Pattern recognition (psychology)

Computer science

Quantum mechanics

Transfer of learning

Machine learning

Cross entropy

Weighting

Medicine

Classifier (UML)

Entropy (arrow of time)

Domain adaptation

Minification

Artificial intelligence

Programming language

Segmentation

Physics

Image segmentation

Radiology

Principle of maximum entropy

Deep neural networks for semantic segmentation always require a large number of samples with pixel-level labels, which becomes the major difficulty in their real-world applications. To reduce the labeling cost, unsupervised domain adaptation (UDA) approaches are proposed to transfer knowledge from labeled synthesized datasets to unlabeled real-world datasets. Recently, some semi-supervised learning methods have been applied to UDA and achieved state-of-the-art performance. One of the most popular approaches in semi-supervised learning is the entropy minimization method. However, when applying the entropy minimization to UDA for semantic segmentation, the gradient of the entropy is biased towards samples that are easy to transfer. To balance the gradient of well-classified target samples, we propose the maximum squares loss. Our maximum squares loss prevents the training process being dominated by easy-to-transfer samples in the target domain. Besides, we introduce the image-wise weighting ratio to alleviate t...

Domain Adaptation for Semantic Segmentation With Maximum Squares Loss