# Discriminative Regularization for Generative Models

arXiv: https://arxiv.org/abs/1602.03220 · HTML: https://mlsanity.com/paper/1602.03220/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2016.

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

- [Multimodal Foundation Models: From Specialists to General-Purpose Assistants](https://mlsanity.com/paper/2309.10020/) (2023)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation](https://mlsanity.com/paper/2412.13059/) (2024)
- [Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulation](https://mlsanity.com/paper/2405.06605/) (2024)
- [Reversing Image Signal Processors by Reverse Style Transferring](https://mlsanity.com/paper/2210.09074/) (2022)
- [Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders](https://mlsanity.com/paper/2102.03082/) (2021)
- [Time series generation with spectrally aligned latent flow matching](https://mlsanity.com/paper/2609.21989/) (2026)

## Abstract (arXiv)

We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to humans: identity in faces, objects in images, and utterances in speech. We propose to take advantage of this by using the representations from discriminative classifiers to augment the objective function corresponding to a generative model. In particular we enhance the objective function of the variational autoencoder, a popular generative model, with a discriminative regularization term. We show that enhancing the objective function in this way leads to samples that are clearer and have higher visual quality than the samples from the standard variational autoencoders.