International Journal of Intelligent Systems · 2022 · 13 citations · 25 references
ComputingComputer ScienceComputer VisionMachine LearningStatistical LearningDeep LearningLoss FunctionOptimization For Machine LearningUnsupervised LearningDomain AdaptationDomain Adaptation For Semantic SegmentationModel RegularizationPseudo-labelingRegularizationSelf-training
Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, thus easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective. It can be achieved via a simple additional regularization or an energy-based loss. This framework allows us to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. The convergence property and its connection with classification expectation minimization are investigated. We deliver extensive experiments on the most popular and large-scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.
25
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi et al. · 2017 · 15.5K citations
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts, Mohamed Omran, Sebastian Ramos et al. · 2016 · 11.9K citations
Adversarial Discriminative Domain Adaptation
Eric Tzeng, Judy Hoffman, Kate Saenko et al. · 2017 · 5K citations