Human and DNN Classification Performance on Images With Quality Distortions

By Samuel F. Dodge, Lina Karam. 2019

40 citations recorded by the source corpus.

Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high-quality image datasets, yet in practical applications the input images cannot be assumed to be of high quality. Modern deep neural networks (DNNs) have been shown to perform poorly on images affected by blur or noise distortions. In this work, we investigate whether human subjects also perform poorly on distorted stimuli and provide a direct comparison with the performance of DNNs. Specifically, we study the effect of Gaussian blur and additive Gaussian noise on human and DNN classification performance. We perform two experiments: one crowd-sourced experiment with unlimited stimulus display time, and one lab experiment with 100ms display time. In both cases, we found that humans outperform neural networks on distorted stimuli, even when the networks are retrained with distorted data.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Industrial and Manufacturing Engineering, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

In Industrial and Manufacturing Engineering

In Media Technology

Citations in the corpus

Shortcut learning in deep neural networks (2020, background): “This has been reported in various cases such as shifting the image by a few pixels [47], rotating the object [49], adding a bit of random noise or blur [51, 50, 52, 53] or (as discussed earlier) by changing background [9] or texture while keeping the shape intact [38] (see Figure 4 for examples).”