Approximating CNNs with Bag-of-local-Features models works surprisingly
well on ImageNet

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

20 March 2019

Wieland Brendel

Matthias Bethge

ArXiv (abs)PDF HTML

Papers citing "Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet"

12 / 312 papers shown

Title
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation Raphael Gontijo-Lopes Dong Yin Ben Poole Justin Gilmer E. D. Cubuk AAML 181 205 0 06 Jun 2019
Interpreting Adversarially Trained Convolutional Neural Networks Tianyuan Zhang Zhanxing Zhu AAML GAN FAtt 125 161 0 23 May 2019
What Do Adversarially Robust Models Look At? Takahiro Itazuri Yoshihiro Fukuhara Hirokatsu Kataoka Shigeo Morishima 32 5 0 19 May 2019
Batch Normalization is a Cause of Adversarial Vulnerability A. Galloway A. Golubeva T. Tanay M. Moussa Graham W. Taylor ODL AAML 84 80 0 06 May 2019
An Analysis of Pre-Training on Object Detection Hengduo Li Bharat Singh Mahyar Najibi Zuxuan Wu L. Davis ObjD 60 39 0 11 Apr 2019
Harvey Mudd College at SemEval-2019 Task 4: The Clint Buchanan Hyperpartisan News Detector M. Drissi Pedro Sandoval Segura Vivaswat Ojha J. Medero 16 6 0 10 Apr 2019
Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks Magdalini Paschali Muhammad Ferjad Naeem Walter Simson K. Steiger M. Mollenhauer Nassir Navab 58 19 0 05 Apr 2019
Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches Shane Storks Qiaozi Gao J. Chai 100 132 0 02 Apr 2019
SRM : A Style-based Recalibration Module for Convolutional Neural Networks HyunJae Lee Hyo-Eun Kim Hyeonseob Nam 72 228 0 26 Mar 2019
What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction Christoph Schöller Vincent Aravantinos F. Lay Alois C. Knoll 74 224 0 19 Mar 2019
Augmenting Model Robustness with Transformation-Invariant Attacks Houpu Yao Zhe Wang Guangyu Nie Yassine Mazboudi Yezhou Yang Yi Ren AAML OOD 31 3 0 31 Jan 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 221 2,682 0 29 Nov 2018