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

03/23/2021
by   Shiyu Tang, et al.
11

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.

READ FULL TEXT

page 5

page 9

07/14/2022

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on ...
08/09/2022

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

Unsupervised domain adaptation for point cloud semantic segmentation has...
04/18/2022

Unsupervised Contrastive Domain Adaptation for Semantic Segmentation

Semantic segmentation models struggle to generalize in the presence of d...
04/20/2022

CALI: Coarse-to-Fine ALIgnments Based Unsupervised Domain Adaptation of Traversability Prediction for Deployable Autonomous Navigation

Traversability prediction is a fundamental perception capability for aut...
10/11/2021

Domain Adaptive Semantic Segmentation with Regional Contrastive Consistency Regularization

Unsupervised domain adaptation (UDA) aims to bridge the domain shift bet...
04/03/2020

RANSAC-Flow: generic two-stage image alignment

This paper considers the generic problem of dense alignment between two ...
06/27/2022

A Novel Unified Self-alignment Method of SINS Based on FGO

The self-alignment process can provide an accurate initial attitude of S...