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

29 November 2018

Wieland Brendel

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

26 / 426 papers shown

Title
Exploring Unlabeled Faces for Novel Attribute Discovery Hyojin Bahng Sunghyo Chung Seungjoo Yoo Jaegul Choo CVBM 13 12 0 06 Dec 2019
Angular Visual Hardness Beidi Chen Weiyang Liu Zhiding Yu Jan Kautz Anshumali Shrivastava Animesh Garg Anima Anandkumar AAML 40 51 0 04 Dec 2019
Adversarial Examples in Modern Machine Learning: A Review R. Wiyatno Anqi Xu Ousmane Amadou Dia A. D. Berker AAML 13 103 0 13 Nov 2019
Pose estimation and bin picking for deformable products Benjamin Joffe Tevon Walker Konrad Ahlin 9 12 0 12 Nov 2019
Semantic Object Accuracy for Generative Text-to-Image Synthesis Tobias Hinz Stefan Heinrich S. Wermter EGVM 24 158 0 29 Oct 2019
Reducing Domain Gap by Reducing Style Bias Hyeonseob Nam HyunJae Lee Jongchan Park Wonjun Yoon Donggeun Yoo 22 61 0 25 Oct 2019
Multimodal Image Outpainting With Regularized Normalized Diversification Lingzhi Zhang Jiancong Wang Jianbo Shi DiffM 8 15 0 25 Oct 2019
Learning the Difference that Makes a Difference with Counterfactually-Augmented Data Divyansh Kaushik Eduard H. Hovy Zachary Chase Lipton CML 9 560 0 26 Sep 2019
A Closer Look at Domain Shift for Deep Learning in Histopathology Karin Stacke Gabriel Eilertsen Jonas Unger Claes Lundström OOD 10 63 0 25 Sep 2019
Intensity augmentation for domain transfer of whole breast segmentation in MRI L. Hesse Grey Kuling M. Veta Anne L. Martel 14 5 0 05 Sep 2019
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming Claudio Michaelis Benjamin Mitzkus Robert Geirhos E. Rusak Oliver Bringmann Alexander S. Ecker Matthias Bethge Wieland Brendel 3DPC 19 436 0 17 Jul 2019
Natural Adversarial Examples Dan Hendrycks Kevin Zhao Steven Basart Jacob Steinhardt D. Song OODD 50 1,417 0 16 Jul 2019
Invariant Risk Minimization Martín Arjovsky Léon Bottou Ishaan Gulrajani David Lopez-Paz OOD 27 2,152 0 05 Jul 2019
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation Raphael Gontijo-Lopes Dong Yin Ben Poole Justin Gilmer E. D. Cubuk AAML 21 204 0 06 Jun 2019
Selective Style Transfer for Text Raul Gomez Ali Furkan Biten Lluís Gómez J. Gibert Marccal Rusinol Dimosthenis Karatzas 19 17 0 04 Jun 2019
Cross-Domain Transferability of Adversarial Perturbations Muzammal Naseer Salman H. Khan M. H. Khan F. Khan Fatih Porikli AAML 25 145 0 28 May 2019
Interpreting Adversarially Trained Convolutional Neural Networks Tianyuan Zhang Zhanxing Zhu AAML GAN FAtt 25 157 0 23 May 2019
Zero-shot Knowledge Transfer via Adversarial Belief Matching P. Micaelli Amos Storkey 17 227 0 23 May 2019
What Do Adversarially Robust Models Look At? Takahiro Itazuri Yoshihiro Fukuhara Hirokatsu Kataoka Shigeo Morishima 16 5 0 19 May 2019
Adversarial Training and Robustness for Multiple Perturbations Florian Tramèr Dan Boneh AAML SILM 17 374 0 30 Apr 2019
Embodied Visual Recognition Jianwei Yang Zhile Ren Mingze Xu Xinlei Chen David J. Crandall Devi Parikh Dhruv Batra 32 26 0 09 Apr 2019
Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets Riccardo Volpi Vittorio Murino 31 29 0 28 Mar 2019
Deep segmentation networks predict survival of non-small cell lung cancer Stephen Seung-Yeob Baek Yusen He B. Allen John Buatti Brian J. Smith ... S. Seyedin M. Gannon Katherine R. Cabel Yusung Kim Xiaodong Wu 6 82 0 26 Mar 2019
Adversarial Examples Are a Natural Consequence of Test Error in Noise Nic Ford Justin Gilmer Nicholas Carlini E. D. Cubuk AAML 22 318 0 29 Jan 2019
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks Kenneth T. Co Luis Muñoz-González Sixte de Maupeou Emil C. Lupu AAML 19 67 0 30 Sep 2018
DeepFense: Online Accelerated Defense Against Adversarial Deep Learning B. Rouhani Mohammad Samragh Mojan Javaheripi T. Javidi F. Koushanfar AAML 10 15 0 08 Sep 2017