# Mixed Evidence for Gestalt Grouping in Deep Neural Networks

arXiv: https://arxiv.org/abs/2203.07302 · HTML: https://mlsanity.com/paper/2203.07302/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 84 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Learning long-range spatial dependencies with horizontal gated-recurrent units](https://mlsanity.com/paper/1805.08315/) (2018)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [Quantifying Translation-Invariance in Convolutional Neural Networks](https://mlsanity.com/paper/1801.01450/) (2017)
- [Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be](https://mlsanity.com/paper/2110.05861/) (2021)
- [Predictive coding feedback results in perceived illusory contours in a recurrent neural network](https://mlsanity.com/paper/2102.01955/) (2021)
- [Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training](https://mlsanity.com/paper/2110.01476/) (2021)
- [A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception](https://mlsanity.com/paper/1805.10734/) (2018)
- [A case for robust translation tolerance in humans and CNNs. A commentary on Han et al](https://mlsanity.com/paper/2012.05950/) (2020)

## Built on by (most cited first, 12 of 12)

- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [MindSet: Vision. A toolbox for testing DNNs on key psychological experiments](https://mlsanity.com/paper/2404.05290/) (2024)
- [Contour Integration Underlies Human-Like Vision](https://mlsanity.com/paper/2504.05253/) (2025)
- [Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping](https://mlsanity.com/paper/2309.16515/) (2023)
- [Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks](https://mlsanity.com/paper/2411.00627/) (2024)
- [Finding Closure: A Closer Look at the Gestalt Law of Closure in Convolutional Neural Networks](https://mlsanity.com/paper/2408.12460/) (2024)
- [Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects](https://mlsanity.com/paper/2302.03992/) (2023)
- [Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics](https://mlsanity.com/paper/2303.00077/) (2023)
- [Fixing the problems of deep neural networks will require better training data and learning algorithms](https://mlsanity.com/paper/2311.12819/) (2023)
- [Locating and Editing Figure-Ground Organization in Vision Transformers](https://mlsanity.com/paper/2603.06407/) (2026)
- [Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images](https://mlsanity.com/paper/2607.08932/) (2026)
- [Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs](https://mlsanity.com/paper/2610.05463/) (2026)

## Abstract (arXiv)

Gestalt psychologists have identified a range of conditions in which humans organize elements of a scene into a group or whole, and perceptual grouping principles play an essential role in scene perception and object identification. Recently, Deep Neural Networks (DNNs) trained on natural images (ImageNet) have been proposed as compelling models of human vision based on reports that they perform well on various brain and behavioral benchmarks. Here we test a total of 16 networks covering a variety of architectures and learning paradigms (convolutional, attention-based, supervised and self-supervised, feed-forward and recurrent) on dots (Experiment 1) and more complex shapes (Experiment 2) stimuli that produce strong Gestalts effects in humans. In Experiment 1 we found that convolutional networks were indeed sensitive in a human-like fashion to the principles of proximity, linearity, and orientation, but only at the output layer. In Experiment 2, we found that most networks exhibited Gestalt effects only for a few sets, and again only at the latest stage of processing. Overall, self-supervised and Vision-Transformer appeared to perform worse than convolutional networks in terms of human similarity. Remarkably, no model presented a grouping effect at the early or intermediate stages of processing. This is at odds with the widespread assumption that Gestalts occur prior to object recognition, and indeed, serve to organize the visual scene for the sake of object recognition. Our overall conclusion is that, albeit noteworthy that networks trained on simple 2D images support a form of Gestalt grouping for some stimuli at the output layer, this ability does not seem to transfer to more complex features. Additionally, the fact that this grouping only occurs at the last layer suggests that networks learn fundamentally different perceptual properties than humans.