# Diverse Rare Sample Generation with Pretrained GANs

arXiv: https://arxiv.org/abs/2412.19543 · HTML: https://mlsanity.com/paper/2412.19543/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 62 references that are in the map.
- First posted on arXiv 27 Dec 2024.

## Builds on (most cited first, 11 of 11)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Discriminator Rejection Sampling](https://mlsanity.com/paper/1810.06758/) (2018)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining](https://mlsanity.com/paper/2110.08009/) (2021)
- [FairFaceGAN: Fairness-aware Facial Image-to-Image Translation](https://mlsanity.com/paper/2012.00282/) (2020)
- [Simplifying deflation for non-convex optimization with applications in Bayesian inference and topology optimization](https://mlsanity.com/paper/2201.11926/) (2022)

## Built on by (most cited first, 3 of 3)

- [Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution](https://mlsanity.com/paper/2605.02167/) (2026)
- [Exploring Image Generation via Mutually Exclusive Probability Spaces and Local Correlation Hypothesis](https://mlsanity.com/paper/2506.21731/) (2025)
- [Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling](https://mlsanity.com/paper/2606.13347/) (2026)

## Abstract (arXiv)

Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve the fidelity of generated samples, they often reduce diversity and coverage by ignoring rare and novel samples. This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs. Our method employs gradient-based optimization of latent vectors within a multi-objective framework and utilizes normalizing flows for density estimation on the feature space. This enables the generation of diverse rare images, with controllable parameters for rarity, diversity, and similarity to a reference image. We demonstrate the effectiveness of our approach both qualitatively and quantitatively across various datasets and GANs without retraining or fine-tuning the pretrained GANs.