2022/05/09 by Dakarai Crowder, Crowder, Dakarai, Girik Malik +1
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.2205.05167
openalex publication_date 2022/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 tasks. This strategy limits their performance in case of out-of-distribution/adversarial data. Humans, meanwhile learn abstract concepts and are mostly unaffected by even extreme image distortions. Humans and networks employ strikingly different strategies to solve visual tasks. To probe this, we introduce a novel set of image transforms and evaluate humans and networks on an object recognition task. We found performance for a few common networks quickly decreases while humans are able to recognize objects with a high accuracy.