# MindSet: Vision. A toolbox for testing DNNs on key psychological experiments

arXiv: https://arxiv.org/abs/2404.05290 · HTML: https://mlsanity.com/paper/2404.05290/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 113 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 16 of 16)

- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition](https://mlsanity.com/paper/1406.3284/) (2014)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?](https://mlsanity.com/paper/2311.00047/) (2023)
- [Recurrent neural circuits for contour detection](https://mlsanity.com/paper/2010.15314/) (2020)
- [Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be](https://mlsanity.com/paper/2110.05861/) (2021)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training](https://mlsanity.com/paper/2110.01476/) (2021)
- [Crowding Reveals Fundamental Differences in Local vs. Global Processing in Humans and Machines](https://mlsanity.com/paper/2004.12676/) (2020)
- [A case for robust translation tolerance in humans and CNNs. A commentary on Han et al](https://mlsanity.com/paper/2012.05950/) (2020)
- [Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping](https://mlsanity.com/paper/2309.16515/) (2023)
- [Convolutional Neural Networks Deceived by Visual Illusions](https://mlsanity.com/paper/1811.10565/) (2018)

## Built on by (most cited first, 8 of 8)

- [Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems](https://mlsanity.com/paper/2411.01173/) (2024)
- [Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems](https://mlsanity.com/paper/2508.12026/) (2025)
- [Adopting a human developmental visual diet yields robust, shape-based AI vision](https://mlsanity.com/paper/2507.03168/) (2025)
- [Finding Closure: A Closer Look at the Gestalt Law of Closure in Convolutional Neural Networks](https://mlsanity.com/paper/2408.12460/) (2024)
- [Visual Language Models show widespread visual deficits on neuropsychological tests](https://mlsanity.com/paper/2504.10786/) (2025)
- [Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models](https://mlsanity.com/paper/2507.00493/) (2025)
- [Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired Evaluation](https://mlsanity.com/paper/2508.10367/) (2025)
- [Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment](https://mlsanity.com/paper/2412.03210/) (2024)

## Abstract (arXiv)

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox textitMindSet: Vision, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible via https://github.com/MindSetVision/MindSetVision. To illustrate the challenges these datasets pose for developing better DNN models of human vision, we test several models on range of datasets included in the toolbox.