RADA: Robust and Accurate Feature Learning with Domain Adaptation

TL;DR

RADA introduces a multi-level feature aggregation network with domain adaptation and Transformer-based boosting to improve robustness and accuracy in local feature learning under challenging conditions.

Contribution

It proposes a novel hierarchical architecture with domain adaptation supervision and a Transformer-based booster for robust feature learning across domains.

Findings

Achieves state-of-the-art results in image matching.

Improves camera pose estimation accuracy.

Enhances visual localization robustness.

Abstract

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as significant appearance changes and domain shifts. In this study, we introduce a multi-level feature aggregation network that incorporates two pivotal components to facilitate the learning of robust and accurate features with domain adaptation. First, we employ domain adaptation supervision to align high-level feature distributions across different domains to achieve invariant domain representations. Second, we propose a Transformer-based booster that enhances descriptor robustness by integrating visual and geometric information through wave position encoding concepts, effectively handling complex conditions. To ensure the accuracy and robustness of features, we adopt a hierarchical architecture to capture comprehensive information and apply meticulous targeted supervision to keypoint detection, descriptor extraction, and their coupled processing. Extensive experiments demonstrate that our method, RADA, achieves excellent results in image matching, camera pose estimation, and visual localization tasks.