Ranked List Loss for Deep Metric Learning
The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the m...
| Main Authors: | , , , , , |
|---|---|
| Format: | Other Non-Article Part of Journal/Newspaper |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://pure.qub.ac.uk/en/publications/ranked-list-loss-for-deep-metric-learning(1efa7f64-9d44-4619-940b-6e3ac4d4abed).html https://pureadmin.qub.ac.uk/ws/files/168412256/RankedNoise.pdf |
| Summary: | The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, rankingmotivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we present two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. Consequently, some useful examples are ignored and the structure is less informative. To address this, we propose to build a setbased similarity structure by exploiting all instances in the gallery. The samples are split into a positive and a negative set. Our objective is to make the query closer to the positive set than to the negative set by a margin. Second, previous methods aim to pull positive pairs as close as possible in the embedding space. As a result, the intraclass data distribution might be dropped. In contrast, we propose to learn a hypersphere for each class in order to preserve the similarity structure inside it. Our extensive experiments show that the proposed method achieves state-of-the-art performance on three widely used benchmarks. |
|---|