# The Group Loss for Deep Metric Learning

arXiv: https://arxiv.org/abs/1912.00385 · HTML: https://mlsanity.com/paper/1912.00385/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2019.

## Built on by (most cited first, 20 of 20)

- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://mlsanity.com/paper/2108.11179/) (2021)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [Noise-resistant Deep Metric Learning with Ranking-based Instance Selection](https://mlsanity.com/paper/2103.16047/) (2021)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Integrating Language Guidance into Vision-based Deep Metric Learning](https://mlsanity.com/paper/2203.08543/) (2022)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [Hierarchical Proxy-based Loss for Deep Metric Learning](https://mlsanity.com/paper/2103.13538/) (2021)
- [Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap](https://mlsanity.com/paper/2303.06484/) (2023)
- [Granularity-aware Adaptation for Image Retrieval over Multiple Tasks](https://mlsanity.com/paper/2210.02254/) (2022)
- [The Group Loss++: A deeper look into group loss for deep metric learning](https://mlsanity.com/paper/2204.01509/) (2022)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [Identifying Ambiguous Similarity Conditions via Semantic Matching](https://mlsanity.com/paper/2204.04053/) (2022)
- [Large-to-small Image Resolution Asymmetry in Deep Metric Learning](https://mlsanity.com/paper/2210.05463/) (2022)
- [Instance-Level Generation for Representation Learning](https://mlsanity.com/paper/2510.09171/) (2025)
- [Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering](https://mlsanity.com/paper/2108.01431/) (2021)
- [Shadow loss: Memory-linear deep metric learning for efficient training](https://mlsanity.com/paper/2311.14012/) (2023)
- [Realigned Softmax Warping for Deep Metric Learning](https://mlsanity.com/paper/2408.15656/) (2024)
- [Boosting CNN-based Handwriting Recognition Systems with Learnable Relaxation Labeling](https://mlsanity.com/paper/2409.05699/) (2024)
- [Geometric 2D Scene Graph Generation](https://mlsanity.com/paper/2607.22325/) (2026)

## Abstract (arXiv)

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles