# Recurrent computations for visual pattern completion

arXiv: https://arxiv.org/abs/1706.02240 · HTML: https://mlsanity.com/paper/1706.02240/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2017.

## Built on by (most cited first, 22 of 22)

- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [Hybrid Predictive Coding: Inferring, Fast and Slow](https://mlsanity.com/paper/2204.02169/) (2022)
- [When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes](https://mlsanity.com/paper/2104.02215/) (2021)
- [Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study](https://mlsanity.com/paper/2108.00107/) (2021)
- [Soft Augmentation for Image Classification](https://mlsanity.com/paper/2211.04625/) (2022)
- [Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species](https://mlsanity.com/paper/2101.01611/) (2021)
- [Continuous Spatiotemporal Transformers](https://mlsanity.com/paper/2301.13338/) (2023)
- [A comparison between humans and AI at recognizing objects in unusual poses](https://mlsanity.com/paper/2402.03973/) (2024)
- [A model of semantic completion in generative episodic memory](https://mlsanity.com/paper/2111.13537/) (2021)
- [Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?](https://mlsanity.com/paper/2409.10775/) (2024)
- [Achieving More Human Brain-Like Vision via Human EEG Representational Alignment](https://mlsanity.com/paper/2401.17231/) (2024)
- [Visual Attention Emerges from Recurrent Sparse Reconstruction](https://mlsanity.com/paper/2204.10962/) (2022)
- [Guiding Visual Attention in Deep Convolutional Neural Networks Based on Human Eye Movements](https://mlsanity.com/paper/2206.10587/) (2022)
- [On the Effects of Artificial Data Modification](https://mlsanity.com/paper/2110.13968/) (2021)
- [Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment](https://mlsanity.com/paper/2310.20599/) (2023)
- [Deep Continuous Networks](https://mlsanity.com/paper/2402.01557/) (2024)
- [Understanding Character Recognition using Visual Explanations Derived from the Human Visual System and Deep Networks](https://mlsanity.com/paper/2108.04558/) (2021)
- [SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks](https://mlsanity.com/paper/2206.08427/) (2022)
- [Understanding the Role of Pathways in a Deep Neural Network](https://mlsanity.com/paper/2402.18132/) (2024)
- [Speeding Up Image Classifiers with Little Companions](https://mlsanity.com/paper/2406.17117/) (2024)
- [Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing](https://mlsanity.com/paper/2507.16427/) (2025)
- [PRISM: Progressive Reasoning through Iterative Slot Memory for Vision](https://mlsanity.com/paper/2605.30942/) (2026)

## Abstract (arXiv)

Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, physiology and computational models to test the hypothesis that pattern completion is implemented by recurrent computations and present three pieces of evidence that are consistent with this hypothesis. First, subjects robustly recognized objects even when rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking. Second, invasive physiological responses along the human ventral cortex exhibited visually selective responses to partially visible objects that were delayed compared to whole objects, suggesting the need for additional computations. These physiological delays were correlated with the effects of backward masking. Third, state-of-the-art feed-forward computational architectures were not robust to partial visibility. However, recognition performance was recovered when the model was augmented with attractor-based recurrent connectivity. These results provide a strong argument of plausibility for the role of recurrent computations in making visual inferences from partial information.