最新的深层神经网络容易受到共同损坏的影响(例如,由天气变化,系统错误和处理引起的输入数据降解,扭曲和干扰)。尽管在分析和改善模型在图像理解中的鲁棒性方面取得了很多进展,但视频理解中的鲁棒性在很大程度上没有探索。在本文中,我们建立了腐败的鲁棒性基准,迷你动力学-C和Mini SSV2-C,该基准认为图像中的空间腐败以外的时间腐败。我们首次尝试对建立的基于CNN和基于变压器的时空模型的腐败鲁棒性进行详尽的研究。该研究提供了有关强大模型设计和培训的一些指导:基于变压器的模型比基于CNN的模型更好地腐败鲁棒性。时空模型的概括能力意味着对时间腐败的鲁棒性;模型腐败鲁棒性(尤其是时间领域的鲁棒性)通过计算成本和模型容量增强,这可能与提高模型计算效率的当前趋势相矛盾。此外,我们发现与图像相关的任务(例如,具有噪声的训练模型)的鲁棒性干预可能对时空模型不起作用。
translated by 谷歌翻译
近年来,我们在视频动作识别方面取得了巨大进展。有几种基于卷积神经网络(CNN)的模型,采用了一些基于变压器的方法,可在现有基准数据集上提供最先进的性能。但是,对于这些模型,尚未研究大规模的鲁棒性,这对于现实世界应用而言是关键方面。在这项工作中,我们对这些现有模型进行大规模鲁棒性分析,以供视频识别。我们主要关注因现实世界扰动而不是对抗性扰动引起的分配变化的鲁棒性。我们提出了四个不同的基准数据集,即HMDB-51P,UCF-101P,Kinetics-400P和SSV2P,并研究了六种针对90种不同扰动的六种不同最先进的动作识别模型的鲁棒性。该研究揭示了一些有趣的发现,1)基于变压器的模型与基于CNN的模型相比,对于大多数扰动,基于变压器的模型始终更健壮,2)预训练有助于基于变压器的模型比基于CNN的模型更适合不同的扰动,而3)所有研究的模型对动力学数据集的时间扰动都具有鲁棒性,但在SSV2上却不是。这表明时间信息对于SSV2数据集的动作标签预​​测比动力学数据集更为重要。我们希望这项研究能够作为在强大的视频行动识别中进行未来研究的基准。有关该项目的更多详细信息,请访问https://rose-ar.github.io/。
translated by 谷歌翻译
Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models against common distribution shifts has so far not been demonstrated. We propose to address this problem with an approach tailored to spatio-temporal models that is capable of adaptation on a single video sample at a step. It consists in a feature distribution alignment technique that aligns online estimates of test set statistics towards the training statistics. We further enforce prediction consistency over temporally augmented views of the same test video sample. Evaluations on three benchmark action recognition datasets show that our proposed technique is architecture-agnostic and able to significantly boost the performance on both, the state of the art convolutional architecture TANet and the Video Swin Transformer. Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts. Code will be available at \url{https://github.com/wlin-at/ViTTA}.
translated by 谷歌翻译
在将人重新识别(REID)模型部署在安全关键型应用程序中时,它是关键,以了解模型的鲁棒性,以反对不同的图像损坏阵列。但是,当前对人的评估Reid仅考虑干净数据集的性能,并忽略各种损坏方案中的图像。在这项工作中,我们全面建立了六种Reid基准,用于学习腐败不变的代表。在Reid领域,我们是第一个在单个和跨模式数据集中开展腐败腐败的彻底研究,包括市场-1501,CUHK03,MSMT17,REGDB,SYSU-MM01。在再现和检查最近的REID方法的鲁棒性能后,我们有一些观察结果:1)基于变压器的模型对损坏的图像更加强大,与基于CNN的模型相比,2)增加了随机擦除的概率(常用的增强方法)伤害模型腐败鲁棒性,3)交叉数据集泛化改善腐败鲁棒性增加。通过分析上述观察,我们提出了一个强大的基线,对单一和跨型号的内部数据集,实现了对不同腐败的改善的鲁棒性。我们的代码可在https://github.com/minghuichen43/cil -reid上获得。
translated by 谷歌翻译
我们研究如何通过网络错误引起的网络腐败 - 与视频机器学习(ML)模型有关的数据。我们发现了基于基准视频ML数据集的Kinetics-400中明显的网络损坏。在一项仿真研究中,我们研究了(1)哪些人伪影造成了网络腐败的原因,(2)这种伪像如何影响ML模型,以及(3)标准鲁棒性方法是否可以减轻其负面影响。我们发现网络损坏会导致视觉和时间伪像(即涂抹颜色或框架掉落)。这些网络损坏在各种视频ML任务上降低了性能,但效果因任务和数据集而异,具体取决于任务所需的时间上下文。最后,我们评估数据扩展(用于数据损坏的标准防御) - 但发现它不会恢复性能。
translated by 谷歌翻译
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 corruption robustness from AlexNet classifiers to ResNet classifiers. Afterward we discover ways to enhance corruption and perturbation robustness. We even find that a bypassed adversarial defense provides substantial common perturbation robustness. Together our benchmarks may aid future work toward networks that robustly generalize.
translated by 谷歌翻译
在为临床应用设计诊断模型时,至关重要的是要确保模型在各种图像损坏方面的稳健性。在此,建立了易于使用的基准,以评估神经网络在损坏的病理图像上的性能。具体而言,通过将九种类型的常见损坏注入验证图像来生成损坏的图像。此外,两个分类和一个排名指标旨在评估腐败下的预测和信心表现。在两个结果的基准数据集上进行了评估,我们发现(1)各种深神经网络模型的准确性降低(两倍是清洁图像上的误差的两倍)和对损坏图像的不可靠置信度估计; (2)验证和测试错误之间的相关性较低,同时用我们的基准替换验证集可以增加相关性。我们的代码可在https://github.com/superjamessyx/robustness_benchmark上找到。
translated by 谷歌翻译
Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness is essential for practical applications. To improve robustness, we study an image enhancement method that generates recognition-friendly images without retraining the recognition model. We propose a novel image enhancement method, AugNet, which is based on differentiable data augmentation techniques and generates a blended image from many augmented images to improve the recognition accuracy under distribution shifts. In addition to standard data augmentations, AugNet can also incorporate deep neural network-based image transformation, which further improves the robustness. Because AugNet is composed of differentiable functions, AugNet can be directly trained with the classification loss of the recognition model. AugNet is evaluated on widely used image recognition datasets using various classification models, including Vision Transformer and MLP-Mixer. AugNet improves the robustness with almost no reduction in classification accuracy for clean images, which is a better result than the existing methods. Furthermore, we show that interpretation of distribution shifts using AugNet and retraining based on that interpretation can greatly improve robustness.
translated by 谷歌翻译
不变性于广泛的图像损坏,例如翘曲,噪声或颜色移位,是在计算机视觉中建立强大模型的一个重要方面。最近,已经提出了几种新的数据增强,从而显着提高了Imagenet-C的性能,这是这种腐败的基准。但是,对数据增强和测试时间损坏之间的关系仍然缺乏基本的理解。为此,我们开发了图像变换的一个特征空间,然后在增强和损坏之间使用该空间中的新措施,称为最小示例距离,以演示相似性和性能之间的强相关性。然后,当测试时间损坏被对来自Imagenet-C中的测试时间损坏被采样时,我们调查最近的数据增强并观察腐败鲁棒性的重大退化。我们的结果表明,通过对感知同类增强的培训来提高测试错误,数据增强可能不会超出现有的基准。我们希望我们的结果和工具将允许更强大的进展,以提高对图像损坏的稳健性。我们在https://github.com/facebookresearch/augmentation - 窗子提供代码。
translated by 谷歌翻译
聚集到基准中的综合损坏经常用于测量神经网络的鲁棒性与分布换档。然而,对综合腐败基准的鲁棒性并不总是预测现实世界应用中遇到的分销班次的鲁棒性。在本文中,我们提出了一种构建综合腐败基准的方法,使鲁棒性估计与对现实世界分布班次的鲁棒性更相关。使用重叠的标准,我们将合成腐败分成了有助于更好地理解神经网络的鲁棒性的类别。根据这些类别,我们确定三个相关参数,以便在构建(1)代表类别的腐败基准时考虑到(1)代表类别,(2)其相对平衡,(3)所考虑的规模基准。在这样做时,我们建立了新的合成腐败选择,这些选择比现有的综合腐败基准更具预测到自然腐败的鲁棒性。
translated by 谷歌翻译
尽管对图像分类任务的表现令人印象深刻,但深网络仍然难以概括其数据的许多常见损坏。为解决此漏洞,事先作品主要专注于提高其培训管道的复杂性,以多样性的名义结合多种方法。然而,在这项工作中,我们逐步回来并遵循原则的方法来实现共同腐败的稳健性。我们提出了一个普遍的数据增强方案,包括最大熵图像变换的简单系列。我们展示了Prime优于现有技术的腐败鲁棒性,而其简单和即插即用性质使其能够与其他方法结合以进一步提升其稳健性。此外,我们分析了对综合腐败图像混合策略的重要性,并揭示了在共同腐败背景下产生的鲁棒性准确性权衡的重要性。最后,我们表明我们的方法的计算效率允许它在线和离线数据增强方案轻松使用。
translated by 谷歌翻译
本文对实例分割模型进行了全面评估,这些模型与现实世界图像损坏以及室外图像集合,例如与培训数据集不同的设置捕获的图像。室外图像评估显示了模型的概括能力,现实世界应用的一个基本方面以及广泛研究的域适应性主题。当设计用于现实世界应用程序的实例分割模型并选择现成的预期模型以直接用于手头的任务时,这些提出的鲁棒性和泛化评估很重要。具体而言,这项基准研究包括最先进的网络架构,网络骨架,标准化层,从头开始训练的模型,从头开始与预处理的网络以及多任务培训对稳健性和概括的影响。通过这项研究,我们获得了一些见解。例如,我们发现组归一化增强了跨损坏的网络的鲁棒性,其中图像内容保持不变,但损坏却添加在顶部。另一方面,分批归一化改善了图像特征统计信息在不同数据集上的概括。我们还发现,单阶段探测器比其训练大小不太概括到更大的图像分辨率。另一方面,多阶段探测器可以轻松地用于不同尺寸的图像上。我们希望我们的全面研究能够激发更强大和可靠的实例细分模型的发展。
translated by 谷歌翻译
经过认证的稳健性保证衡量模型对测试时间攻击的稳健性,并且可以评估模型对现实世界中部署的准备情况。在这项工作中,我们批判性地研究了对基于随机平滑的认证方法的对抗鲁棒性如何在遇到配送外(OOD)数据的最先进的鲁棒模型时改变。我们的分析显示了这些模型的先前未知的漏洞,以低频OOD数据,例如与天气相关的损坏,使这些模型不适合在野外部署。为了缓解这个问题,我们提出了一种新的数据增强方案,Fourimix,产生增强以改善训练数据的光谱覆盖范围。此外,我们提出了一种新规范器,鼓励增强数据的噪声扰动的一致预测,以提高平滑模型的质量。我们发现Fouriermix增强有助于消除可认真强大的模型的频谱偏差,使其能够在一系列ood基准上实现明显更好的稳健性保证。我们的评估还在突出模型的光谱偏差时揭示了当前的OOD基准。为此,我们提出了一个全面的基准套件,其中包含来自光谱域中不同区域的损坏。对拟议套件上流行的增强方法培训的模型的评估突出了它们的光谱偏差,并建立了富硫克斯训练型模型在实现整个频谱上变化下的更好认证的鲁棒性担保的优势。
translated by 谷歌翻译
We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbations (noise, simulated weather artifacts, adversarial examples, etc.), which leaves open how robustness on synthetic distribution shift relates to distribution shift arising in real data. Informed by an evaluation of 204 ImageNet models in 213 different test conditions, we find that there is often little to no transfer of robustness from current synthetic to natural distribution shift. Moreover, most current techniques provide no robustness to the natural distribution shifts in our testbed. The main exception is training on larger and more diverse datasets, which in multiple cases increases robustness, but is still far from closing the performance gaps. Our results indicate that distribution shifts arising in real data are currently an open research problem. We provide our testbed and data as a resource for future work at https://modestyachts.github.io/imagenet-testbed/.
translated by 谷歌翻译
Video Super-Resolution (VSR) aims to restore high-resolution (HR) videos from low-resolution (LR) videos. Existing VSR techniques usually recover HR frames by extracting pertinent textures from nearby frames with known degradation processes. Despite significant progress, grand challenges are remained to effectively extract and transmit high-quality textures from high-degraded low-quality sequences, such as blur, additive noises, and compression artifacts. In this work, a novel Frequency-Transformer (FTVSR) is proposed for handling low-quality videos that carry out self-attention in a combined space-time-frequency domain. First, video frames are split into patches and each patch is transformed into spectral maps in which each channel represents a frequency band. It permits a fine-grained self-attention on each frequency band, so that real visual texture can be distinguished from artifacts. Second, a novel dual frequency attention (DFA) mechanism is proposed to capture the global frequency relations and local frequency relations, which can handle different complicated degradation processes in real-world scenarios. Third, we explore different self-attention schemes for video processing in the frequency domain and discover that a ``divided attention'' which conducts a joint space-frequency attention before applying temporal-frequency attention, leads to the best video enhancement quality. Extensive experiments on three widely-used VSR datasets show that FTVSR outperforms state-of-the-art methods on different low-quality videos with clear visual margins. Code and pre-trained models are available at https://github.com/researchmm/FTVSR.
translated by 谷歌翻译
Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In this paper, we examine the role of self-attention in learning robust representations. Our study is motivated by the intriguing properties of the emerging visual grouping in Vision Transformers, which indicates that self-attention may promote robustness through improved mid-level representations. We further propose a family of fully attentional networks (FANs) that strengthen this capability by incorporating an attentional channel processing design. We validate the design comprehensively on various hierarchical backbones. Our model achieves a state-of-the-art 87.1% accuracy and 35.8% mCE on ImageNet-1k and ImageNet-C with 76.8M parameters. We also demonstrate state-of-the-art accuracy and robustness in two downstream tasks: semantic segmentation and object detection. Code is available at: https://github.com/NVlabs/FAN.
translated by 谷歌翻译
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are mismatched, accuracy can plummet. Currently there are few techniques that improve robustness to unforeseen data shifts encountered during deployment. In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. We propose AUGMIX, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. AUGMIX significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.
translated by 谷歌翻译
现代神经网络Excel在图像分类中,但它们仍然容易受到常见图像损坏,如模糊,斑点噪音或雾。最近的方法关注这个问题,例如Augmix和Deepaulment,引入了在预期运行的防御,以期望图像损坏分布。相比之下,$ \ ell_p $ -norm界限扰动的文献侧重于针对最坏情况损坏的防御。在这项工作中,我们通过提出防范内人来调和两种方法,这是一种优化图像到图像模型的参数来产生对外损坏的增强图像的技术。我们理论上激发了我们的方法,并为其理想化版本的一致性以及大纲领提供了足够的条件。我们的分类机器在预期对CiFar-10-C进行的常见图像腐败基准上提高了最先进的,并改善了CIFAR-10和ImageNet上的$ \ ell_p $ -norm有界扰动的最坏情况性能。
translated by 谷歌翻译
最近,数据增强已成为视觉识别任务的现代培训食谱的重要组成部分。但是,尽管有效性,但很少探索视频识别的数据增强。很少有用于视频识别的现有增强食谱通过将相同的操作应用于整个视频框架来天真地扩展图像增强方法。我们的主要思想是,每帧的增强操作的大小都需要随着时间的推移而更改,以捕获现实世界视频的时间变化。在训练过程中,应使用更少的额外超参数来尽可能多地生成这些变化。通过这种动机,我们提出了一个简单而有效的视频数据增强框架Dynaaugment。每个帧上增强操作的大小通过有效的机制,傅立叶采样更改,该采样将各种,平滑和现实的时间变化参数化。 Dynaaugment还包括一个适用于视频的扩展搜索空间,用于自动数据增强方法。 Dynaaugment在实验上表明,从各种视频模型的静态增强中可以改善其他性能室。具体而言,我们在各种视频数据集和任务上显示了Dynaaugment的有效性:大规模视频识别(Kinetics-400和Sothings-Something-v2),小规模视频识别(UCF-101和HMDB-51),精细元素视频识别(潜水48和FINEGYM),早餐的视频动作细分,Thumos'14上的视频动作本地化以及MOT17DET上的视频对象检测。 Dynaaugment还使视频模型能够学习更广泛的表示形式,以改善损坏视频的模型鲁棒性。
translated by 谷歌翻译
用于计算机视觉任务的深度神经网络在越来越安全 - 严重和社会影响的应用中部署,激励需要在各种,天然存在的成像条件下关闭模型性能的差距。在包括对抗机器学习的多种上下文中尤为色难地使用的鲁棒性,然后指在自然诱导的图像损坏或改变下保持模型性能。我们进行系统审查,以识别,分析和总结当前定义以及对计算机愿景深度学习中的非对抗鲁棒性的进展。我们发现,该研究领域已经收到了相对于对抗机器学习的不成比例地注意力,但存在显着的稳健性差距,这些差距通常表现在性能下降中与对抗条件相似。为了在上下文中提供更透明的稳健性定义,我们引入了数据生成过程的结构因果模型,并将非对抗性鲁棒性解释为模型在损坏的图像上的行为,其对应于来自未纳入数据分布的低概率样本。然后,我们确定提高神经网络鲁棒性的关键架构,数据增强和优化策略。这种稳健性的这种因果观察表明,目前文献中的常见做法,关于鲁棒性策略和评估,对应于因果概念,例如软干预导致成像条件的决定性分布。通过我们的调查结果和分析,我们提供了对未来研究如何可能介意这种明显和显着的非对抗的鲁棒性差距的观点。
translated by 谷歌翻译