# Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition

arXiv: https://arxiv.org/abs/1508.03929 · HTML: https://mlsanity.com/paper/1508.03929/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2015.

## Built on by (most cited first, 14 of 14)

- [If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components](https://mlsanity.com/paper/2202.03930/) (2022)
- [Guiding Visual Attention in Deep Convolutional Neural Networks Based on Human Eye Movements](https://mlsanity.com/paper/2206.10587/) (2022)
- [RTify: Aligning Deep Neural Networks with Human Behavioral Decisions](https://mlsanity.com/paper/2411.03630/) (2024)
- [Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AI](https://mlsanity.com/paper/2401.11835/) (2024)
- [Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance](https://mlsanity.com/paper/2402.19401/) (2024)
- [Modeling biological face recognition with deep convolutional neural networks](https://mlsanity.com/paper/2208.06681/) (2022)
- [Beyond still images: Temporal features and input variance resilience](https://mlsanity.com/paper/2311.00800/) (2023)
- [Layerwise complexity-matched learning yields an improved model of cortical area V2](https://mlsanity.com/paper/2312.11436/) (2023)
- [Measuring Error Alignment for Decision-Making Systems](https://mlsanity.com/paper/2409.13919/) (2024)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Adversarial Attacks with Time-Scale Representations](https://mlsanity.com/paper/2107.12473/) (2021)
- [Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis](https://mlsanity.com/paper/2502.07277/) (2025)
- [Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment](https://mlsanity.com/paper/2505.16419/) (2025)
- [Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance](https://mlsanity.com/paper/2506.17040/) (2025)

## Abstract (arXiv)

Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.