Why And How: Knowledge-guided Learning For Cross-spectral Image Patch Matching

Abstract

Recently, cross-spectral image patch matching based on feature relation learning has attracted extensive attention. However, performance bottleneck problems have gradually emerged in existing methods. To address this challenge, we make the first attempt to explore a stable and efficient bridge between descriptor learning and metric learning, and construct a knowledge-guided learning network (KGL-Net), which achieves amazing performance improvements while abandoning complex network structures. Specifically, we find that there is feature extraction consistency between metric learning based on feature difference learning and descriptor learning based on Euclidean distance. This provides the foundation for bridge building. To ensure the stability and efficiency of the constructed bridge, on the one hand, we conduct an in-depth exploration of 20 combined network architectures. On the other hand, a feature-guided loss is constructed to achieve mutual guidance of features. In addition, unlike

Stats

• citations0
• S2 citations—
• github stars44
• HF likes0
• heat score3.31
• arxiv keyyu2024why

Related papers

• Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
• Cross-domain Visual Matching Via Generalized Similarity Measure And Feature Learning (2016)15.54
• Unsupervised Natural Image Patch Learning (2018)8.82
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Towards Interpretable Deep Metric Learning With Structural Matching (2021)15.87
• GSSF: Generalized Structural Sparse Function For Deep Cross-modal Metric Learning (2024)7.74
• Pairingnet: A Learning-based Pair-searching And -matching Network For Image Fragments (2023)4.52
• Utilizing Complex-valued Network For Learning To Compare Image Patches (2018)0.00