# Understanding Deep Convolutional Networks through Gestalt Theory

arXiv: https://arxiv.org/abs/1810.08697 · HTML: https://mlsanity.com/paper/1810.08697/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2018.

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

- [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)
- [Can Artificial Intelligence Reconstruct Ancient Mosaics?](https://mlsanity.com/paper/2210.06145/) (2022)
- [Advancing Perception in Artificial Intelligence through Principles of Cognitive Science](https://mlsanity.com/paper/2310.08803/) (2023)
- [Efficient Visualization of Neural Networks with Generative Models and Adversarial Perturbations](https://mlsanity.com/paper/2409.13559/) (2024)
- [Monkey Transfer Learning Can Improve Human Pose Estimation](https://mlsanity.com/paper/2412.15966/) (2024)
- [Locating and Editing Figure-Ground Organization in Vision Transformers](https://mlsanity.com/paper/2603.06407/) (2026)
- [EEG Decoding Using CNN and LSTM Network](https://mlsanity.com/paper/2608.13285/) (2026)

## Abstract (arXiv)

The superior performance of deep convolutional networks over high-dimensional problems have made them very popular for several applications. Despite their wide adoption, their underlying mechanisms still remain unclear with their improvement procedures still relying mainly on a trial and error process. We introduce a novel sensitivity analysis based on the Gestalt theory for giving insights into the classifier function and intermediate layers. Since Gestalt psychology stipulates that perception can be a product of complex interactions among several elements, we perform an ablation study based on this concept to discover which principles and image context significantly contribute in the network classification. Our results reveal that ConvNets follow most of the visual cortical perceptual mechanisms defined by the Gestalt principles at several levels. The proposed framework stimulates specific feature maps in classification problems and reveal important network attributes that can produce more explainable network models.