# Comparing deep neural networks against humans: object recognition when the signal gets weaker

arXiv: https://arxiv.org/abs/1706.06969 · HTML: https://mlsanity.com/paper/1706.06969/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2017.

## Built on by (most cited first, 30 of 34)

- [Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions](https://mlsanity.com/paper/2110.06513/) (2021)
- [Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance](https://mlsanity.com/paper/2208.08664/) (2022)
- [MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition](https://mlsanity.com/paper/2305.07214/) (2023)
- [Do Perceptually Aligned Gradients Imply Adversarial Robustness?](https://mlsanity.com/paper/2207.11378/) (2022)
- [Temporal Coherent Test-Time Optimization for Robust Video Classification](https://mlsanity.com/paper/2302.14309/) (2023)
- [Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study](https://mlsanity.com/paper/2108.00107/) (2021)
- [CLAD: A Contrastive Learning based Approach for Background Debiasing](https://mlsanity.com/paper/2210.02748/) (2022)
- [CPPE-5: Medical Personal Protective Equipment Dataset](https://mlsanity.com/paper/2112.09569/) (2021)
- [Class-Conditioned Transformation for Enhanced Robust Image Classification](https://mlsanity.com/paper/2303.15409/) (2023)
- [Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation](https://mlsanity.com/paper/2103.03102/) (2021)
- [Visual Attention Emerges from Recurrent Sparse Reconstruction](https://mlsanity.com/paper/2204.10962/) (2022)
- [Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection](https://mlsanity.com/paper/2211.16806/) (2022)
- [Natural Perturbed Training for General Robustness of Neural Network Classifiers](https://mlsanity.com/paper/2103.11372/) (2021)
- [Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?](https://mlsanity.com/paper/2401.09237/) (2024)
- [Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AI](https://mlsanity.com/paper/2401.11835/) (2024)
- [Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement](https://mlsanity.com/paper/2411.01099/) (2024)
- [textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time](https://mlsanity.com/paper/2506.00358/) (2025)
- [ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better](https://mlsanity.com/paper/2603.26486/) (2026)
- [The Barrier of meaning in archaeological data science](https://mlsanity.com/paper/2102.06022/) (2021)
- [Deep Convolutional Neural Networks for Onychomycosis Detection](https://mlsanity.com/paper/2106.16139/) (2021)
- [SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control](https://mlsanity.com/paper/2202.01816/) (2022)
- [Virtual Underwater Datasets for Autonomous Inspections](https://mlsanity.com/paper/2209.06013/) (2022)
- [Just Mix Once: Worst-group Generalization by Group Interpolation](https://mlsanity.com/paper/2210.12195/) (2022)
- [ExpNet: A unified network for Expert-Level Classification](https://mlsanity.com/paper/2211.15672/) (2022)
- [BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition](https://mlsanity.com/paper/2303.01309/) (2023)
- [Beyond still images: Temporal features and input variance resilience](https://mlsanity.com/paper/2311.00800/) (2023)
- [Assessing Graphical Perception of Image Embedding Models using Channel Effectiveness](https://mlsanity.com/paper/2407.20845/) (2024)
- [Bayesian Comparisons Between Representations](https://mlsanity.com/paper/2411.08739/) (2024)
- [Network-Agnostic Knowledge Transfer for Medical Image Segmentation](https://mlsanity.com/paper/2101.09560/) (2021)
- [Wiggling Weights to Improve the Robustness of Classifiers](https://mlsanity.com/paper/2111.09779/) (2021)

## Abstract (arXiv)

Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algorithms called deep neural networks (DNNs) that achieve human-level classification performance on object recognition tasks. Furthermore, a growing number of studies report similarities in the way DNNs and the human visual system process objects, suggesting that current DNNs may be good models of human visual object recognition. Yet there clearly exist important architectural and processing differences between state-of-the-art DNNs and the primate visual system. The potential behavioural consequences of these differences are not well understood. We aim to address this issue by comparing human and DNN generalisation abilities towards image degradations. We find the human visual system to be more robust to image manipulations like contrast reduction, additive noise or novel eidolon-distortions. In addition, we find progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker, indicating that there may still be marked differences in the way humans and current DNNs perform visual object recognition. We envision that our findings as well as our carefully measured and freely available behavioural datasets provide a new useful benchmark for the computer vision community to improve the robustness of DNNs and a motivation for neuroscientists to search for mechanisms in the brain that could facilitate this robustness.