paper-with-me

Papers

Universal Adversarial Robustness of Texture and Shape-Biased Models

2019-11-23 · Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan, Ben Glocker, Emil C. Lupu

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial Perturbations (UAPs). We use UAPs to evaluate the robustness of DNN models with varying degrees of shape-based training. We find that shape-biased models do not markedly improve adversarial robustness, and we show that ensembles of texture and shape-biased models can improve universal adversarial robustness while maintaining strong performance.

📄 PDF Abstract BibTeX arXiv:1911.10364

Code (1)

kenny-co/sgd-uap-torch 공식 구현 pytorch

Tasks

Adversarial RobustnessImage Classification

Similar Papers 제목 키워드 기반

Shape-Texture Debiased Neural Network Training

2020-10-12 · ICLR 2021 1 · Yingwei Li, Qihang Yu, Mingxing Tan, Jieru Mei 외

Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. Our abla…

Adversarial RobustnessData AugmentationImage ClassificationRepresentation Learning

InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness

2022-06-12 · Shruthi Gowda, Bahram Zonooz, Elahe Arani

Humans rely less on spurious correlations and trivial cues, such as texture, compared to deep neural networks which lead to better generalization and robustness. It can be attributed to the prior knowledge or the high-le…

Inductive Bias

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

2020-08-10 · ICML 2020 1 · Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu 외

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN's texture-bias and its robustness a…

Domain GeneralizationRepresentation Learning

Robustness properties of Facebook's ResNeXt WSL models

2019-07-17 · A. Emin Orhan

We investigate the robustness properties of ResNeXt class image recognition models trained with billion scale weakly supervised data (ResNeXt WSL models). These models, recently made public by Facebook AI, were trained w…

Adversarial Robustness

StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures

2021-08-24 · Sanghyuk Chun, Song Park

Recent powerful vision classifiers are biased towards textures, while shape information is overlooked by the models. A simple attempt by augmenting training images using the artistic style transfer method, called Stylize…

Data AugmentationDiversityStyle Transfer