# Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification

arXiv: https://arxiv.org/abs/2007.13547 · HTML: https://mlsanity.com/paper/2007.13547/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [Class-Level Logit Perturbation](https://mlsanity.com/paper/2209.05668/) (2022)
- [Altering Backward Pass Gradients improves Convergence](https://mlsanity.com/paper/2111.12495/) (2021)
- [Online Deep Learning based on Auto-Encoder](https://mlsanity.com/paper/2201.07383/) (2022)
- [Multimorbidity Content-Based Medical Image Retrieval Using Proxies](https://mlsanity.com/paper/2211.12185/) (2022)
- [Semantic-embedded Similarity Prototype for Scene Recognition](https://mlsanity.com/paper/2308.05896/) (2023)
- [Multi-Label Takagi-Sugeno-Kang Fuzzy System](https://mlsanity.com/paper/2309.11469/) (2023)
- [Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook](https://mlsanity.com/paper/2607.00839/) (2026)

## Abstract (arXiv)

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively. To capture the relationships between image features and labels, we aim to learn a two-way deep distance metric over the embedding space from two different views, i.e., the distance between one image and its labels is not only smaller than those distances between the image and its labels' nearest neighbors, but also smaller than the distances between the labels and other images corresponding to the labels' nearest neighbors. Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. Our model can be trained in an end-to-end manner. Experimental results on publicly available image datasets corroborate the efficacy of our method compared with the state-of-the-arts.