A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations

12 December 2022

Papers citing "A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations"

13 / 13 papers shown

Title
A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines Alexa R. Tartaglini Wai Keen Vong Brenden M. Lake 43 14 0 16 Feb 2022
Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning Grace W. Lindsay J. Merel T. Mrsic-Flogel M. Sahani SSL DRL 57 6 0 03 Dec 2021
The Emergence of the Shape Bias Results from Communicative Efficiency Eva Portelance Michael C. Frank Dan Jurafsky Alessandro Sordoni Romain Laroche 111 19 0 13 Sep 2021
Partial success in closing the gap between human and machine vision Robert Geirhos Kantharaju Narayanappa Benjamin Mitzkus Tizian Thieringer Matthias Bethge Felix Wichmann Wieland Brendel VLM AAML 69 227 0 14 Jun 2021
The Pitfalls of Simplicity Bias in Neural Networks Harshay Shah Kaustav Tamuly Aditi Raghunathan Prateek Jain Praneeth Netrapalli AAML 59 359 0 13 Jun 2020
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet Wieland Brendel Matthias Bethge SSL FAtt 79 561 0 20 Mar 2019
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness Robert Geirhos Patricia Rubisch Claudio Michaelis Matthias Bethge Felix Wichmann Wieland Brendel 96 2,662 0 29 Nov 2018
Generalisation in humans and deep neural networks Robert Geirhos Carlos R. Medina Temme Jonas Rauber Heiko H. Schutt Matthias Bethge Felix Wichmann OOD 107 606 0 27 Aug 2018
Measuring the tendency of CNNs to Learn Surface Statistical Regularities Jason Jo Yoshua Bengio AAML 62 250 0 30 Nov 2017
Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly Yongqin Xian Christoph H. Lampert Bernt Schiele Zeynep Akata VLM 139 1,565 0 03 Jul 2017
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study Samuel Ritter David Barrett Adam Santoro M. Botvinick 73 196 0 26 Jun 2017
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.8K 193,426 0 10 Dec 2015
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition C. Cadieu Ha Hong Daniel L. K. Yamins Nicolas Pinto Diego Ardila E. Solomon N. Majaj J. DiCarlo 86 786 0 12 Jun 2014