# Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales

arXiv: https://arxiv.org/abs/2103.11781 · HTML: https://mlsanity.com/paper/2103.11781/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [Precise Detection in Densely Packed Scenes](https://mlsanity.com/paper/1904.00853/) (2019)
- [Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification](https://mlsanity.com/paper/1904.00537/) (2019)
- [SVDNet for Pedestrian Retrieval](https://mlsanity.com/paper/1703.05693/) (2017)
- [Products-10K: A Large-scale Product Recognition Dataset](https://mlsanity.com/paper/2008.10545/) (2020)
- [RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification](https://mlsanity.com/paper/2006.12634/) (2020)
- [Vehicle Re-identification Using Quadruple Directional Deep Learning Features](https://mlsanity.com/paper/1811.05163/) (2018)

## Built on by (most cited first, 11 of 11)

- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [Delving into Semantic Scale Imbalance](https://mlsanity.com/paper/2212.14613/) (2022)
- [Optimization of Rank Losses for Image Retrieval](https://mlsanity.com/paper/2309.08250/) (2023)
- [Hierarchical Average Precision Training for Pertinent Image Retrieval](https://mlsanity.com/paper/2207.04873/) (2022)
- [Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels](https://mlsanity.com/paper/2311.11019/) (2023)
- [Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization](https://mlsanity.com/paper/2210.01908/) (2022)
- [Fine-Grained Domain Generalization with Feature Structuralization](https://mlsanity.com/paper/2406.09166/) (2024)
- [Hierarchical Image Classification with A Literally Toy Dataset](https://mlsanity.com/paper/2111.00892/) (2021)
- [Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels](https://mlsanity.com/paper/2502.19816/) (2025)
- [CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification](https://mlsanity.com/paper/2309.01483/) (2023)
- [Dynamic Contrastive Learning for Hierarchical Retrieval: A Case Study of Distance-Aware Cross-View Geo-Localization](https://mlsanity.com/paper/2506.23077/) (2025)

## Abstract (arXiv)

This paper introduces a new fundamental characteristic, ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic quality of a metric tool, indicating its flexibility to accommodate various scales. Larger dynamic range offers higher flexibility. In visual recognition, the multiple scale problem also exist. Different visual concepts may have different semantic scales. For example, ``Animal'' and ``Plants'' have a large semantic scale while ``Elk'' has a much smaller one. Under a small semantic scale, two different elks may look quite different to each other . However, under a large semantic scale (eg, animals and plants), these two elks should be measured as being similar. %We argue that such flexibility is also important for deep metric learning, because different visual concepts indeed correspond to different semantic scales. Introducing the dynamic range to deep metric learning, we get a novel computer vision task, ie, the Dynamic Metric Learning. It aims to learn a scalable metric space to accommodate visual concepts across multiple semantic scales. Based on three types of images, i.e., vehicle, animal and online products, we construct three datasets for Dynamic Metric Learning. We benchmark these datasets with popular deep metric learning methods and find Dynamic Metric Learning to be very challenging. The major difficulty lies in a conflict between different scales: the discriminative ability under a small scale usually compromises the discriminative ability under a large one, and vice versa. As a minor contribution, we propose Cross-Scale Learning (CSL) to alleviate such conflict. We show that CSL consistently improves the baseline on all the three datasets. The datasets and the code will be publicly available at https://github.com/SupetZYK/DynamicMetricLearning.