A scale-invariant framework for image classification with deep learning

Yalong Jiang, Zheru Chi

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)


In this paper, we propose a scale-invariant framework based on Convolutional Neural Networks (CNNs). The network exhibits robustness to scale and resolution variations in data. Previous efforts in achieving scale invariance were made on either integrating several variant-specific CNNs or data augmentation. However, these methods did not solve the fundamental problem that CNNs develop different feature representations for the variants of the same image. The topology proposed by this paper develops a uniform representation for each of the variants of the same image. The uniformity is acquired by concatenating scale-variant and scale-invariant features to enlarge the feature space so that the case when input images are of diverse variations but from the same class can be distinguished from another case when images are of different classes. Higher-order decision boundaries lead to the success of the framework. Experimental results on a challenging dataset substantiates that our framework performs better than traditional frameworks with the same number of free parameters. Our proposed framework can also achieve a higher training efficiency.
Original languageEnglish
Title of host publication2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
Number of pages6
ISBN (Electronic)9781538616451
Publication statusPublished - 27 Nov 2017
Event2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 - Banff Center, Banff, Canada
Duration: 5 Oct 20178 Oct 2017


Conference2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017


  • Convolutional neural networks
  • Higher-order decision boundaries
  • Robustness to scale variations
  • Scale invariance

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Control and Optimization

Cite this