Patch-NetVLAD+: Learned patch descriptor and weighted matching strategy for place recognition
This work addresses localization confusion in visual place recognition for urban or indoor scenarios, representing an incremental improvement over existing patch-based methods.
The paper tackles the challenge of Visual Place Recognition (VPR) in similar scenes by introducing Patch-NetVLAD+, which extracts and weights local specific regions to reduce localization confusion, achieving up to 6.35% performance improvement over existing patch-based methods on datasets like Pittsburgh30k and Tokyo247.
Visual Place Recognition (VPR) in areas with similar scenes such as urban or indoor scenarios is a major challenge. Existing VPR methods using global descriptors have difficulty capturing local specific regions (LSR) in the scene and are therefore prone to localization confusion in such scenarios. As a result, finding the LSR that are critical for location recognition becomes key. To address this challenge, we introduced Patch-NetVLAD+, which was inspired by patch-based VPR researches. Our method proposed a fine-tuning strategy with triplet loss to make NetVLAD suitable for extracting patch-level descriptors. Moreover, unlike existing methods that treat all patches in an image equally, our method extracts patches of LSR, which present less frequently throughout the dataset, and makes them play an important role in VPR by assigning proper weights to them. Experiments on Pittsburgh30k and Tokyo247 datasets show that our approach achieved up to 6.35\% performance improvement than existing patch-based methods.