Testing Deep Neural Networks on the Same-Different Task

  title={Testing Deep Neural Networks on the Same-Different Task},
  author={N. Messina and G. Amato and Fabio Carrara and F. Falchi and C. Gennaro},
  journal={2019 International Conference on Content-Based Multimedia Indexing (CBMI)},
  • N. Messina, G. Amato, +2 authors C. Gennaro
  • Published 2019
  • Computer Science
  • 2019 International Conference on Content-Based Multimedia Indexing (CBMI)
  • Developing abstract reasoning abilities in neural networks is an important goal towards the achievement of human-like performances on many tasks. As of now, some works have tackled this problem, developing ad-hoc architectures and reaching overall good generalization performances. In this work we try to understand to what extent state-of-the-art convolutional neural networks for image classification are able to deal with a challenging abstract problem, the so-called same-different task. This… CONTINUE READING
    2 Citations

    Figures, Tables, and Topics from this paper.

    Evaluating the Progress of Deep Learning for Visual Relational Concepts
    • 1
    • Highly Influenced
    • PDF


    A dataset and architecture for visual reasoning with a working memory
    • 31
    • PDF
    Going deeper with convolutions
    • 20,823
    • Highly Influential
    • PDF
    Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks
    • 14
    • Highly Influential
    A simple neural network module for relational reasoning
    • 814
    • PDF
    ImageNet classification with deep convolutional neural networks
    • 54,895
    • Highly Influential
    • PDF
    Measuring abstract reasoning in neural networks
    • 97
    • PDF
    CORnet: Modeling the Neural Mechanisms of Core Object Recognition
    • 54
    • Highly Influential
    • PDF
    Very deep convolutional neural network based image classification using small training sample size
    • Shuying Liu, W. Deng
    • Computer Science
    • 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)
    • 2015
    • 184
    • Highly Influential
    Deep Residual Learning for Image Recognition
    • 53,474
    • PDF