Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

07/22/2022
by   Geon Lee, et al.
0

We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation is to learn domain-invariant and discriminative features without target ground-truth labels. To this end, we propose a bi-directional pixel-prototype contrastive learning framework that minimizes intra-class variations of features for the same object class, while maximizing inter-class variations for different ones, regardless of domains. Specifically, our framework aligns pixel-level features and a prototype of the same object class in target and source images (i.e., positive pairs), respectively, sets them apart for different classes (i.e., negative pairs), and performs the alignment and separation processes toward the other direction with pixel-level features in the source image and a prototype in the target image. The cross-domain matching encourages domain-invariant feature representations, while the bidirectional pixel-prototype correspondences aggregate features for the same object class, providing discriminative features. To establish training pairs for contrastive learning, we propose to generate dynamic pseudo labels of target images using a non-parametric label transfer, that is, pixel-prototype correspondences across different domains. We also present a calibration method compensating class-wise domain biases of prototypes gradually during training.

READ FULL TEXT

page 9

page 12

page 14

page 22

page 23

research
11/24/2021

SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning

Although there is significant progress in supervised semantic segmentati...
research
04/29/2023

Regularizing Self-training for Unsupervised Domain Adaptation via Structural Constraints

Self-training based on pseudo-labels has emerged as a dominant approach ...
research
04/18/2022

Unsupervised Contrastive Domain Adaptation for Semantic Segmentation

Semantic segmentation models struggle to generalize in the presence of d...
research
06/22/2021

Give Me Your Trained Model: Domain Adaptive Semantic Segmentation without Source Data

Benefited from considerable pixel-level annotations collected from a spe...
research
08/12/2022

Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation

In unsupervised domain adaptive (UDA) semantic segmentation, the distill...
research
04/19/2022

SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation

Domain adaptive semantic segmentation attempts to make satisfactory dens...
research
06/20/2022

Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation

This paper proposes a novel pixel-level distribution regularization sche...

Please sign up or login with your details

Forgot password? Click here to reset