# Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval

arXiv: https://arxiv.org/abs/1802.09662 · HTML: https://mlsanity.com/paper/1802.09662/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2018.

## Built on by (most cited first, 16 of 16)

- [Non-Parametric Outlier Synthesis](https://mlsanity.com/paper/2303.02966/) (2023)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards](https://mlsanity.com/paper/2405.13459/) (2024)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2201.07394/) (2022)
- [Gaussian Process on the Product of Directional Manifolds](https://mlsanity.com/paper/2303.06799/) (2023)
- [Dynamic Feature Learning and Matching for Class-Incremental Learning](https://mlsanity.com/paper/2405.08533/) (2024)
- [Von Mises-Fisher Elliptical Distribution](https://mlsanity.com/paper/2103.07948/) (2021)
- [Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering](https://mlsanity.com/paper/2108.01431/) (2021)
- [Towards Robust Feature Learning with t-vFM Similarity for Continual Learning](https://mlsanity.com/paper/2306.02335/) (2023)
- [S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localization](https://mlsanity.com/paper/2509.09110/) (2025)
- [Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States](https://mlsanity.com/paper/2603.03146/) (2026)
- [XAI and Few-shot-based Hybrid Classification Model for Plant Leaf Disease Prognosis](https://mlsanity.com/paper/2603.06676/) (2026)
- [Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing](https://mlsanity.com/paper/2608.24010/) (2026)

## Abstract (arXiv)

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.L2-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for L2-normalized embedding space, i.e., a hyper-sphere. Another challenge of current DDML methods is that their loss functions are usually based on rigid data formats, such as the triplet tuple. Thus, an extra process is needed to prepare data in specific formats. In addition, their losses are obtained from a limited number of samples, which leads to a lack of the global view of the embedding space. In this paper, we replace the Euclidean distance with the cosine similarity to better utilize the L2-normalization, which is able to attenuate the curse of dimensionality. More specifically, a novel loss function based on the von Mises-Fisher distribution is proposed to learn a compact hyper-spherical embedding space. Moreover, a new efficient learning algorithm is developed to better capture the global structure of the embedding space. Experiments for both classification and retrieval tasks on several standard datasets show that our method achieves state-of-the-art performance with a simpler training procedure. Furthermore, we demonstrate that, even with a small number of convolutional layers, our model can still obtain significantly better classification performance than the widely used softmax loss.