Hardness-Aware Deep Metric Learning

Abstract

This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.

Accepted as CVPR 2019 Oral. Source code available at https://github.com/wzzheng/HDML

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Deep Embeddings with Histogram Loss

Cited by in corpus (6)

• Unsupervised Deep Metric Learning via Auxiliary Rotation Loss
• Instance Cross Entropy for Deep Metric Learning
• Towards Visually Explaining Similarity Models
• Adapting Grad-CAM for Embedding Networks
• Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning