# Diversity vs. Recognizability: Human-like generalization in one-shot generative models

arXiv: https://arxiv.org/abs/2205.10370 · HTML: https://mlsanity.com/paper/2205.10370/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 71 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [Towards a Neural Statistician](https://mlsanity.com/paper/1606.02185/) (2016)
- [A Close Look at Deep Learning with Small Data](https://mlsanity.com/paper/2003.12843/) (2020)
- [One-Shot Generalization in Deep Generative Models](https://mlsanity.com/paper/1603.05106/) (2016)
- [Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons](https://mlsanity.com/paper/2006.14304/) (2020)
- [Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics](https://mlsanity.com/paper/2106.02749/) (2021)
- [Adaptive Density Estimation for Generative Models](https://mlsanity.com/paper/1901.01091/) (2019)
- [Generating new concepts with hybrid neuro-symbolic models](https://mlsanity.com/paper/2003.08978/) (2020)
- [Effect of top-down connections in Hierarchical Sparse Coding](https://mlsanity.com/paper/2002.00892/) (2020)
- [Iterative VAE as a predictive brain model for out-of-distribution generalization](https://mlsanity.com/paper/2012.00557/) (2020)
- [Meta-Meta Classification for One-Shot Learning](https://mlsanity.com/paper/2004.08083/) (2020)

## Built on by (most cited first, 9 of 9)

- [TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling](https://mlsanity.com/paper/2310.01819/) (2023)
- [Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?](https://mlsanity.com/paper/2301.11722/) (2023)
- [Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models](https://mlsanity.com/paper/2505.18230/) (2025)
- [Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks](https://mlsanity.com/paper/2406.06079/) (2024)
- [Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification](https://mlsanity.com/paper/2508.09550/) (2025)
- [BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise](https://mlsanity.com/paper/2309.06046/) (2023)
- [Abstracted Gaussian Prototypes for True One-Shot Concept Learning](https://mlsanity.com/paper/2408.17251/) (2024)
- [Stable diffusion models reveal a persisting human and AI gap in visual creativity](https://mlsanity.com/paper/2511.16814/) (2025)
- [Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot](https://mlsanity.com/paper/2605.23819/) (2026)

## Abstract (arXiv)

Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural architectures capable of synthesizing novel instances of unknown visual concepts from a single training example. Yet, a more precise comparison between these models and humans is not possible because existing performance metrics for generative models (i.e., FID, IS, likelihood) are not appropriate for the one-shot generation scenario. Here, we propose a new framework to evaluate one-shot generative models along two axes: sample recognizability vs. diversity (i.e., intra-class variability). Using this framework, we perform a systematic evaluation of representative one-shot generative models on the Omniglot handwritten dataset. We first show that GAN-like and VAE-like models fall on opposite ends of the diversity-recognizability space. Extensive analyses of the effect of key model parameters further revealed that spatial attention and context integration have a linear contribution to the diversity-recognizability trade-off. In contrast, disentanglement transports the model along a parabolic curve that could be used to maximize recognizability. Using the diversity-recognizability framework, we were able to identify models and parameters that closely approximate human data.