134 citations · 258 across the 6 of their papers we have counts for
5 papers · 1 filter
Assessing Shape Bias Property of Convolutional Neural Networks
Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1
It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networ…
Semantic Adversarial Examples
Hossein Hosseini, Radha Poovendran
Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mos…
Google's Cloud Vision API Is Not Robust To Noise
Hossein Hosseini, Baicen Xiao, Radha Poovendran
Google has recently introduced the Cloud Vision API for image analysis. According to the demonstration website, the API "quickly classifies images into thousands of categories, det…
Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos
Hossein Hosseini, Baicen Xiao, Radha Poovendran
Despite the rapid progress of the techniques for image classification, video annotation has remained a challenging task. Automated video annotation would be a breakthrough technolo…
On the Limitation of Convolutional Neural Networks in Recognizing Negative Images
Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance on a variety of computer vision tasks, particularly visual classification problems, where new algori…