# Grounding Psychological Shape Space in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2111.08409 · HTML: https://mlsanity.com/paper/2111.08409/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 67 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Learning to Generate Chairs, Tables and Cars with Convolutional Networks](https://mlsanity.com/paper/1411.5928/) (2014)
- [Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings](https://mlsanity.com/paper/2011.11015/) (2020)
- [Extracting low-dimensional psychological representations from convolutional neural networks](https://mlsanity.com/paper/2005.14363/) (2020)
- [Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity](https://mlsanity.com/paper/2010.06512/) (2020)
- [End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior](https://mlsanity.com/paper/2007.08723/) (2020)
- [Generalizing Psychological Similarity Spaces to Unseen Stimuli](https://mlsanity.com/paper/1908.09260/) (2019)

## Built on by (most cited first, 1 of 1)

- [On convex decision regions in deep network representations](https://mlsanity.com/paper/2305.17154/) (2023)

## Abstract (arXiv)

Shape information is crucial for human perception and cognition, and should therefore also play a role in cognitive AI systems. We employ the interdisciplinary framework of conceptual spaces, which proposes a geometric representation of conceptual knowledge through low-dimensional interpretable similarity spaces. These similarity spaces are often based on psychological dissimilarity ratings for a small set of stimuli, which are then transformed into a spatial representation by a technique called multidimensional scaling. Unfortunately, this approach is incapable of generalizing to novel stimuli. In this paper, we use convolutional neural networks to learn a generalizable mapping between perceptual inputs (pixels of grayscale line drawings) and a recently proposed psychological similarity space for the shape domain. We investigate different network architectures (classification network vs. autoencoder) and different training regimes (transfer learning vs. multi-task learning). Our results indicate that a classification-based multi-task learning scenario yields the best results, but that its performance is relatively sensitive to the dimensionality of the similarity space.