With the deterioration of climate, the phenomenon of rain-induced flooding has become frequent. To mitigate its impact, recent works adopt convolutional neural networks or other variants to predict the floods. However, these methods directly force the model to reconstruct the raw pixels of water depth maps through constraining pixel-level differences, ignoring the high-level information contained in terrain features and rainfall patterns. To address this, we present a novel GAN-based framework for precise flood prediction, which incorporates hierarchical terrain spatial attention to help the model focus on spatially-salient areas of terrain features and constructs multi-scale rainfall embedding to extensively integrate rainfall pattern information into generation. To better adapt the model in various rainfall conditions, we leverage a rainfall regression loss for both the generator and the discriminator as additional supervision. Extensive evaluations on real catchment datasets demonstrate the superior performance of our method, which greatly surpasses the previous arts under different rainfall conditions.
translated by 谷歌翻译
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoise are typical strategies for defending adversarial perturbations, including adversarial training and statistical filtering, respectively. However, they either induce massive computational overhead or rely heavily upon specified noise priors, limiting generalized robustness against attacks of all kinds. This paper introduces a new defense mechanism based on denoising diffusion models that can adaptively remove diverse noises with a tailored intensity estimator. Specifically, we first estimate adversarial distortions by calculating the distance of the points to their neighborhood best-fit plane. Depending on the distortion degree, we choose specific diffusion time steps for the input point cloud and perform the forward diffusion to disrupt potential adversarial shifts. Then we conduct the reverse denoising process to restore the disrupted point cloud back to a clean distribution. This approach enables effective defense against adaptive attacks with varying noise budgets, achieving accentuated robustness of existing 3D deep recognition models.
translated by 谷歌翻译
尽管在各种应用中取得了突出的性能,但点云识别模型经常遭受自然腐败和对抗性扰动的困扰。在本文中,我们深入研究了点云识别模型的一般鲁棒性,并提出了点云对比对抗训练(PointCat)。 PointCat的主要直觉是鼓励目标识别模型缩小清洁点云和损坏点云之间的决策差距。具体而言,我们利用有监督的对比损失来促进识别模型提取的超晶体特征的对齐和均匀性,并设计一对带有动态原型指南的集中式损失,以避免这些特征与其属于其属于其归属类别群的偏离。为了提供更具挑战性的损坏点云,我们对噪声生成器以及从头开始的识别模型进行了对手训练,而不是将基于梯度的攻击用作内部循环,例如以前的对手训练方法。全面的实验表明,在包括各种损坏的情况下,所提出的PointCat优于基线方法,并显着提高不同点云识别模型的稳健性,包括各向同性点噪声,LIDAR模拟的噪声,随机点掉落和对抗性扰动。
translated by 谷歌翻译
受益于生成对抗性网络(GAN)的发展,面部操纵最近在学术界和工业中取得了重大进展。它激发了越来越多的娱乐应用,但也遭到对个人隐私甚至政治安全的严重威胁。为了减轻这种风险,已经提出了许多对策。然而,大多数方法以被动方式设计,这是为了检测它们在广泛传播之后是否篡改了面部图像或视频。这些基于检测的方法具有致命的限制,即它们仅适用于前后的取证,但不能阻止对恶意行为的发挥作用。为了解决限制,在本文中,我们提出了一种新颖的倡议防御框架,以降低恶意用户控制的面部操纵模型的性能。基本思想是在操纵之前将难以察觉的毒液纳入目标面部数据。为此,我们首先使用替代模型模仿目标操纵模型,然后设计毒药扰动发生器以获得所需的毒液。交替的培训策略进一步利用以培训代理模型和扰动发生器。两个典型的面部操纵任务:面部属性编辑和面部重新制定,在我们的倡议防御框架中考虑。广泛的实验证明了我们在不同环境中框架的有效性和稳健性。最后,我们希望这项工作能够在针对更多对抗方案的主动对策上阐明一些灯。
translated by 谷歌翻译
最近的研究表明,深层神经网络容易受到不同类型的攻击,例如对抗性攻击,数据中毒攻击和后门攻击。其中,后门攻击是最狡猾的攻击,几乎可以在深度学习管道的每个阶段发生。因此,后门攻击吸引了学术界和行业的许多兴趣。但是,大多数现有的后门攻击方法对于某些轻松的预处理(例如常见数据转换)都是可见的或脆弱的。为了解决这些限制,我们提出了一种强大而无形的后门攻击,称为“毒药”。具体而言,我们首先利用图像结构作为目标中毒区域,并用毒药(信息)填充它们以生成触发图案。由于图像结构可以在数据转换期间保持其语义含义,因此这种触发模式对数据转换本质上是强大的。然后,我们利用深度注射网络将这种触发模式嵌入封面图像中,以达到隐身性。与现有流行的后门攻击方法相比,毒药的墨水在隐形和健壮性方面都优于表现。通过广泛的实验,我们证明了毒药不仅是不同数据集和网络体系结构的一般性,而且对于不同的攻击场景也很灵活。此外,它对许多最先进的防御技术也具有非常强烈的抵抗力。
translated by 谷歌翻译
作为最成功的AI驱动应用程序之一,推荐系统的目的是通过在我们生活的许多方面提供个性化建议,以有效而有效的方式帮助人们做出适当的决定,尤其是针对各种面向人类的在线服务,例如E-商务平台和社交媒体网站。在过去的几十年中,推荐系统的快速发展通过创造经济价值,节省时间和精力以及促进社会利益,从而使人类受益匪浅。但是,最近的研究发现,数据驱动的推荐系统可能会对用户和社会构成严重威胁,例如传播虚假新闻以操纵社交媒体网站中的公众舆论,扩大不公平为代表性不足的团体或在工作匹配服务中的个人,或从建议结果中推断隐私信息。因此,系统的可信赖性一直吸引着各个方面的关注,以减轻推荐系统引起的负面影响,以增强公众对推荐系统技术的信任。在这项调查中,我们提供了可信赖的推荐系统(TREC)的全面概述,特别关注六个最重要的方面;即安全与鲁棒性,非歧视与公平,解释性,隐私,环境福祉以及问责制和可审计性。对于每个方面,我们总结了最近的相关技术,并讨论了潜在的研究方向,以帮助未来实现值得信赖的推荐系统。
translated by 谷歌翻译
可靠,高分辨率气候和天气数据的可用性对于为气候适应和缓解的长期决策提供了重要的意见,并指导对极端事件的快速响应。预测模型受到计算成本的限制,因此通常以粗空间分辨率预测数量。统计降尺度可以提供高采样低分辨率数据的有效方法。在这个领域,经常使用计算机视觉中超分辨率域中的方法成功地应用了深度学习。尽管经常取得令人信服的结果,但这种模型在预测物理变量时通常会违反保护法。为了节省重要的物理量,我们开发的方法可以通过深层缩减模型来确保物理约束,同时还根据传统指标提高其性能。我们介绍了约束网络的两种方法:添加到神经网络末尾的重新归一化层,并连续的方法随着增加的采样因子的增加而扩展。我们使用ERE5重新分析数据显示了我们在不同流行架构和更高采样因子上的方法的适用性。
translated by 谷歌翻译
探索和建立具有电生理特征和高计算效率的人工神经网络是计算机视觉领域的流行主题。受主要视觉皮层的工作机制的启发,脉冲耦合神经网络(PCNN)可以表现出同步振荡,难治期和指数衰减的特征。然而,电生理证据表明,当外部周期性信号刺激时,神经元表现出高度复杂的非线性动力学。这种混乱现象,也称为“蝴蝶效应”,无法用所有PCNN模型来解释。在这项工作中,我们分析了防止PCNN模型模仿真实主要视觉皮层的主要障碍。我们认为神经元激发是一个随机过程。然后,我们提出了一个新型的神经网络,称为连续耦合神经网络(CCNN)。理论分析表明,CCNN的动态行为与PCNN不同。数值结果表明,CCNN模型在直流刺激下表现出周期性的行为,并在交流刺激下表现出混沌行为,这与实际神经元的结果一致。此外,分析了CCNN模型的图像和视频处理机制。图像分割的实验结果表明,CCNN模型的性能要比视觉皮层神经网络模型的最先进。
translated by 谷歌翻译
This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.
translated by 谷歌翻译
Supervised Question Answering systems (QA systems) rely on domain-specific human-labeled data for training. Unsupervised QA systems generate their own question-answer training pairs, typically using secondary knowledge sources to achieve this outcome. Our approach (called PIE-QG) uses Open Information Extraction (OpenIE) to generate synthetic training questions from paraphrased passages and uses the question-answer pairs as training data for a language model for a state-of-the-art QA system based on BERT. Triples in the form of <subject, predicate, object> are extracted from each passage, and questions are formed with subjects (or objects) and predicates while objects (or subjects) are considered as answers. Experimenting on five extractive QA datasets demonstrates that our technique achieves on-par performance with existing state-of-the-art QA systems with the benefit of being trained on an order of magnitude fewer documents and without any recourse to external reference data sources.
translated by 谷歌翻译