# Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2411.00627 · HTML: https://mlsanity.com/paper/2411.00627/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Builds on (most cited first, 9 of 9)

- [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)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Understanding Deep Convolutional Networks through Gestalt Theory](https://mlsanity.com/paper/1810.08697/) (2018)
- [Evaluating CNNs on the Gestalt Principle of Closure](https://mlsanity.com/paper/1904.00285/) (2019)

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

- [Perception-Guided EEG Analysis: A Deep Learning Approach Inspired by Level of Detail (LOD) Theory](https://mlsanity.com/paper/2501.10428/) (2025)
- [Monkey Transfer Learning Can Improve Human Pose Estimation](https://mlsanity.com/paper/2412.15966/) (2024)
- [The General Theory of Localization Methods](https://mlsanity.com/paper/2605.20635/) (2026)
- [Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images](https://mlsanity.com/paper/2607.08932/) (2026)

## Abstract (arXiv)

Deep neural networks perform well in object recognition, but do they perceive objects like humans? This study investigates the Gestalt principle of closure in convolutional neural networks. We propose a protocol to identify closure and conduct experiments using simple visual stimuli with progressively removed edge sections. We evaluate well-known networks on their ability to classify incomplete polygons. Our findings reveal a performance degradation as the edge removal percentage increases, indicating that current models heavily rely on complete edge information for accurate classification. The data used in our study is available on Github.