# Normalized Diversification

arXiv: https://arxiv.org/abs/1904.03608 · HTML: https://mlsanity.com/paper/1904.03608/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

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

- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision](https://mlsanity.com/paper/2205.02300/) (2022)
- [Few-shot Image Generation with Mixup-based Distance Learning](https://mlsanity.com/paper/2111.11672/) (2021)
- [MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators](https://mlsanity.com/paper/2107.07260/) (2021)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [Few-shot Image Generation via Information Transfer from the Built Geodesic Surface](https://mlsanity.com/paper/2401.01749/) (2024)

## Abstract (arXiv)

Generating diverse yet specific data is the goal of the generative adversarial network (GAN), but it suffers from the problem of mode collapse. We introduce the concept of normalized diversity which force the model to preserve the normalized pairwise distance between the sparse samples from a latent parametric distribution and their corresponding high-dimensional outputs. The normalized diversification aims to unfold the manifold of unknown topology and non-uniform distribution, which leads to safe interpolation between valid latent variables. By alternating the maximization over the pairwise distance and updating the total distance (normalizer), we encourage the model to actively explore in the high-dimensional output space. We demonstrate that by combining the normalized diversity loss and the adversarial loss, we generate diverse data without suffering from mode collapsing. Experimental results show that our method achieves consistent improvement on unsupervised image generation, conditional image generation and hand pose estimation over strong baselines.