# The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks

arXiv: https://arxiv.org/abs/2205.10144 · HTML: https://mlsanity.com/paper/2205.10144/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 100 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 25 of 25)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency](https://mlsanity.com/paper/2006.16736/) (2020)
- [Self-supervised learning through the eyes of a child](https://mlsanity.com/paper/2007.16189/) (2020)
- [Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet](https://mlsanity.com/paper/1411.1045/) (2014)
- [The Overfitted Brain: Dreams evolved to assist generalization](https://mlsanity.com/paper/2007.09560/) (2020)
- [Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12142/) (2020)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)

## Built on by (most cited first, 9 of 9)

- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Learning high-level visual representations from a child's perspective without strong inductive biases](https://mlsanity.com/paper/2305.15372/) (2023)
- [The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences](https://mlsanity.com/paper/2406.10447/) (2024)
- [Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?](https://mlsanity.com/paper/2305.17023/) (2023)
- [Adopting a human developmental visual diet yields robust, shape-based AI vision](https://mlsanity.com/paper/2507.03168/) (2025)
- [The Acquisition of Physical Knowledge in Generative Neural Networks](https://mlsanity.com/paper/2310.19943/) (2023)
- [Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag](https://mlsanity.com/paper/2402.09303/) (2024)
- [Characterizing the visual representation of objects from the child's view](https://mlsanity.com/paper/2605.14990/) (2026)
- [LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")](https://mlsanity.com/paper/2606.05497/) (2026)

## Abstract (arXiv)

In laboratory object recognition tasks based on undistorted photographs, both adult humans and Deep Neural Networks (DNNs) perform close to ceiling. Unlike adults', whose object recognition performance is robust against a wide range of image distortions, DNNs trained on standard ImageNet (1.3M images) perform poorly on distorted images. However, the last two years have seen impressive gains in DNN distortion robustness, predominantly achieved through ever-increasing large-scale datasetsunicodex2014orders of magnitude larger than ImageNet. While this simple brute-force approach is very effective in achieving human-level robustness in DNNs, it raises the question of whether human robustness, too, is simply due to extensive experience with (distorted) visual input during childhood and beyond. Here we investigate this question by comparing the core object recognition performance of 146 children (aged 4unicodex201315) against adults and against DNNs. We find, first, that already 4unicodex20136 year-olds showed remarkable robustness to image distortions and outperform DNNs trained on ImageNet. Second, we estimated the number of unicodex201Cimagesunicodex201D children have been exposed to during their lifetime. Compared to various DNNs, children's high robustness requires relatively little data. Third, when recognizing objects childrenunicodex2014like adults but unlike DNNsunicodex2014rely heavily on shape but not on texture cues. Together our results suggest that the remarkable robustness to distortions emerges early in the developmental trajectory of human object recognition and is unlikely the result of a mere accumulation of experience with distorted visual input. Even though current DNNs match human performance regarding robustness they seem to rely on different and more data-hungry strategies to do so.