Entropy Minimization vs. Diversity Maximization for Domain Adaptation
Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity maximization (MEDM) can be directly implemented by stochastic gradient descent without use of adversarial learning. Empirical evidence demonstrates that MEDM outperforms the state-of-the-art methods on four popular domain adaptation datasets.
Code (1)
Tasks
DiversityDomain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain. A common solution is to minimize the Sh…
DiversityDomain AdaptationPredictionTest-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data…
Test-time AdaptationTest-Time Adaptation to Distribution Shifts by Confidence Maximization and Input Transformation
Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data…
Test-time AdaptationTowards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
The learning of the deep networks largely relies on the data with human-annotated labels. In some label insufficient situations, the performance degrades on the decision boundary with high data density. A common solution…
DiversityDomain AdaptationSingular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation
Fully test-time adaptation (FTTA) adapts a model that is trained on a source domain to a target domain during the testing phase, where the two domains follow different distributions and source data is unavailable during …
Data AugmentationDiversityDomain AdaptationPrediction+1