# Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering

arXiv: https://arxiv.org/abs/1901.07169 · HTML: https://mlsanity.com/paper/1901.07169/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [CoNT: Contrastive Neural Text Generation](https://mlsanity.com/paper/2205.14690/) (2022)
- [Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting](https://mlsanity.com/paper/2108.08023/) (2021)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning](https://mlsanity.com/paper/2108.09335/) (2021)
- [Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification](https://mlsanity.com/paper/2102.09321/) (2021)
- [A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networks](https://mlsanity.com/paper/2106.06420/) (2021)
- [Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methods](https://mlsanity.com/paper/2107.01130/) (2021)
- [Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting](https://mlsanity.com/paper/2402.03758/) (2024)
- [SVMax: A Feature Embedding Regularizer](https://mlsanity.com/paper/2103.02770/) (2021)
- [Towards Adversarially Robust Deep Metric Learning](https://mlsanity.com/paper/2501.01025/) (2025)

## Abstract (arXiv)

Deep metric learning has been widely applied in many computer vision tasks, and recently, it is more attractive in zero-shot image retrieval and clustering(ZSRC) where a good embedding is requested such that the unseen classes can be distinguished well. Most existing works deem this 'good' embedding just to be the discriminative one and thus race to devise powerful metric objectives or hard-sample mining strategies for leaning discriminative embedding. However, in this paper, we first emphasize that the generalization ability is a core ingredient of this 'good' embedding as well and largely affects the metric performance in zero-shot settings as a matter of fact. Then, we propose the Energy Confused Adversarial Metric Learning(ECAML) framework to explicitly optimize a robust metric. It is mainly achieved by introducing an interesting Energy Confusion regularization term, which daringly breaks away from the traditional metric learning idea of discriminative objective devising, and seeks to 'confuse' the learned model so as to encourage its generalization ability by reducing overfitting on the seen classes. We train this confusion term together with the conventional metric objective in an adversarial manner. Although it seems weird to 'confuse' the network, we show that our ECAML indeed serves as an efficient regularization technique for metric learning and is applicable to various conventional metric methods. This paper empirically and experimentally demonstrates the importance of learning embedding with good generalization, achieving state-of-the-art performances on the popular CUB, CARS, Stanford Online Products and In-Shop datasets for ZSRC tasks. textcolor[rgb]1, 0, 0Code available at http://www.bhchen.cn/.