Author of the publication

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.

, , , , , and . ICLR, OpenReview.net, (2019)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness., , , , , and . CoRR, (2018)Excessive Invariance Causes Adversarial Vulnerability, , , and . (2018)cite arxiv:1811.00401.Towards the first adversarially robust neural network model on MNIST., , , and . ICLR (Poster), OpenReview.net, (2019)Excessive Invariance Causes Adversarial Vulnerability., , , and . ICLR (Poster), OpenReview.net, (2019)The Notorious Difficulty of Comparing Human and Machine Perception., , , , , and . CoRR, (2020)Playing repeated games with Large Language Models., , , , , and . CoRR, (2023)Closing the Generalization Gap in One-Shot Object Detection., , and . CoRR, (2020)Neural system identification for large populations separating "what" and "where"., , , and . NIPS, page 3506-3516. (2017)System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina., , , , , , and . NeurIPS, (2020)Partial success in closing the gap between human and machine vision., , , , , , and . NeurIPS, page 23885-23899. (2021)