Unsupervised Scene Adaptation with Memory Regularization in vivo

Abstract

We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the intra-domain knowledge and inherent uncertainty learned by the network are under-explored. In this paper, we propose an orthogonal method, called memory regularization in vivo to exploit the intra-domain knowledge and regularize the model training. Specifically, we refer to the segmentation model itself as the memory module, and minor the discrepancy of the two classifiers, i.e., the primary classifier and the auxiliary classifier, to reduce the prediction inconsistency. Without extra parameters, the proposed method is complementary to the most existing domain adaptation methods and could generally improve the performance of existing methods. Albeit simple, we verify the effectiveness of memory regularization on two synthetic-to-real benchmarks: GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, yielding +11.1% and +11.3% mIoU improvement over the baseline model, respectively. Besides, a similar +12.0% mIoU improvement is observed on the cross-city benchmark: Cityscapes -> Oxford RobotCar.

arXiv comment7 pages, 4 figures, 6 tables (accepted by IJCAI 2020)

References in corpus (5)

• Distilling the Knowledge in a Neural Network
• Temporal Ensembling for Semi-Supervised Learning
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Dual Graph Convolutional Network for Semantic Segmentation
• Confidence Regularized Self-Training

Cited by in corpus (15)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
• Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images
• Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
• I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation
• Multi-source Pseudo-label Learning of Semantic Segmentation for the Scene Recognition of Agricultural Mobile Robots
• Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation
• Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
• ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
• More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
• Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task
• Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint