# Contour Integration Underlies Human-Like Vision

arXiv: https://arxiv.org/abs/2504.05253 · HTML: https://mlsanity.com/paper/2504.05253/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 74 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [Self-supervised Pretraining of Visual Features in the Wild](https://mlsanity.com/paper/2103.01988/) (2021)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Learning long-range spatial dependencies with horizontal gated-recurrent units](https://mlsanity.com/paper/1805.08315/) (2018)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency](https://mlsanity.com/paper/2006.16736/) (2020)
- [Human alignment of neural network representations](https://mlsanity.com/paper/2211.01201/) (2022)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Predictive coding feedback results in perceived illusory contours in a recurrent neural network](https://mlsanity.com/paper/2102.01955/) (2021)

## Built on by (most cited first, 6 of 6)

- [Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference](https://mlsanity.com/paper/2507.04494/) (2025)
- [Inducing Dyslexia in Vision Language Models](https://mlsanity.com/paper/2509.24597/) (2025)
- [On the Reliability of Cue Conflict and Beyond](https://mlsanity.com/paper/2603.10834/) (2026)
- [Human-like Object Grouping in Self-supervised Vision Transformers](https://mlsanity.com/paper/2603.13994/) (2026)
- [Reward Valuation in Large Language Models: Causal Induction of Anhedonia](https://mlsanity.com/paper/2607.06626/) (2026)
- [Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images](https://mlsanity.com/paper/2607.08932/) (2026)

## Abstract (arXiv)

Despite the tremendous success of deep learning in computer vision, models still fall behind humans in generalizing to new input distributions. Existing benchmarks do not investigate the specific failure points of models by analyzing performance under many controlled conditions. Our study systematically dissects where and why models struggle with contour integration -- a hallmark of human vision -- by designing an experiment that tests object recognition under various levels of object fragmentation. Humans (n=50) perform at high accuracy, even with few object contours present. This is in contrast to models which exhibit substantially lower sensitivity to increasing object contours, with most of the over 1,000 models we tested barely performing above chance. Only at very large scales (~5B training dataset size) do models begin to approach human performance. Importantly, humans exhibit an integration bias -- a preference towards recognizing objects made up of directional fragments over directionless fragments. We find that not only do models that share this property perform better at our task, but that this bias also increases with model training dataset size, and training models to exhibit contour integration leads to high shape bias. Taken together, our results suggest that contour integration is a hallmark of object vision that underlies object recognition performance, and may be a mechanism learned from data at scale.