# Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

arXiv: https://arxiv.org/abs/1904.02616 · HTML: https://mlsanity.com/paper/1904.02616/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 32)

- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Towards Interpretable Deep Metric Learning with Structural Matching](https://mlsanity.com/paper/2108.05889/) (2021)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Do Different Deep Metric Learning Losses Lead to Similar Learned Features?](https://mlsanity.com/paper/2205.02698/) (2022)
- [Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models](https://mlsanity.com/paper/2107.12250/) (2021)
- [Searching for Structure in Unfalsifiable Claims](https://mlsanity.com/paper/2209.00495/) (2022)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations](https://mlsanity.com/paper/2311.18575/) (2023)
- [Potential Field Based Deep Metric Learning](https://mlsanity.com/paper/2405.18560/) (2024)
- [GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning](https://mlsanity.com/paper/2410.15266/) (2024)
- [Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learning](https://mlsanity.com/paper/2211.11751/) (2022)
- [DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection](https://mlsanity.com/paper/2510.22622/) (2025)
- [Semi-Supervised Metric Learning: A Deep Resurrection](https://mlsanity.com/paper/2105.05061/) (2021)
- [Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methods](https://mlsanity.com/paper/2107.01130/) (2021)
- [Construct Informative Triplet with Two-stage Hard-sample Generation](https://mlsanity.com/paper/2112.02259/) (2021)
- [Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning](https://mlsanity.com/paper/2211.16264/) (2022)
- [Structural Alignment Improves Graph Test-Time Adaptation](https://mlsanity.com/paper/2502.18334/) (2025)
- [Metric Learning for Session-based Recommendations](https://mlsanity.com/paper/2101.02655/) (2021)
- [CORN: Co-Trained Full- And No-Reference Speech Quality Assessment](https://mlsanity.com/paper/2310.09388/) (2023)
- [DCAE-SR: Design of a Denoising Convolutional Autoencoder for reconstructing Electrocardiograms signals at Super Resolution](https://mlsanity.com/paper/2404.15307/) (2024)
- [All You Need to Know About Training Image Retrieval Models](https://mlsanity.com/paper/2503.13045/) (2025)
- [Variational Learning of Disentangled Representations](https://mlsanity.com/paper/2506.17182/) (2025)
- [Introspective Deep Metric Learning for Image Retrieval](https://mlsanity.com/paper/2205.04449/) (2022)
- [Topological Graph Signal Compression](https://mlsanity.com/paper/2308.11068/) (2023)
- [Explainable Metric Learning for Deflating Data Bias](https://mlsanity.com/paper/2407.04866/) (2024)
- [Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering](https://mlsanity.com/paper/2507.10088/) (2025)

## Abstract (arXiv)

Deep metric learning, which learns discriminative features to process image clustering and retrieval tasks, has attracted extensive attention in recent years. A number of deep metric learning methods, which ensure that similar examples are mapped close to each other and dissimilar examples are mapped farther apart, have been proposed to construct effective structures for loss functions and have shown promising results. In this paper, different from the approaches on learning the loss structures, we propose a robust SNR distance metric based on Signal-to-Noise Ratio (SNR) for measuring the similarity of image pairs for deep metric learning. By exploring the properties of our SNR distance metric from the view of geometry space and statistical theory, we analyze the properties of our metric and show that it can preserve the semantic similarity between image pairs, which well justify its suitability for deep metric learning. Compared with Euclidean distance metric, our SNR distance metric can further jointly reduce the intra-class distances and enlarge the inter-class distances for learned features. Leveraging our SNR distance metric, we propose Deep SNR-based Metric Learning (DSML) to generate discriminative feature embeddings. By extensive experiments on three widely adopted benchmarks, including CARS196, CUB200-2011 and CIFAR10, our DSML has shown its superiority over other state-of-the-art methods. Additionally, we extend our SNR distance metric to deep hashing learning, and conduct experiments on two benchmarks, including CIFAR10 and NUS-WIDE, to demonstrate the effectiveness and generality of our SNR distance metric.