# Class-Specific Variational Auto-Encoder for Content-Based Image Retrieval

arXiv: https://arxiv.org/abs/2304.11734 · HTML: https://mlsanity.com/paper/2304.11734/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 23 Apr 2023.

## Builds on (most cited first, 7 of 7)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval](https://mlsanity.com/paper/1805.08587/) (2018)
- [Image Retrieval with Fisher Vectors of Binary Features](https://mlsanity.com/paper/1609.08291/) (2016)
- [Multilinear Class-Specific Discriminant Analysis](https://mlsanity.com/paper/1710.10695/) (2017)
- [Probabilistic Class-Specific Discriminant Analysis](https://mlsanity.com/paper/1812.05980/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Scalable Vector Graphics Latent Space](https://mlsanity.com/paper/2608.21893/) (2026)

## Abstract (arXiv)

Using a discriminative representation obtained by supervised deep learning methods showed promising results on diverse Content-Based Image Retrieval (CBIR) problems. However, existing methods exploiting labels during training try to discriminate all available classes, which is not ideal in cases where the retrieval problem focuses on a class of interest. In this paper, we propose a regularized loss for Variational Auto-Encoders (VAEs) forcing the model to focus on a given class of interest. As a result, the model learns to discriminate the data belonging to the class of interest from any other possibility, making the learnt latent space of the VAE suitable for class-specific retrieval tasks. The proposed Class-Specific Variational Auto-Encoder (CS-VAE) is evaluated on three public and one custom datasets, and its performance is compared with that of three related VAE-based methods. Experimental results show that the proposed method outperforms its competition in both in-domain and out-of-domain retrieval problems.