Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are biased towards features that encode textures and that these alone are sufficient to generalize to unseen test data from the same distribution as the training data but often fail to generalize to out-of-distribution data. It has been shown that augmenting the training data with different image styles decreases this texture bias in favor of increased shape bias while at the same time improving robustness to common corruptions, such as noise and blur. Commonly, this is interpreted as shape bias increasing corruption robustness. However, this relationship is only hypothesized. We perform a systematic study of different ways of composing inputs based on natural images, explicit edge information, and stylization. While stylization is essential for achieving high corruption robustness, we do not find a clear correlation between shape bias and robustness. We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.
Synthetic corruptions gathered into a benchmark are frequently used to measure neural network robustness to distribution shifts. However, robustness to synthetic corruption benchmarks is not always predictive of robustness to distribution shifts encountered in real-world applications. In this paper, we propose a methodology to build synthetic corruption benchmarks that make robustness estimations more correlated with robustness to real-world distribution shifts. Using the overlapping criterion, we split synthetic corruptions into categories that help to better understand neural network robustn…
Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）
The state-of-the-art deep neural networks are vulnerable to common corruptions (e.g., input data degradations, distortions, and disturbances caused by weather changes, system error, and processing). While much progress has been made in analyzing and improving the robustness of models in image understanding, the robustness in video understanding is largely unexplored. In this paper, we establish a corruption robustness benchmark, Mini Kinetics-C and Mini SSV2-C, which considers temporal corruptions beyond spatial corruptions in images. We make the first attempt to conduct an exhaustive study on…
Korea Advanced Institute of Science Technology (KAIST)（韩国科学技术院）
The performance of DNNs trained on clean images has been shown to decrease when the test images have common corruptions. In this work, we interpret corruption robustness as a domain shift and propose to rectify batch normalization (BN) statistics for improving model robustness. This is motivated by perceiving the shift from the clean domain to the corruption domain as a style shift that is represented by the BN statistics. We find that simply estimating and adapting the BN statistics on a few (32 for instance) representation samples, without retraining the model, improves the corruption robust…
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
Data and Web Science Group, University of Mannheim（曼海姆大学数据与网络科学小组）；Max-Planck-Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克研究所信息学研究所萨尔兰信息学校区）
Fudan University（复旦大学）；Microsoft Research Asia（微软亚洲研究院）
With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their unique architecture impact robustness towards common corruptions. In this paper, we make the first attempt to probe into the robustness gap among ViT variants and explore underlying designs that are essential for robustness. Through an extensive and rigorous benchmarking, we demonstrate that simple architecture designs such as overlapping patch embedding and …
Southern University of Science and Technology（南方科技大学）
When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions. However, current evaluations of person ReID only consider the performance on clean datasets and ignore images in various corrupted scenarios. In this work, we comprehensively establish six ReID benchmarks for learning corruption invariant representation. In the field of ReID, we are the first to conduct an exhaustive study on corruption invariant learning in single- and cross-modality datasets, including M…
University of Freiburg（弗莱堡大学）；Inria（法国国家信息与自动化研究所）
CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts, or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, whic…
Artificial Intelligence Research Institute, Shenzhen MSU-BIT University（深圳北理莫斯科大学人工智能研究院）；Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing（粤港澳情感智能与普适计算联合实验室）；Shenzhen University（深圳大学）；South China University of Technology（华南理工大学）
Temporal action detection (TAD) aims to locate action positions and recognize action categories in long-term untrimmed videos. Although many methods have achieved promising results, their robustness has not been thoroughly studied. In practice, we observe that temporal information in videos can be occasionally corrupted, such as missing or blurred frames. Interestingly, existing methods often incur a significant performance drop even if only one frame is affected. To formally evaluate the robustness, we establish two temporal corruption robustness benchmarks, namely THUMOS14-C and ActivityNet-…
Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection
School of Electrical & Computer Engineering, National Technical University Athens（雅典国立技术大学电气与计算机工程学院）；Hellenic Drones S.A.（希腊无人机公司）；School of Electronic Engineering & Computer Science, Queen Mary University of London（伦敦大学玛丽皇后学院电子工程与计算机科学学院）
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several new data augmentations have been proposed that significantly improve performance on ImageNet-C, a benchmark of such corruptions. However, there is still a lack of basic understanding on the relationship between data augmentations and test-time corruptions. To this end, we develop a feature space for image transforms, and then use a new measure in this space between augmentations and corruptions called the Minimal Sampl…
Exploring the Robustness of Human Parsers Towards Common Corruptions
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Sun Yat-sen University（中山大学）；Westlake University（西湖大学）；OPPO；Tsinghua University（清华大学）
Carnegie Mellon University（卡内基梅隆大学）；Symbiosis Institute of Technology (SIT), Symbiosis International (Deemed University)（共生技术学院，共生国际（视为大学））；Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis International (Deemed University)（共生应用人工智能中心，共生国际（视为大学））
Several popular computer vision (CV) datasets, specifically employed for Object Detection (OD) in autonomous driving tasks exhibit biases due to a range of factors including weather and lighting conditions. These biases may impair a model's generalizability, rendering it ineffective for OD in novel and unseen datasets. Especially, in autonomous driving, it may prove extremely high risk and unsafe for the vehicle and its surroundings. This work focuses on understanding these datasets better by identifying such "good-weather" bias. Methods to mitigate such bias which allows the OD models to perf…
University of California, Berkeley（加州大学伯克利分校）；Oregon State University（俄勒冈州立大学）
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations. Unlike recent robustness research, this benchmark evaluates performance on common corruptions and perturbations not worst-case adversarial perturbations. We find that there are negligible changes in relative cor…
Tsinghua University（清华大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；UC Santa Cruz（加州大学圣克鲁兹分校）
Neural Radiance Field (NeRF) has demonstrated excellent quality in novel view synthesis, thanks to its ability to model 3D object geometries in a concise formulation. However, current approaches to NeRF-based models rely on clean images with accurate camera calibration, which can be difficult to obtain in the real world, where data is often subject to corruption and distortion. In this work, we provide the first comprehensive analysis of the robustness of NeRF-based novel view synthesis algorithms in the presence of different types of corruptions. We find that NeRF-based models are significant…
3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor noises, etc., provoking concerns about the safety and reliability of autonomous driving systems. To comprehensively and rigorously benchmark the corruption robustness of 3D detectors, in this paper we design 27 types of common corruptions for both LiDAR and camera inputs considering real-world driving scenarios. By synthesizing these corruptions on public dataset…
3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness a…
Nanyang Technological University（南洋理工大学）；Agency for Science, Technology and Research（新加坡科技研究局）
Model robustness is vital for the reliable deployment of machine learning models in real-world applications. Recent studies have shown that data augmentation can result in model over-relying on features in the low-frequency domain, sacrificing performance against low-frequency corruptions, highlighting a connection between frequency and robustness. Here, we take one step further to more directly study the frequency bias of a model through the lens of its Jacobians and its implication to model robustness. To achieve this, we propose Jacobian frequency regularization for models' Jacobians to hav…
University of California, Berkeley（加州大学伯克利分校）；Oregon State University（俄勒冈州立大学）
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performance on commonplace corruptions not worst-case adversarial corruptions. We find that there are negligible changes in relative corruption robustness from AlexNet to ResNet classifiers, and we discover ways to enhance corruption robustness. Then we propose a new dataset called Icons-…
Recently, vision transformers and MLP-based models have been developed in order to address some of the prevalent weaknesses in convolutional neural networks. Due to the novelty of transformers being used in this domain along with the self-attention mechanism, it remains unclear to what degree these architectures are robust to corruptions. Despite some works proposing that data augmentation remains essential for a model to be robust against corruptions, we propose to explore the impact that the architecture has on corruption robustness. We find that vision transformer architectures are inherent…
Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；ETH Zürich（苏黎世联邦理工学院）；Imperial College London（伦敦帝国理工学院）
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability, prior works have built complex data augmentation strategies, combining multiple methods to enrich the training data. However, introducing intricate design choices or heuristics makes it hard to understand which elements of these methods are indeed crucial for improving robustness. In this work, we take a step back and follow a principled approach to achieve robustness to common corruptions. We propose PRIME, a genera…
When designing a diagnostic model for a clinical application, it is crucial to guarantee the robustness of the model with respect to a wide range of image corruptions. Herein, an easy-to-use benchmark is established to evaluate how deep neural networks perform on corrupted pathology images. Specifically, corrupted images are generated by injecting nine types of common corruptions into validation images. Besides, two classification and one ranking metrics are designed to evaluate the prediction and confidence performance under corruption. Evaluated on two resulting benchmark datasets, we find t…
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robustness to out-of-distribution inputs for semantic segmentation models for little to no cost. In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid in order to improve understanding their relationship to robustness. As a result of this analysis, we propose combini…
Neural Networks are sensitive to various corruptions that usually occur in real-world applications such as blurs, noises, low-lighting conditions, etc. To estimate the robustness of neural networks to these common corruptions, we generally use a group of modeled corruptions gathered into a benchmark. Unfortunately, no objective criterion exists to determine whether a benchmark is representative of a large diversity of independent corruptions. In this paper, we propose a metric called corruption overlapping score, which can be used to reveal flaws in corruption benchmarks. Two corruptions overl…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；NVIDIA（英伟达）；ASU（亚利桑那州立大学（ASU））
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the first comprehensive benchmark on 3D point cloud corruption robustness, consisting of 15 common and realistic corruptions. Our evaluation shows a significant gap between the performances on ModelNet40 and ModelNet40-C for state-of-the-art (SOTA) models. To reduce the gap, we propose a simple but effective method by combining PointCutMix-R and TENT after evaluatin…
University of Michigan（密歇根大学）；Stanford University（斯坦福大学）
We study how networking corruptions--data corruptions caused by networking errors--affect video machine learning (ML) models. We discover apparent networking corruptions in Kinetics-400, a benchmark video ML dataset. In a simulation study, we investigate (1) what artifacts networking corruptions cause, (2) how such artifacts affect ML models, and (3) whether standard robustness methods can mitigate their negative effects. We find that networking corruptions cause visual and temporal artifacts (i.e., smeared colors or frame drops). These networking corruptions degrade performance on a variety o…
Huazhong University of Science and Technology（华中科技大学）；The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；SenseTime Research and Tetras.AI（商汤科技研究院与Tetras.AI）
Human pose estimation is a fundamental yet challenging task in computer vision, which aims at localizing human anatomical keypoints. However, unlike human vision that is robust to various data corruptions such as blur and pixelation, current pose estimators are easily confused by these corruptions. This work comprehensively studies and addresses this problem by building rigorous robust benchmarks, termed COCO-C, MPII-C, and OCHuman-C, to evaluate the weaknesses of current advanced pose estimators, and a new algorithm termed AdvMix is proposed to improve their robustness in different corruption…
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
Nanyang Technological University（南洋理工大学）；East China Normal University（华东师范大学）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；New York University（纽约大学）
University of Tübingen（蒂宾根大学）；IMPRS-IS（国际马克斯·普朗克智能系统研究学院）；LMU Munich（慕尼黑大学）
Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model robustness against common corruptions (like ImageNet-C) underestimate model robustness in many (but not all) application scenarios. The key insight is that in many scenarios, multiple unlabeled examples of the corruptions are available and can be used for unsupervised online adaptation. Replacing the activation statistics estimated by batch normalization on th…
Modularity Trumps Invariance for Compositional Robustness
Massachusetts Institute of Technology（麻省理工学院）；Artificial Intelligence Laboratory（人工智能实验室）；Fujitsu Limited（富士通有限公司）；Fujitsu Research of America, Inc.（美国富士通研究公司）
