On the Limitation of Convolutional Neural Networks in Recognizing Negative Images

03/20/2017
by   Hossein Hosseini, et al.
0

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance on a variety of computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. In this paper, we examine whether CNNs are capable of learning the semantics of training data. To this end, we evaluate CNNs on negative images, since they share the same structure and semantics as regular images and humans can classify them correctly. Our experimental results indicate that when training on regular images and testing on negative images, the model accuracy is significantly lower than when it is tested on regular images. This leads us to the conjecture that current training methods do not effectively train models to generalize the concepts. We then introduce the notion of semantic adversarial examples - transformed inputs that semantically represent the same objects, but the model does not classify them correctly - and present negative images as one class of such inputs.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

04/24/2018

Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning

Detection and rejection of adversarial examples in security sensitive an...
03/21/2018

Assessing Shape Bias Property of Convolutional Neural Networks

It is known that humans display "shape bias" when classifying new items,...
12/18/2017

Guiding human gaze with convolutional neural networks

The eye fixation patterns of human observers are a fundamental indicator...
10/02/2020

Homography Estimation with Convolutional Neural Networks Under Conditions of Variance

Planar homography estimation is foundational to many computer vision pro...
01/22/2022

Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs

Even though convolutional neural networks can classify objects in images...
09/11/2018

Taking a machine's perspective: Humans can decipher adversarial images

How similar is the human mind to the sophisticated machine-learning syst...
09/11/2018

Taking a machine's perspective: Human deciphering of adversarial images

How similar is the human mind to the sophisticated machine-learning syst...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.