# Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments

arXiv: https://arxiv.org/abs/2211.15053 · HTML: https://mlsanity.com/paper/2211.15053/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Morphable Face Models - An Open Framework](https://mlsanity.com/paper/1709.08398/) (2017)
- [Simple and Effective VAE Training with Calibrated Decoders](https://mlsanity.com/paper/2006.13202/) (2020)
- [A Framework For Contrastive Self-Supervised Learning And Designing A New Approach](https://mlsanity.com/paper/2009.00104/) (2020)
- [Statistical inference on representational geometries](https://mlsanity.com/paper/2112.09200/) (2021)
- [Controversial stimuli: pitting neural networks against each other as models of human recognition](https://mlsanity.com/paper/1911.09288/) (2019)
- [Testing the limits of natural language models for predicting human language judgments](https://mlsanity.com/paper/2204.03592/) (2022)

## Built on by (most cited first, 4 of 4)

- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Bayesian Comparisons Between Representations](https://mlsanity.com/paper/2411.08739/) (2024)
- [Perceived face similarity reflects inverse-generative and naturalistic discriminative objectives](https://mlsanity.com/paper/2605.12619/) (2026)
- [More Data Cannot Break a Symmetry: Identifiability by Design](https://mlsanity.com/paper/2608.27651/) (2026)

## Abstract (arXiv)

Comparing representations of complex stimuli in neural network layers to human brain representations or behavioral judgments can guide model development. However, even qualitatively distinct neural network models often predict similar representational geometries of typical stimulus sets. We propose a Bayesian experimental design approach to synthesizing stimulus sets for adjudicating among representational models efficiently. We apply our method to discriminate among candidate neural network models of behavioral face dissimilarity judgments. Our results indicate that a neural network trained to invert a 3D-face-model graphics renderer is more human-aligned than the same architecture trained on identification, classification, or autoencoding. Our proposed stimulus synthesis objective is generally applicable to designing experiments to be analyzed by representational similarity analysis for model comparison.