# Visual Explanation for Deep Metric Learning

arXiv: https://arxiv.org/abs/1909.12977 · HTML: https://mlsanity.com/paper/1909.12977/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 14 of 14)

- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning](https://mlsanity.com/paper/2103.00370/) (2021)
- [Do Different Deep Metric Learning Losses Lead to Similar Learned Features?](https://mlsanity.com/paper/2205.02698/) (2022)
- [A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios](https://mlsanity.com/paper/2505.07622/) (2025)
- [Pairwise Matching of Intermediate Representations for Fine-grained Explainability](https://mlsanity.com/paper/2503.22881/) (2025)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [MN-Pair Contrastive Damage Representation and Clustering for Prognostic Explanation](https://mlsanity.com/paper/2301.06077/) (2023)
- [Visual Explanation via Similar Feature Activation for Metric Learning](https://mlsanity.com/paper/2506.01636/) (2025)
- [Attention-based Dynamic Subspace Learners for Medical Image Analysis](https://mlsanity.com/paper/2206.09068/) (2022)
- [Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild](https://mlsanity.com/paper/2408.13774/) (2024)
- [Transparency Techniques for Neural Networks trained on Writer Identification and Writer Verification](https://mlsanity.com/paper/2506.16331/) (2025)
- [FAME: Feature Activation Map Explanation on Image Classification and Face Recognition](https://mlsanity.com/paper/2605.12017/) (2026)
- [OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement](https://mlsanity.com/paper/2606.11233/) (2026)
- [AlignFace: Human-Aligned Face Similarity Metric with Interpretable Concept Relations](https://mlsanity.com/paper/2608.14130/) (2026)

## Abstract (arXiv)

This work explores the visual explanation for deep metric learning and its applications. As an important problem for learning representation, metric learning has attracted much attention recently, while the interpretation of such model is not as well studied as classification. To this end, we propose an intuitive idea to show where contributes the most to the overall similarity of two input images by decomposing the final activation. Instead of only providing the overall activation map of each image, we propose to generate point-to-point activation intensity between two images so that the relationship between different regions is uncovered. We show that the proposed framework can be directly deployed to a large range of metric learning applications and provides valuable information for understanding the model. Furthermore, our experiments show its effectiveness on two potential applications, i.e. cross-view pattern discovery and interactive retrieval. The source code is available at urlhttps://github.com/Jeff-Zilence/ExplainMetricLearning.