Evaluating Visual Number Discrimination in Deep Neural Networks

• URL: http://arxiv.org/abs/2303.07172v1
• Date: Mon, 13 Mar 2023 15:14:26 GMT
• Title: Evaluating Visual Number Discrimination in Deep Neural Networks
• Authors: Ivana Kaji\'c and Aida Nematzadeh
• Abstract summary: We show that vision-specific inductive biases are helpful in numerosity discrimination. Even the strongest models, as measured on standard metrics of performance, fail to discriminate quantities in transfer experiments.
• Score: 8.447161322658628
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to discriminate between large and small quantities is a core aspect of basic numerical competence in both humans and animals. In this work, we examine the extent to which the state-of-the-art neural networks designed for vision exhibit this basic ability. Motivated by studies in animal and infant numerical cognition, we use the numerical bisection procedure to test number discrimination in different families of neural architectures. Our results suggest that vision-specific inductive biases are helpful in numerosity discrimination, as models with such biases have lowest test errors on the task, and often have psychometric curves that qualitatively resemble those of humans and animals performing the task. However, even the strongest models, as measured on standard metrics of performance, fail to discriminate quantities in transfer experiments with differing training and testing conditions, indicating that such inductive biases might not be sufficient.

Related papers

• Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples [53.95282502030541]
  Neural Network-based active learning (NAL) is a cost-effective data selection technique that utilizes neural networks to select and train on a small subset of samples. We try to move one step forward by offering a unified explanation for the success of both query criteria-based NAL from a feature learning view.
  arXiv  Detail & Related papers  (2024-06-06T10:38:01Z)
• Evaluating alignment between humans and neural network representations in image-based learning tasks [5.657101730705275]
  We tested how well the representations of $86$ pretrained neural network models mapped to human learning trajectories. We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation. In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks.
  arXiv  Detail & Related papers  (2023-06-15T08:18:29Z)
• Dataset Bias in Human Activity Recognition [57.91018542715725]
  This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR.
  arXiv  Detail & Related papers  (2023-01-19T12:33:50Z)
• Ultrafast Image Categorization in Biology and Neural Models [0.0]
  We re-trained the standard VGG 16 CNN on two independent tasks that are ecologically relevant to humans. We show that re-training the network achieves a human-like level of performance, comparable to that reported in psychophysical tasks.
  arXiv  Detail & Related papers  (2022-05-07T11:19:40Z)
• Do DNNs trained on Natural Images acquire Gestalt Properties? [0.6091702876917281]
  Deep Neural Networks (DNNs) trained on natural images have been proposed as compelling models of human vision. We compared human and DNN responses in discrimination judgments. We found that network trained on natural images exhibited sensitivity to shapes at the last stage of classification.
  arXiv  Detail & Related papers  (2022-03-14T17:06:11Z)
• Overcoming the Domain Gap in Neural Action Representations [60.47807856873544]
  3D pose data can now be reliably extracted from multi-view video sequences without manual intervention. We propose to use it to guide the encoding of neural action representations together with a set of neural and behavioral augmentations. To reduce the domain gap, during training, we swap neural and behavioral data across animals that seem to be performing similar actions.
  arXiv  Detail & Related papers  (2021-12-02T12:45:46Z)
• Uncovering the Bias in Facial Expressions [0.0]
  We train a neural network for Action Unit classification and analyze its performance quantitatively based on its accuracy and qualitatively based on heatmaps. A structured review of our results indicates that we are able to detect bias. Even though we cannot conclude from our results that lower classification performance emerged solely from gender and skin color bias, these biases must be addressed.
  arXiv  Detail & Related papers  (2020-11-23T10:20:10Z)
• Seeing eye-to-eye? A comparison of object recognition performance in humans and deep convolutional neural networks under image manipulation [0.0]
  This study aims towards a behavioral comparison of visual core object recognition performance between humans and feedforward neural networks. Analyses of accuracy revealed that humans not only outperform DCNNs on all conditions, but also display significantly greater robustness towards shape and most notably color alterations.
  arXiv  Detail & Related papers  (2020-07-13T10:26:30Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [73.85525896663371]
  This work explores the biases in learning processes based on deep neural network architectures. We employ two gender detection models based on popular deep neural networks. We propose InsideBias, a novel method to detect biased models.
  arXiv  Detail & Related papers  (2020-04-14T15:20:50Z)
• 1-D Convlutional Neural Networks for the Analysis of Pupil Size Variations in Scotopic Conditions [79.71065005161566]
  1-D convolutional neural network models are trained for classification of short-range sequences. Model provides prediction with high average accuracy on a hold out test set.
  arXiv  Detail & Related papers  (2020-02-06T17:25:37Z)

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.