Zero-shot Metric Learning

Zero-shot Metric Learning

Xinyi Xu, Huanhuan Cao, Yanhua Yang, Erkun Yang, Cheng Deng

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 3996-4002. https://doi.org/10.24963/ijcai.2019/555

In this work, we tackle the zero-shot metric learning problem and propose a novel method abbreviated as ZSML, with the purpose to learn a distance metric that measures the similarity of unseen categories (even unseen datasets). ZSML achieves strong transferability by capturing multi-nonlinear yet continuous relation among data. It is motivated by two facts: 1) relations can be essentially described from various perspectives; and 2) traditional binary supervision is insufficient to represent continuous visual similarity. Specifically, we first reformulate a collection of specific-shaped convolutional kernels to combine data pairs and generate multiple relation vectors. Furthermore, we design a new cross-update regression loss to discover continuous similarity. Extensive experiments including intra-dataset transfer and inter-dataset transfer on four benchmark datasets demonstrate that ZSML can achieve state-of-the-art performance.
Keywords:
Machine Learning: Multi-instance;Multi-label;Multi-view learning
Machine Learning: Dimensionality Reduction and Manifold Learning