mlsanityData to 7 Oct 2026

Extracting low-dimensional psychological representations from convolutional neural networks

arXiv 2005.14363 ↗First posted 29 May 2020q-bio.NC cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are increasingly being used in cognitive modeling as a means of deriving representations for complex stimuli such as images. While the predictive power of these networks is high, it is often not clear whether they also offer useful explanations of the task at hand. Convolutional neural network representations have been shown to be predictive of human similarity judgments for images after appropriate adaptation. However, these high-dimensional representations are difficult to interpret. Here we present a method for reducing these representations to a low-dimensional space which is still predictive of similarity judgments. We show that these low-dimensional representations also provide insightful explanations of factors underlying human similarity judgments.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 4; 2024: 5; 2025: 1; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Human-like object concept representations emerge naturally in multimodal large language modelscited by 24
  2. 2022Words are all you need? Language as an approximation for human similarity judgmentscited by 18
  3. 2022On the Informativeness of Supervision Signalscited by 12
  4. 2022Predicting Human Similarity Judgments Using Large Language Modelscited by 10
  5. 2024CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representationscited by 5
  6. 2023The Universal Law of Generalization Holds for Naturalistic Stimulicited by 4
  7. 2023Divergences in Color Perception between Deep Neural Networks and Humanscited by 4
  8. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  9. 2023Algebras of actions in an agent's representations of the worldcited by 2
  10. 2021Grounding Psychological Shape Space in Convolutional Neural Networkscited by 1
  11. 2023A Rational Model of Dimension-reduced Human Categorizationcited by 0
  12. 2024Face processing emerges from object-trained convolutional neural networkscited by 0
4 more
  1. 2024Explaining Human Comparisons using Alignment-Importance Heatmapscited by 0
  2. 2025Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Modelcited by 0
  3. 2026Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitextscited by 0
  4. 2026Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networkscited by 0