Semi-Supervised Domain Adaptation via Minimax Entropy

Citations Over TimeTop 1% of 2019 papers

Abstract

Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target domain. To address this semi-supervised domain adaptation (SSDA) setting, we propose a novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model. Our base model consists of a feature encoding network, followed by a classification layer that computes the features' similarity to estimated prototypes (representatives of each class). Adaptation is achieved by alternately maximizing the conditional entropy of unlabeled target data with respect to the classifier and minimizing it with respect to the feature encoder. We empirically demonstrate the superiority of our method over many baselines, including conventional feature alignment and few-shot methods, setting a new state of the art for SSDA. Our code is available at http://cs-people.bu.edu/keisaito/research/MME.html.

Related Papers

• → Letter to the Editor—Some Aspects of a Minimax Location Problem(1967)62 cited
• → Minimax and maximin efficient designs for estimating the location-shift parameter of parallel models with dual responses(2005)3 cited
• → Interplay of minimax estimation and minimax support recovery under sparsity(2018)6 cited
• → Asymptotic Minimax Theory for Estimating Location(2009)
• Minimax image detection from noisy tomographic data(2011)