DeepAI AI Chat
Log In Sign Up

On the Limitation of Convolutional Neural Networks in Recognizing Negative Images

by   Hossein Hosseini, et al.

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.


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

Detection and rejection of adversarial examples in security sensitive an...

Seeing in Words: Learning to Classify through Language Bottlenecks

Neural networks for computer vision extract uninterpretable features des...

Guiding human gaze with convolutional neural networks

The eye fixation patterns of human observers are a fundamental indicator...

Assessing Shape Bias Property of Convolutional Neural Networks

It is known that humans display "shape bias" when classifying new items,...

Seeing Neural Networks Through a Box of Toys: The Toybox Dataset of Visual Object Transformations

Deep convolutional neural networks (CNNs) have enjoyed tremendous succes...

Homography Estimation with Convolutional Neural Networks Under Conditions of Variance

Planar homography estimation is foundational to many computer vision pro...

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...