mlsanityData to 7 Oct 2026

Introducing the structural bases of typicality effects in deep learning

arXiv 2107.03279 ↗First posted 7 Jul 2021cs.CV cs.AI math.RTcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to representing natural semantic categories and based on the Prototype Theory foundations, we propose a novel Computational Prototype Model (CPM) to represent the internal structure of semantic categories. Unlike other prototype learning approaches, our mathematical framework proposes a first approach to provide deep neural networks with the ability to model abstract semantic concepts such as category central semantic meaning, typicality degree of an object's image, and family resemblance relationship. We proposed several methodologies based on the typicality's concept to evaluate our CPM-model in image semantic processing tasks such as image classification, a global semantic description, and transfer learning. Our experiments on different image datasets, such as ImageNet and Coco, showed that our approach might be an admissible proposition in the effort to endow machines with greater power of abstraction for the semantic representation of objects' categories.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 105 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

26 of 105 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  9. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  10. 2016LIFT: Learned Invariant Feature Transformcited by 305
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
14 more
  1. 2018Robust Classification with Convolutional Prototype Learningcited by 122
  2. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  3. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  4. 2019Towards Explainable Deep Neural Networks (xDNN)cited by 61
  5. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  6. 2014Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognitioncited by 50
  7. 2017SCNet: Learning Semantic Correspondencecited by 48
  8. 2017FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondencecited by 42
  9. 2014Do Convnets Learn Correspondence?cited by 28
  10. 2017Gaussian Prototypical Networks for Few-Shot Learning on Omniglotcited by 20
  11. 2020Leveraging Class Hierarchies with Metric-Guided Prototype Learningcited by 20
  12. 2015Dense Semantic Correspondence where Every Pixel is a Classifiercited by 15
  13. 2015Prototypical Priors: From Improving Classification to Zero-Shot Learningcited by 14
  14. 2015Multivariate Chebyshev Inequality with Estimated Mean and Variancecited by 5

Built on by

Not cited yet.