# Deep Metric Learning Beyond Binary Supervision

arXiv: https://arxiv.org/abs/1904.09626 · HTML: https://mlsanity.com/paper/1904.09626/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2019.

## Built on by (most cited first, 30 of 36)

- [How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?](https://mlsanity.com/paper/2203.04450/) (2022)
- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [On Semantic Similarity in Video Retrieval](https://mlsanity.com/paper/2103.10095/) (2021)
- [Data-efficient Large Scale Place Recognition with Graded Similarity Supervision](https://mlsanity.com/paper/2303.11739/) (2023)
- [Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings](https://mlsanity.com/paper/2502.01108/) (2025)
- [LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments](https://mlsanity.com/paper/2104.09169/) (2021)
- [Generalized Contrastive Optimization of Siamese Networks for Place Recognition](https://mlsanity.com/paper/2103.06638/) (2021)
- [HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization](https://mlsanity.com/paper/2212.14258/) (2022)
- [Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging](https://mlsanity.com/paper/2502.14064/) (2025)
- [Embedding Transfer with Label Relaxation for Improved Metric Learning](https://mlsanity.com/paper/2103.14908/) (2021)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [CoNT: Contrastive Neural Text Generation](https://mlsanity.com/paper/2205.14690/) (2022)
- [REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning](https://mlsanity.com/paper/2311.00519/) (2023)
- [RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data](https://mlsanity.com/paper/2411.18822/) (2024)
- [Utilizing Expert Features for Contrastive Learning of Time-Series Representations](https://mlsanity.com/paper/2206.11517/) (2022)
- [Self-Taught Metric Learning without Labels](https://mlsanity.com/paper/2205.01903/) (2022)
- [Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining](https://mlsanity.com/paper/2312.12661/) (2023)
- [Practical Relative Order Attack in Deep Ranking](https://mlsanity.com/paper/2103.05248/) (2021)
- [Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval](https://mlsanity.com/paper/2105.03647/) (2021)
- [Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval](https://mlsanity.com/paper/2211.07116/) (2022)
- [Efficient Malware Analysis Using Metric Embeddings](https://mlsanity.com/paper/2212.02663/) (2022)
- [DAS: Densely-Anchored Sampling for Deep Metric Learning](https://mlsanity.com/paper/2208.00119/) (2022)
- [SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval](https://mlsanity.com/paper/2111.05814/) (2021)
- [Multi-Head Deep Metric Learning Using Global and Local Representations](https://mlsanity.com/paper/2112.14327/) (2021)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Prompt Augmentation for Self-supervised Text-guided Image Manipulation](https://mlsanity.com/paper/2412.13081/) (2024)
- [Learning to Generate Novel Classes for Deep Metric Learning](https://mlsanity.com/paper/2201.01008/) (2022)
- [Deep Metric Learning-Based Semi-Supervised Regression With Alternate Learning](https://mlsanity.com/paper/2202.11388/) (2022)
- [Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2309.08944/) (2023)
- [Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches](https://mlsanity.com/paper/2312.08230/) (2023)

## Abstract (arXiv)

Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and is not sufficient to represent semantic similarity between images described by continuous and/or structured labels such as object poses, image captions, and scene graphs. Motivated by this, we present a novel method for deep metric learning using continuous labels. First, we propose a new triplet loss that allows distance ratios in the label space to be preserved in the learned metric space. The proposed loss thus enables our model to learn the degree of similarity rather than just the order. Furthermore, we design a triplet mining strategy adapted to metric learning with continuous labels. We address three different image retrieval tasks with continuous labels in terms of human poses, room layouts and image captions, and demonstrate the superior performance of our approach compared to previous methods.