Domain Adaptation of Learned Features for Visual Localization
This addresses the problem of domain gaps in visual localization for robotics or autonomous systems, offering a practical solution with minimal data, though it is incremental as it builds on existing learned features.
The paper tackles visual localization under changing conditions by proposing a few-shot domain adaptation framework for learned local features, achieving superior performance over baselines with only a few target domain examples.
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have shown superior performance over classical hand-crafted local features. However, in a real-world scenario, there often exists a large domain gap between training and target images, which can significantly degrade the localization accuracy. While existing methods utilize a large amount of data to tackle the problem, we present a novel and practical approach, where only a few examples are needed to reduce the domain gap. In particular, we propose a few-shot domain adaptation framework for learned local features that deals with varying conditions in visual localization. The experimental results demonstrate the superior performance over baselines, while using a scarce number of training examples from the target domain.