Semi-supervised Domain Adaptation via Minimax Entropy

TL;DR

This paper introduces a novel semi-supervised domain adaptation method called Minimax Entropy (MME) that effectively leverages a few labeled target samples by adversarially optimizing feature representations and classifier confidence.

Contribution

The paper proposes the MME approach that combines adversarial entropy minimization and maximization for improved semi-supervised domain adaptation performance.

Findings

Outperforms baseline methods on SSDA benchmarks

Sets new state-of-the-art results in semi-supervised domain adaptation

Demonstrates effectiveness with limited labeled target data

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. 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.