On Improving Generalization of CNN-Based Image Classification with Delineation Maps Using the CORF Push-Pull Inhibition Operator

Swaroop Bennabhaktula*, Joey Antonisse, George Azzopardi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Downloads (Pure)


Deployed image classification pipelines are typically dependent on the images captured in real-world environments. This means that images might be affected by different sources of perturbations (e.g. sensor noise in low-light environments). The main challenge arises by the fact that image quality directly impacts the reliability and consistency of classification tasks. This challenge has, hence, attracted wide interest within the computer vision communities. We propose a transformation step that attempts to enhance the generalization ability of CNN models in the presence of unseen noise in the test set. Concretely, the delineation maps of given images are determined using the CORF push-pull inhibition operator. Such an operation transforms an input image into a space that is more robust to noise before being processed by a CNN. We evaluated our approach on the Fashion MNIST data set with an AlexNet model. It turned out that the proposed CORF-augmented pipeline achieved comparable results on noise-free images to those of a conventional AlexNet classification model without CORF delineation maps, but it consistently achieved significantly superior performance on test images perturbed with different levels of Gaussian and uniform noise.
Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns
Subtitle of host publicationCAIP 2021
EditorsN Tsapatsoulis, A Panayides, T Theocharides, A Lanitis, C Pattichis, M Vento
Place of PublicationCham
Number of pages11
VolumePart 1
ISBN (Electronic)978-3-030-89128-2
ISBN (Print)978-3-030-89127-5
Publication statusPublished - 31-Oct-2021
Event19th International Conference, CAIP 2021 - Virtual event
Duration: 28-Sep-202130-Sep-2021

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


Conference19th International Conference, CAIP 2021

Cite this