StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition
This work addresses the challenge of feature stability in visual place recognition for robotics and autonomous systems, representing an incremental improvement over existing methods.
The paper tackles the problem of extracting stable global features for visual place recognition by proposing StructVPR, a training architecture that uses segmentation images and knowledge distillation to enhance structural knowledge, achieving state-of-the-art performance on benchmarks with low computational cost.
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.