Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning

Abstract

Previous feature alignment methods in Unsupervised domain adaptation(UDA) mostly only align global features without considering the mismatch between class-wise features. In this work, we propose a new coarse-to-fine feature alignment method using contrastive learning called CFContra. It draws class-wise features closer than coarse feature alignment or class-wise feature alignment only, therefore improves the model's performance to a great extent. We build it upon one of the most effective methods of UDA called entropy minimization to further improve performance. In particular, to prevent excessive memory occupation when applying contrastive loss in semantic segmentation, we devise a new way to build and update the memory bank. In this way, we make the algorithm more efficient and viable with limited memory. Extensive experiments show the effectiveness of our method and model trained on the GTA5 to Cityscapes dataset has boost mIOU by 3.5 compared to the MinEnt algorithm. Our code will be publicly available.

References in corpus (9)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Bootstrap your own latent: A new approach to self-supervised Learning
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Exploring Simple Siamese Representation Learning
• Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Image to Image Translation for Domain Adaptation
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation