TCDesc: Learning Topology Consistent Descriptors
Honghu Pan, Fanyang Meng, Zhenyu He, Yongsheng Liang, Wei Liu

TL;DR
This paper introduces a novel topology-aware triplet loss that incorporates topology measures alongside Euclidean distance to learn more consistent local descriptors, improving performance on benchmark datasets.
Contribution
It proposes a new topology vector and topology distance to enhance triplet loss by considering topological relations among descriptors.
Findings
Outperforms state-of-the-art methods on multiple benchmarks.
Effectively improves descriptor matching accuracy.
Enhances triplet loss with topology information.
Abstract
Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptors, which neglects the topology similarity between two descriptor sets. In this paper, we propose topology measure besides Euclidean distance to learn topology consistent descriptors by considering kNN descriptors of positive sample. First we establish a novel topology vector for each descriptor followed by Locally Linear Embedding (LLE) to indicate the topological relation among the descriptor and its kNN descriptors. Then we define topology distance between descriptors as the difference of their topology vectors. Last we employ the dynamic weighting strategy to fuse Euclidean distance and topology distance of matching descriptors and take the fusion result as the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Video Analysis and Summarization
MethodsTriplet Loss
