Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

07/14/2022
by   Zhengkai Jiang, et al.
9

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning method for unsupervised domain adaptive semantic segmentation. Previous domain adaptation methods merely consider the alignment of the intra-class representational distributions across various domains, while the inter-class structural relationship is insufficiently explored, resulting in the aligned representations on the target domain might not be as easily discriminated as done on the source domain anymore. Instead, ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation. By considering the same class prototypes as positives and other class prototypes as negatives to achieve class-centered distribution alignment, ProCA achieves state-of-the-art performance on classical domain adaptation tasks, {\em i.e., GTA5 $\to$ Cityscapes \text{and} SYNTHIA $\to$ Cityscapes}. Code is available at \href{https://github.com/jiangzhengkai/ProCA}{ProCA}

READ FULL TEXT
research
03/08/2021

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

Multi-source unsupervised domain adaptation (MSDA) aims at adapting mode...
research
11/26/2022

1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsuperv...
research
11/28/2019

Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

Existing domain adaptation methods aim at learning features that can be ...
research
07/20/2021

DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation

Unsupervised domain adaptation (UDA) for semantic segmentation aims to a...
research
07/22/2022

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

This paper studies a new, practical but challenging problem, called Clas...
research
03/23/2021

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

Previous feature alignment methods in Unsupervised domain adaptation(UDA...
research
03/25/2023

Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation

Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers ...

Please sign up or login with your details

Forgot password? Click here to reset