Domain Adaptation for Semantic Segmentation with Maximum Squares Loss

Abstract

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 the class imbalance in the unlabeled target domain. Both synthetic-to-real and cross-city adaptation experiments demonstrate the effectiveness of our proposed approach. The code is released at https://github. com/ZJULearning/MaxSquareLoss.

Published in IEEE International Conference on Computer Vision (ICCV) 2019

References in corpus (10)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Adversarial Discriminative Domain Adaptation
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Cited by in corpus (6)

• Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• On Universal Black-Box Domain Adaptation
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Transferring and Regularizing Prediction for Semantic Segmentation
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation