Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
arXiv:2104.11056
Abstract
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge the domain gap by aligning the features of structurally similar label patches across domains. As a result, the networks are easier to train and deliver better performance. Our approach consistently outperforms state-of-the-art unsupervised and semi-supervised methods on two challenging domain adaptive segmentation tasks, particularly with a small number of target domain annotations. It can also be naturally extended to weakly-supervised domain adaptation, where only a minor drop in accuracy can save up to 75% of annotation cost.
References in corpus (6)
- A Simple Framework for Contrastive Learning of Visual Representations
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Beyond Sharing Weights for Deep Domain Adaptation
- Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
- Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
Cited by in corpus (5)
- CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
- Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
- Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation
- Learning to Align Sequential Actions in the Wild
- REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter