arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.11900cs.LGcs.CVstat.ML
收藏

图像变换集上分布移位的模型脆弱性研究

Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets

Istituto Italiano di Tecnologia(意大利技术研究院);Università di Verona(维罗纳大学);Huawei Technologies (Ireland) Co., Ltd.(华为技术(爱尔兰)有限公司)

Riccardo Volpi, Vittorio Murino

摘要:

我们关注的是计算机视觉模型对分布变化的脆弱性。我们制定了一个组合优化的问题,允许评估区域中的图像空间中,一个给定的模型是更脆弱的,在图像变换应用到输入,并面对它与标准的搜索算法。我们进一步将这一想法嵌入到训练过程中,在训练过程中,我们根据当前模型在迭代过程中最容易受到的图像变换来定义新的数据增强规则。分类和语义分割问题的实证评估表明,设计的算法允许训练模型,更强大的内容保持图像操作,并在一般情况下,对分布的变化。

英文摘要:

We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard search algorithms. We further embed this idea in a training procedure, where we define new data augmentation rules according to the image transformations that the current model is most vulnerable to, over iterations. An empirical evaluation on classification and semantic segmentation problems suggests that the devised algorithm allows to train models that are more robust against content-preserving image manipulations and, in general, against distributional shifts.

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。

↑