Measuring Human Perception to Improve Open Set Recognition

• URL: http://arxiv.org/abs/2209.03519v4
• Date: Mon, 24 Apr 2023 20:48:12 GMT
• Title: Measuring Human Perception to Improve Open Set Recognition
• Authors: Jin Huang, Derek Prijatelj, Justin Dulay and Walter Scheirer
• Abstract summary: Human ability to recognize when an object belongs or does not belong to a particular vision task outperforms all open set recognition algorithms. measured reaction time from human subjects can offer insight as to whether a class sample is prone to be confused with a different class. New psychophysical loss function enforces consistency with human behavior in deep networks which exhibit variable reaction time for different images.
• Score: 4.124573231232705
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The human ability to recognize when an object belongs or does not belong to a particular vision task outperforms all open set recognition algorithms. Human perception as measured by the methods and procedures of visual psychophysics from psychology provides an additional data stream for algorithms that need to manage novelty. For instance, measured reaction time from human subjects can offer insight as to whether a class sample is prone to be confused with a different class -- known or novel. In this work, we designed and performed a large-scale behavioral experiment that collected over 200,000 human reaction time measurements associated with object recognition. The data collected indicated reaction time varies meaningfully across objects at the sample-level. We therefore designed a new psychophysical loss function that enforces consistency with human behavior in deep networks which exhibit variable reaction time for different images. As in biological vision, this approach allows us to achieve good open set recognition performance in regimes with limited labeled training data. Through experiments using data from ImageNet, significant improvement is observed when training Multi-Scale DenseNets with this new formulation: it significantly improved top-1 validation accuracy by 6.02%, top-1 test accuracy on known samples by 9.81%, and top-1 test accuracy on unknown samples by 33.18%. We compared our method to 10 open set recognition methods from the literature, which were all outperformed on multiple metrics.

Related papers

• Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation [24.35436087740559]
  We propose an experimental method for measuring bias in face recognition systems. Our method is based on generating synthetic faces using a neural face generator. We validate our method quantitatively by evaluating race and gender biases of three research-grade face recognition models.
  arXiv  Detail & Related papers  (2023-08-10T08:57:31Z)
• Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms [88.93372675846123]
  We propose a task-agnostic evaluation framework Camilla for evaluating machine learning algorithms. We use cognitive diagnosis assumptions and neural networks to learn the complex interactions among algorithms, samples and the skills of each sample. In our experiments, Camilla outperforms state-of-the-art baselines on the metric reliability, rank consistency and rank stability.
  arXiv  Detail & Related papers  (2023-07-14T03:15:56Z)
• Advancing 3D finger knuckle recognition via deep feature learning [51.871256510747465]
  Contactless 3D finger knuckle patterns have emerged as an effective biometric identifier due to its discriminativeness, visibility from a distance, and convenience. Recent research has developed a deep feature collaboration network which simultaneously incorporates intermediate features from deep neural networks with multiple scales. This paper advances this approach by investigating the possibility of learning a discriminative feature vector with the least possible dimension for representing 3D finger knuckle images.
  arXiv  Detail & Related papers  (2023-01-07T20:55:16Z)
• A high performance fingerprint liveness detection method based on quality related features [66.41574316136379]
  The system is tested on a highly challenging database comprising over 10,500 real and fake images. The proposed solution proves to be robust to the multi-scenario dataset, and presents an overall rate of 90% correctly classified samples.
  arXiv  Detail & Related papers  (2021-11-02T21:09:39Z)
• Passive attention in artificial neural networks predicts human visual selectivity [8.50463394182796]
  We show that passive attention techniques reveal a significant overlap with human visual selectivity estimates. We validate these correlational results with causal manipulations using recognition experiments. This work contributes a new approach to evaluating the biological and psychological validity of leading ANNs as models of human vision.
  arXiv  Detail & Related papers  (2021-07-14T21:21:48Z)
• Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation [93.73198973454944]
  The performance of our method is evaluated on three widely used datasets. It is comparable to that of video-based state-of-the-art methods while it has much less complexity.
  arXiv  Detail & Related papers  (2021-06-08T13:40:30Z)
• Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Dataset [4.511561231517167]
  This paper presents a convolutional neural network for authenticating users using their eye movements. The network is trained with an established metric learning loss function, multi-similarity loss. We find that eye movements are quite resilient against template aging after 3 years.
  arXiv  Detail & Related papers  (2021-04-21T12:21:28Z)
• Face Forensics in the Wild [121.23154918448618]
  We construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assessment network. In addition, we propose a novel algorithm to tackle the task of multi-person face forgery detection.
  arXiv  Detail & Related papers  (2021-03-30T05:06:19Z)
• Learning Realistic Patterns from Unrealistic Stimuli: Generalization and Data Anonymization [0.5091527753265949]
  This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such private data. We use sleep monitoring data from both an open and a large closed clinical study and evaluate whether (1) end-users can create and successfully use customized classification models for sleep apnea detection, and (2) the identity of participants in the study is protected.
  arXiv  Detail & Related papers  (2020-09-21T16:31:21Z)
• Real-Time Face and Landmark Localization for Eyeblink Detection [1.617280000789628]
  A face- and landmark-detection algorithm have been carefully combined in order to provide fully automated eyelid tracking. Our experimental evaluation reveals an overall runtime application of 0.533 ms per frame. This is 1,101$times$ faster than the sequential implementation and well within the real-time requirements of eyeblink conditioning in humans.
  arXiv  Detail & Related papers  (2020-06-01T09:46:25Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

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.