Semi-supervised Domain Adaptation via Minimax Entropy

04/13/2019
by   Kuniaki Saito, et al.
6

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.

READ FULL TEXT

page 8

page 11

research
10/18/2021

Dynamic Feature Alignment for Semi-supervised Domain Adaptation

Most research on domain adaptation has focused on the purely unsupervise...
research
08/15/2023

Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts

Time domain astronomy is advancing towards the analysis of multiple mass...
research
06/05/2021

Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Contemporary domain adaptive semantic segmentation aims to address data ...
research
01/01/2013

Semi-Supervised Domain Adaptation with Non-Parametric Copulas

A new framework based on the theory of copulas is proposed to address se...
research
12/12/2021

Semi-supervised Domain Adaptive Structure Learning

Semi-supervised domain adaptation (SSDA) is quite a challenging problem ...
research
01/19/2021

Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics

In this paper, we propose a novel domain adaptation method for the sourc...
research
11/05/2017

Few-Shot Adversarial Domain Adaptation

This work provides a framework for addressing the problem of supervised ...

Please sign up or login with your details

Forgot password? Click here to reset