Improving model robustness in case of corrupted images is among the key
challenges to enable robust vision systems on smart devices, such as robotic
agents. Particularly, robust test-time performance is imperative for most of
the applications. This paper presents a novel approach to improve robustness of
any classification model, especially on severely corrupted images. Our method
(FROST) employs high-frequency features to detect input image corruption type,
and select layer-wise feature normalization statistics. FROST provides the
state-of-the-art results for different models and datasets, outperforming
competitors on ImageNet-C by up to 37.1% relative gain, improving baseline of
40.9% mCE on severe corruptions.

为了在智能设备上实现强大的视觉系统，尤其是机器人代理，提高对损坏图像的模型稳健性是其中的关键挑战。本文介绍了一种新方法（FROST），通过使用高频特征检测输入图像的损坏类型，并选择逐层特征归一化统计，从而提高任何分类模型的稳健性，尤其是在严重损坏的图像上。FROST 方法在不同模型和数据集上取得了最新的研究成果，在 ImageNet-C 上相较于竞争对手的最大相对收益为 37.1%，改善了 40.9% 的严重损坏情况下的基线 mCE。

基于 FFT 的选择与优化统计量方法用于严重损坏图像的鲁棒识别

FFT-based Selection and Optimization of Statistics for Robust  Recognition of Severely Corrupted Images

The ability to detect objects regardless of image distortions or weather
conditions is crucial for real-world applications of deep learning like
autonomous driving. We here provide an easy-to-use benchmark to assess how
object detection models perform when image quality degrades. The three
resulting benchmark datasets, termed Pascal-C, Coco-C and Cityscapes-C, contain
a large variety of image corruptions. We show that a range of standard object
detection models suffer a severe performance loss on corrupted images (down to
30--60\% of the original performance). However, a simple data augmentation
trick---stylizing the training images---leads to a substantial increase in
robustness across corruption type, severity and dataset. We envision our
comprehensive benchmark to track future progress towards building robust object
detection models. Benchmark, code and data are publicly available.

该论文提供了一个易于使用的基准来评估深度学习模型在图像质量下降的情况下完成目标检测的能力，并通过数据增强方法，即对训练图像进行艺术风格化处理，有效提高了模型鲁棒性。

在目标检测中进行鲁棒性基准测试：自动驾驶应对冬日来临

Benchmarking Robustness in Object Detection: Autonomous Driving when  Winter is Coming

The network flow optimization approach is offered for restoration of
grayscale and color images corrupted by noise. The Ising models are used as a
statistical background of the proposed method. The new multiresolution network
flow minimum cut algorithm, which is especially efficient in identification of
the maximum a posteriori estimates of corrupted images, is presented. The
algorithm is able to compute the MAP estimates of large size images and can be
used in a concurrent mode. We also describe the efficient solutions of the
problem of integer minimization of two energy functions for the Ising models of
gray-scale and color images.

提出了一种网络流优化方法，用于恢复受噪声干扰的灰度和彩色图像，其中使用了 Ising 模型作为所提出方法的统计背景，并呈现了特别有效的多分辨率网络流最小割算法，该算法能够计算出大尺寸图像的最大后验估计，并且能够以并发模式运行。同时还讨论了 Ising 模型灰度和彩色图像两个能量函数的整数最小化问题的高效解决方案。