# Towards Improved and Interpretable Deep Metric Learning via Attentive Grouping

arXiv: https://arxiv.org/abs/2011.08877 · HTML: https://mlsanity.com/paper/2011.08877/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees](https://mlsanity.com/paper/2209.07225/) (2022)
- [Group Contrastive Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2107.09787/) (2021)
- [Boosting Factorization Machines via Saliency-Guided Mixup](https://mlsanity.com/paper/2206.08661/) (2022)
- [GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence](https://mlsanity.com/paper/2307.09810/) (2023)

## Abstract (arXiv)

Grouping has been commonly used in deep metric learning for computing diverse features. However, current methods are prone to overfitting and lack interpretability. In this work, we propose an improved and interpretable grouping method to be integrated flexibly with any metric learning framework. Our method is based on the attention mechanism with a learnable query for each group. The query is fully trainable and can capture group-specific information when combined with the diversity loss. An appealing property of our method is that it naturally lends itself interpretability. The attention scores between the learnable query and each spatial position can be interpreted as the importance of that position. We formally show that our proposed grouping method is invariant to spatial permutations of features. When used as a module in convolutional neural networks, our method leads to translational invariance. We conduct comprehensive experiments to evaluate our method. Our quantitative results indicate that the proposed method outperforms prior methods consistently and significantly across different datasets, evaluation metrics, base models, and loss functions. For the first time to the best of our knowledge, our interpretation results clearly demonstrate that the proposed method enables the learning of distinct and diverse features across groups. The code is available on https://github.com/XinyiXuXD/DGML-master.