Semi-supervised Domain Adaptation via Minimax Entropy

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.

accepted to ICCV2019. ICCV paper version

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Prototypical Networks for Few-shot Learning
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• Domain Separation Networks
• Adversarial Discriminative Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Good Semi-supervised Learning that Requires a Bad GAN
• A Closer Look at Few-shot Classification
• Maximum-Entropy Fine-Grained Classification

Cited by in corpus (10)

• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
• Adversarial-Learned Loss for Domain Adaptation
• Dynamic Scale Inference by Entropy Minimization
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Partial Domain Adaptation Using Graph Convolutional Networks
• Unsupervised Domain Expansion for Visual Categorization
• Unsupervised Domain Adaptation: A Reality Check
• Hard Class Rectification for Domain Adaptation
• Learning to smell for wellness