Overview

Metric learning studies how to shape similarity so that distances in a representation reflect the relationships that matter for a task. Common approaches include contrastive, triplet, proxy, and angular-margin losses, alongside learned Mahalanobis, manifold, and optimal-transport distances. These methods support image and cross-modal retrieval, person re-identification, few-shot classification, clustering, and open-set recognition, with evaluations often measuring retrieval ranking, recognition accuracy, and robustness to domain shift. A central challenge is making learned geometries expressive enough to capture task-specific structure while remaining stable under scarce or noisy labels and generalizing to unfamiliar data.

Latest papers

92 papers11 papers in the last four weeks, up 10% on the four weeks before. 0.1% of all new papers.

Dec 15, 2024

Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching

Recently, cross-spectral image patch matching based on feature relation learning has attracted extensive attention. However, existing methods focus on mining richer feature relations by building complex relation extraction structures. Meanwhile, performance bottlenecks have gradually emerged. To address this, 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 significant 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 existing methods, we consider that the feature mapping ability of the metric branch should receive more attention. Therefore, a hard negative sample mining for metric learning (HNSM-M) strategy is constructed. To the best of our knowledge, this is the first time that hard negative sample mining for metric networks has been implemented and brings significant performance gains. Extensive experimental results show that our KGL-Net achieves SOTA performance in multiple cross-spectral image patch matching datasets. Our code is available at https://github.com/YuChuang1205/KGL-Net
Dec 4, 2023

Metric Learning with Quantum Feature Spaces

The 2N2^N dimensions of Hilbert space give quantum metric learning exponentially many mutually orthogonal states with which to separate classes, but the same exponential dimension also degrades its optimization landscape and the tractability of evaluating its metric. By letting a classical network predict all gate parameters of a fixed ansatz, we isolate the reachable state manifold and its fidelity metric. We prove that this separability is already present on the unentangled manifold Munentangled=(CP1)N\mathbb{M}_{\text{unentangled}} = (\mathbb{CP}^1)^N, which saturates the 2N2^N maximal orthogonal capacity needed for classification, while entanglement adds states only at intermediate separations, which are costly to resolve under finite sampling. The same size carries costs. Global fidelity causes exponential gradient collapse across both unentangled (Θ(c−N)Θ(c^{-N})) and entangled (Θ(4−N)Θ(4^{-N})) manifolds; as fidelities concentrate, the fidelity signal-to-noise ratio at a fixed shot budget also decays exponentially in NN; and because Munentangled\mathbb{M}_{\text{unentangled}} already holds 2N2^N orthogonal states, expressive, unconstrained encoders under contrastive losses reach trivial minima by geometric shattering even without entanglement. We introduce Quantum Projective Metric Learning (QPMeL), an exact O(N)O(N) closed-form kernel on Munentangled\mathbb{M}_{\text{unentangled}} that circumvents circuit simulation. QPMeL resolves gradient collapse via a curriculum annealing from a 11-local observable regime (restoring Θ(1/N2)Θ(1/N^2) polynomial variance) to the global product kernel. Empirically, QPMeL as a complete design exceeds eight and matches two of 11 published quantum few-shot designs.