Min-Max Statistical Alignment for Transfer Learning
A profound idea in learning invariant features for transfer learning is to align statistical properties of the domains. In practice, this is achieved by minimizing the disparity between the domains, usually measured in terms of their statistical properties. We question the capability of this school of thought and propose to minimize the maximum disparity between domains. Furthermore, we develop an end-to-end learning scheme that enables us to benefit from the proposed min-max strategy in training deep models. We show that the min-max solution can outperform the existing statistical alignment solutions, and can compete with state-of-the-art solutions on two challenging learning tasks, namely, Unsupervised Domain Adaptation (UDA) and Zero-Shot Learning (ZSL).
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationTransfer LearningUnsupervised Domain AdaptationZero-Shot LearningSimilar Papers 제목 키워드 기반
End-to-End Neural Word Alignment Outperforms GIZA++
Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT …
Machine TranslationTranslationWord AlignmentA Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment
Word alignment and machine translation are two closely related tasks. Neural translation models, such as RNN-based and Transformer models, employ a target-to-source attention mechanism which can provide rough word alignm…
Machine TranslationTranslationWord AlignmentBilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of dif…
Cross-Lingual TransferLanguage ModellingMachine Reading ComprehensionReading Comprehension+2Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora
This paper describes a method for the automatic inference of structural transfer rules to be used in a shallow-transfer machine translation (MT) system from small parallel corpora. The structural transfer rules are based…
Machine TranslationSentenceTranslationWord TranslationAugmenting and Aligning Snippets for Few-Shot Video Domain Adaptation
For video models to be transferred and applied seamlessly across video tasks in varied environments, Video Unsupervised Domain Adaptation (VUDA) has been introduced to improve the robustness and transferability of video …
Action RecognitionDomain AdaptationUnsupervised Domain Adaptation