Convolutional neural net face recognition works in non-human-like ways

• URL: http://arxiv.org/abs/2004.04069v2
• Date: Tue, 23 Jun 2020 11:59:06 GMT
• Title: Convolutional neural net face recognition works in non-human-like ways
• Authors: P. J. B. Hancock, R. S. Somai and V. R. Mileva
• Abstract summary: Convolutional neural networks (CNNs) give state of the art performance in many pattern recognition problems. We report that CNN face recognition systems also make surprising "errors" Best CNNs perform almost perfectly on the human face matching tasks, but also declare the most matches for faces of a different apparent race or sex.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional neural networks (CNNs) give state of the art performance in many pattern recognition problems but can be fooled by carefully crafted patterns of noise. We report that CNN face recognition systems also make surprising "errors". We tested six commercial face recognition CNNs and found that they outperform typical human participants on standard face matching tasks. However, they also declare matches that humans would not, where one image from the pair has been transformed to look a different sex or race. This is not due to poor performance; the best CNNs perform almost perfectly on the human face matching tasks, but also declare the most matches for faces of a different apparent race or sex. Although differing on the salience of sex and race, humans and computer systems are not working in completely different ways. They tend to find the same pairs of images difficult, suggesting some agreement about the underlying similarity space.

Related papers

• Human-Machine Comparison for Cross-Race Face Verification: Race Bias at the Upper Limits of Performance? [0.7036032466145111]
  Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. We constructed a challenging test of 'cross-race' face verification and used it to compare humans and two state-of-the-art face recognition systems. We conclude that state-of-the-art systems for identity verification between two frontal face images of Black and White individuals can surpass the general population.
  arXiv  Detail & Related papers  (2023-05-25T19:41:13Z)
• Decoupled Mixup for Generalized Visual Recognition [71.13734761715472]
  We propose a novel "Decoupled-Mixup" method to train CNN models for visual recognition. Our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions to train CNN models. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts.
  arXiv  Detail & Related papers  (2022-10-26T15:21:39Z)
• Twin identification over viewpoint change: A deep convolutional neural network surpasses humans [2.9363019325439255]
  Deep convolutional neural networks have achieved human-level accuracy in face identification. It is unclear how accurately they discriminate highly-similar faces. A DCNN trained for face identification was tested on the same image pairs presented to humans. Machine performance mirrored the pattern of human accuracy, but with performance at or above all humans in all but one condition.
  arXiv  Detail & Related papers  (2022-07-12T04:59:53Z)
• Convolutional Neural Network Based Partial Face Detection [0.0]
  This study aims to create and enhance a machine learning model that correctly recognizes faces. After creating and running the model, Multi-Task Convolutional Neural Network (MTCNN) achieved 96.2% best model accuracy.
  arXiv  Detail & Related papers  (2022-06-29T01:26:40Z)
• BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks [65.2021953284622]
  We study robustness of CNNs against white-box and black-box adversarial attacks. Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
  arXiv  Detail & Related papers  (2021-03-14T20:43:19Z)
• A Study of Face Obfuscation in ImageNet [94.2949777826947]
  In this paper, we explore image obfuscation in the ImageNet challenge. Most categories in the ImageNet challenge are not people categories; nevertheless, many incidental people are in the images. We benchmark various deep neural networks on face-blurred images and observe a disparate impact on different categories. Results show that features learned on face-blurred images are equally transferable.
  arXiv  Detail & Related papers  (2021-03-10T17:11:34Z)
• Sparse Fooling Images: Fooling Machine Perception through Unrecognizable Images [36.42135216182063]
  We propose a new class of fooling images, sparse fooling images (SFIs), which are single color images with a small number of altered pixels. SFIs are recognizable as natural objects and classified to certain classes with high confidence scores. This study gives rise to questions on the structure and robustness of CNNs and discusses the differences between human and machine perception.
  arXiv  Detail & Related papers  (2020-12-07T16:47:33Z)
• Face Hallucination via Split-Attention in Split-Attention Network [58.30436379218425]
  convolutional neural networks (CNNs) have been widely employed to promote the face hallucination. We propose a novel external-internal split attention group (ESAG) to take into account the overall facial profile and fine texture details simultaneously. By fusing the features from these two paths, the consistency of facial structure and the fidelity of facial details are strengthened.
  arXiv  Detail & Related papers  (2020-10-22T10:09:31Z)
• The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [71.24825724518847]
  Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
  arXiv  Detail & Related papers  (2020-09-15T09:25:37Z)
• Video Face Manipulation Detection Through Ensemble of CNNs [17.051112469244778]
  We tackle the problem of face manipulation detection in video sequences targeting modern facial manipulation techniques. In particular, we study the ensembling of different trained Convolutional Neural Network (CNN) models. We show that combining these networks leads to promising face manipulation detection results on two publicly available datasets.
  arXiv  Detail & Related papers  (2020-04-16T14:19:40Z)
• Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [51.31334977346847]
  We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
  arXiv  Detail & Related papers  (2020-04-01T09:31:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.