arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04254cs.LGcs.CVstat.ML
收藏

鲁棒表示学习的信息丢失:形状偏差视角

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

Peking University(北京大学);Microsoft Research Asia(微软亚洲研究院)

Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang

摘要:

众所周知,卷积神经网络(CNN)在做出决策时更多地依赖于局部纹理而不是全局形状。最近的工作也表明了CNN的纹理偏差和它的鲁棒性之间的密切关系,对分布偏移,对抗扰动,随机腐败等,在这项工作中,我们试图提高各种鲁棒性普遍减轻CNN的纹理偏差。从人类视觉系统的启发,我们提出了一个轻量级的模型无关的方法,即信息丢弃(InfoDrop),以提高可解释性和减少纹理偏差。具体地说,我们区分纹理形状的基础上的局部自信息的图像,并采用一个Drop-like算法去相关的模型输出从局部纹理。通过大量的实验,我们观察到增强的鲁棒性在各种情况下(领域泛化,Few-Shot分类,图像损坏,和对抗扰动)。据我们所知,这项工作是最早的尝试之一,以提高不同种类的鲁棒性在一个统一的模型,形状偏差和鲁棒性之间的关系,也对值得信赖的机器学习算法的新方法提供了新的光。代码可在https://github.com/bfshi/InfoDrop上获得。

英文摘要:

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 against distribution shift, adversarial perturbation, random corruption, etc. In this work, we attempt at improving various kinds of robustness universally by alleviating CNN's texture bias. With inspiration from the human visual system, we propose a light-weight model-agnostic method, namely Informative Dropout (InfoDrop), to improve interpretability and reduce texture bias. Specifically, we discriminate texture from shape based on local self-information in an image, and adopt a Dropout-like algorithm to decorrelate the model output from the local texture. Through extensive experiments, we observe enhanced robustness under various scenarios (domain generalization, few-shot classification, image corruption, and adversarial perturbation). To the best of our knowledge, this work is one of the earliest attempts to improve different kinds of robustness in a unified model, shedding new light on the relationship between shape-bias and robustness, also on new approaches to trustworthy machine learning algorithms. Code is available at https://github.com/bfshi/InfoDrop.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑