Extreme Image Transformations Affect Humans and Machines Differently
Some recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evaluate humans and ANNs on an object recognition task. We show that machines perform better than humans for certain transforms and struggle to perform at par with humans on others that are easy for humans. We quantify the differences in accuracy for humans and machines and find a ranking of difficulty for our transforms for human data. We also suggest how certain characteristics of human visual processing can be adapted to improve the performance of ANNs for our difficult-for-machines transforms.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionSimilar Papers 제목 키워드 기반
Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations
Recent neural network architectures have claimed to explain data from the human visual cortex. Their demonstrated performance is however still limited by the dependence on exploiting low-level features for solving visual…
Object RecognitionExtreme Image Transformations Facilitate Robust Latent Object Representations
Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. W…
feature selectionMemorizationObjectObject RecognitionForbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme
A novel algorithm for face obfuscation, called Forbes, which aims to obfuscate facial appearance recognizable by humans but preserve the identity and attributes decipherable by machines, is proposed in this paper. Forbes…
Finding the unicorn: Predicting early stage startup success through a hybrid intelligence method
Artificial intelligence is an emerging topic and will soon be able to perform decisions better than humans. In more complex and creative contexts such as innovation, however, the question remains whether machines are sup…
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation
Self-supervised learning is a powerful way to learn useful representations from natural data. It has also been suggested as one possible means of building visual representation in humans, but the specific objective and a…
Data AugmentationRepresentation LearningSelf-Supervised Learning