# Predictive coding feedback results in perceived illusory contours in a recurrent neural network

arXiv: https://arxiv.org/abs/2102.01955 · HTML: https://mlsanity.com/paper/2102.01955/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 69 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [Difference Target Propagation](https://mlsanity.com/paper/1412.7525/) (2014)
- [Learning long-range spatial dependencies with horizontal gated-recurrent units](https://mlsanity.com/paper/1805.08315/) (2018)
- [Predictive Coding Approximates Backprop along Arbitrary Computation Graphs](https://mlsanity.com/paper/2006.04182/) (2020)
- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision](https://mlsanity.com/paper/1608.03425/) (2016)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [Deep Predictive Coding Network for Object Recognition](https://mlsanity.com/paper/1802.04762/) (2018)
- [Neural Networks with Recurrent Generative Feedback](https://mlsanity.com/paper/2007.09200/) (2020)
- [GAIT-prop: A biologically plausible learning rule derived from backpropagation of error](https://mlsanity.com/paper/2006.06438/) (2020)
- [Deep Predictive Coding Networks](https://mlsanity.com/paper/1301.3541/) (2013)
- [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)
- [Predictive coding: A Possible Explanation of Filling-in at the blind spot](https://mlsanity.com/paper/1507.01390/) (2015)

## Built on by (most cited first, 10 of 10)

- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics](https://mlsanity.com/paper/2106.02749/) (2021)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Predictive Coding Networks and Inference Learning: Tutorial and Survey](https://mlsanity.com/paper/2407.04117/) (2024)
- [Quantum-tunnelling deep neural network for optical illusion recognition](https://mlsanity.com/paper/2407.11013/) (2024)
- [Contour Integration Underlies Human-Like Vision](https://mlsanity.com/paper/2504.05253/) (2025)
- [Divergences in Color Perception between Deep Neural Networks and Humans](https://mlsanity.com/paper/2309.05809/) (2023)
- [On the role of feedback in visual processing: a predictive coding perspective](https://mlsanity.com/paper/2106.04225/) (2021)
- [Abutting Grating Illusion: Cognitive Challenge to Neural Network Models](https://mlsanity.com/paper/2208.03958/) (2022)
- [Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures](https://mlsanity.com/paper/2607.17138/) (2026)

## Abstract (arXiv)

Modern feedforward convolutional neural networks (CNNs) can now solve some computer vision tasks at super-human levels. However, these networks only roughly mimic human visual perception. One difference from human vision is that they do not appear to perceive illusory contours (e.g. Kanizsa squares) in the same way humans do. Physiological evidence from visual cortex suggests that the perception of illusory contours could involve feedback connections. Would recurrent feedback neural networks perceive illusory contours like humans? In this work we equip a deep feedforward convolutional network with brain-inspired recurrent dynamics. The network was first pretrained with an unsupervised reconstruction objective on a natural image dataset, to expose it to natural object contour statistics. Then, a classification decision layer was added and the model was finetuned on a form discrimination task: squares vs. randomly oriented inducer shapes (no illusory contour). Finally, the model was tested with the unfamiliar ''illusory contour'' configuration: inducer shapes oriented to form an illusory square. Compared with feedforward baselines, the iterative ''predictive coding'' feedback resulted in more illusory contours being classified as physical squares. The perception of the illusory contour was measurable in the luminance profile of the image reconstructions produced by the model, demonstrating that the model really ''sees'' the illusion. Ablation studies revealed that natural image pretraining and feedback error correction are both critical to the perception of the illusion. Finally we validated our conclusions in a deeper network (VGG): adding the same predictive coding feedback dynamics again leads to the perception of illusory contours.