasks show CORAL outperforms other unsupervised domain adaptation methods.
[Paper Reading] Learning Distributed Representations for Structured Output Pr...Yusuke Iwasawa
1) The document proposes a new method called DISTRO that uses distributed representations for structured output prediction tasks.
2) DISTRO represents labels as dense real-valued vectors rather than one-hot vectors, and defines compositionality of labels using tensor products of label vectors.
3) Experiments on document classification and part-of-speech tagging show that DISTRO outperforms baselines by learning label vectors that capture similarities between labels.
[Paper Reading] Learning Distributed Representations for Structured Output Pr...Yusuke Iwasawa
1) The document proposes a new method called DISTRO that uses distributed representations for structured output prediction tasks.
2) DISTRO represents labels as dense real-valued vectors rather than one-hot vectors, and defines compositionality of labels using tensor products of label vectors.
3) Experiments on document classification and part-of-speech tagging show that DISTRO outperforms baselines by learning label vectors that capture similarities between labels.
2. 書誌情報
• Proc. NIPS2015 and arXiv
• arXivの方が若干詳しいのでオススメ
• Authours:
• Antti Ramsus, Harri Valpola, Mikko Honkala, Mathias Berglund, and Tapani
Raiko
• #citations: 10
• 選定理由
• 精度が良い
• 半教師、教師なし学習界隈の戦いがすごい