# Recurrent neural circuits for contour detection

arXiv: https://arxiv.org/abs/2010.15314 · HTML: https://mlsanity.com/paper/2010.15314/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [Visual Planning: Let's Think Only with Images](https://mlsanity.com/paper/2505.11409/) (2025)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [A Benchmark for Compositional Visual Reasoning](https://mlsanity.com/paper/2206.05379/) (2022)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [The 3D-PC: a benchmark for visual perspective taking in humans and machines](https://mlsanity.com/paper/2406.04138/) (2024)
- [Understanding the computational demands underlying visual reasoning](https://mlsanity.com/paper/2108.03603/) (2021)
- [Tracking Without Re-recognition in Humans and Machines](https://mlsanity.com/paper/2105.13351/) (2021)
- [Better artificial intelligence does not mean better models of biology](https://mlsanity.com/paper/2504.16940/) (2025)
- [MindSet: Vision. A toolbox for testing DNNs on key psychological experiments](https://mlsanity.com/paper/2404.05290/) (2024)
- [Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition](https://mlsanity.com/paper/2112.12175/) (2021)
- [Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception](https://mlsanity.com/paper/2306.03229/) (2023)
- [The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks](https://mlsanity.com/paper/2110.02772/) (2021)
- [Visual Attention Emerges from Recurrent Sparse Reconstruction](https://mlsanity.com/paper/2204.10962/) (2022)
- [Rethinking Interactive Image Segmentation: Feature Space Annotation](https://mlsanity.com/paper/2101.04378/) (2021)
- [BRI3L: A Brightness Illusion Image Dataset for Identification and Localization of Regions of Illusory Perception](https://mlsanity.com/paper/2402.04541/) (2024)
- [From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?](https://mlsanity.com/paper/2509.17280/) (2025)
- [Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics](https://mlsanity.com/paper/2303.00077/) (2023)
- [Unsupervised learning of features and object boundaries from local prediction](https://mlsanity.com/paper/2205.14195/) (2022)
- [PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture](https://mlsanity.com/paper/2306.14650/) (2023)
- [Fixing the problems of deep neural networks will require better training data and learning algorithms](https://mlsanity.com/paper/2311.12819/) (2023)
- [Developmental Pretraining (DPT) for Image Classification Networks](https://mlsanity.com/paper/2312.00304/) (2023)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)
- [Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation](https://mlsanity.com/paper/2509.15460/) (2025)

## Abstract (arXiv)

We introduce a deep recurrent neural network architecture that approximates visual cortical circuits. We show that this architecture, which we refer to as the gamma-net, learns to solve contour detection tasks with better sample efficiency than state-of-the-art feedforward networks, while also exhibiting a classic perceptual illusion, known as the orientation-tilt illusion. Correcting this illusion significantly reduces gamma-net contour detection accuracy by driving it to prefer low-level edges over high-level object boundary contours. Overall, our study suggests that the orientation-tilt illusion is a byproduct of neural circuits that help biological visual systems achieve robust and efficient contour detection, and that incorporating these circuits in artificial neural networks can improve computer vision.