Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled target data, which raises the question: How can we validate unsupervised adaptation techniques in a realistic way? We first empirically analyze existing criteria and demonstrate that they are not very effective for tuning hyper-parameters. Intuitively, a well-trained source classifier should embed target samples of the same class nearby, forming dense neighborhoods in feature space. Based on this assumption, we propose a novel unsupervised validation criterion that measures the density of soft neighborhoods by computing the entropy of the similarity distribution between points. Our criterion is simpler than competing validation methods, yet more effective; it can tune hyper-parameters and the number of training iterations in both image classification and semantic segmentation models. The code used for the paper will be available at \url{https://github.com/VisionLearningGroup/SND}.
Code (2)
Tasks
Domain Adaptationimage-classificationImage ClassificationSemantic SegmentationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Domain Adaptation with BERT-based Domain Classification and Data Selection
The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data. For example, the pre-trained BERT model can be easily fine-tuned with just one additional o…
ClassificationDomain Adaptationdomain classificationGeneral ClassificationModel Selection with Nonlinear Embedding for Unsupervised Domain Adaptation
Domain adaptation deals with adapting classifiers trained on data from a source distribution, to work effectively on data from a target distribution. In this paper, we introduce the Nonlinear Embedding Transform (NET) fo…
Domain AdaptationGeneral ClassificationModel SelectionUnsupervised Domain AdaptationTowards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation
Unsupervised domain adaptation (UDA) in semantic segmentation transfers the knowledge of the source domain to the target one to improve the adaptability of the segmentation model in the target domain. The need to acc…
Domain AdaptationSemantic SegmentationSource-Free Domain AdaptationUnsupervised Domain AdaptationUnsupervised Domain Adaptation in the Absence of Source Data
Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is…
Domain AdaptationUnsupervised Domain AdaptationRobust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation
The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with co…
Domain AdaptationObjectSemantic SegmentationUnsupervised Domain Adaptation