Data Augmentation in Training CNNs: Injecting Noise to ImagesDownload PDF

25 Sept 2019 (modified: 22 Oct 2023)ICLR 2020 Conference Blind SubmissionReaders: Everyone
Keywords: deep learning, data augmentation, convolutional neural networks, noise, image processing, SSIM
TL;DR: Ideal methodology to inject noise to input data during CNN training
Abstract: Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying magnitudes to Convolutional Neural Network (CNN) architectures. Noise models that are distributed with different density functions are given common magnitude levels via Structural Similarity (SSIM) metric in order to create an appropriate ground for comparison. The basic results are conforming with the most of the common notions in machine learning, and also introduces some novel heuristics and recommendations on noise injection. The new approaches will provide better understanding on optimal learning procedures for image classification.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
Original Pdf: pdf
6 Replies