Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $\rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $\rho$-Vision that eliminates the ISP are the potential reductions in computations and processing times.
translated by 谷歌翻译
对图像分类器的最新基于模型的攻击压倒性地集中在单对象(即单个主体对象)图像上。与此类设置不同,我们解决了一个更实用的问题,即使用多对象(即多个主导对象)图像生成对抗性扰动,因为它们代表了大多数真实世界场景。我们的目标是设计一种攻击策略,该策略可以通过利用此类图像中固有的本地贴片差异来从此类自然场景中学习(例如,对象上的局部贴片在“人”上的局部贴片与在交通场景中的对象`自行车'之间的差异)。我们的关键想法是:为了误解对抗性的多对象图像,图像中的每个本地贴片都会使受害者分类器感到困惑。基于此,我们提出了一种新颖的生成攻击(称为局部斑块差异或LPD攻击),其中新颖的对比损失函数使用上述多对象场景特征空间的局部差异来优化扰动生成器。通过各种受害者卷积神经网络的各种实验,我们表明我们的方法在不同的白色盒子和黑色盒子设置下进行评估时,我们的方法优于基线生成攻击,具有高度可转移的扰动。
translated by 谷歌翻译
制作对抗性攻击的大多数方法都集中在具有单个主体对象的场景上(例如,来自Imagenet的图像)。另一方面,自然场景包括多个在语义上相关的主要对象。因此,探索设计攻击策略至关重要,这些攻击策略超出了在单对象场景上学习或攻击单对象受害者分类器。由于其固有的属性将扰动向未知模型的强大可传递性强,因此本文介绍了使用生成模型对多对象场景的对抗性攻击的第一种方法。为了代表输入场景中不同对象之间的关系,我们利用开源的预训练的视觉语言模型剪辑(对比语言图像 - 预训练),并动机利用语言中的编码语义来利用编码的语义空间与视觉空间一起。我们称这种攻击方法生成对抗性多对象场景攻击(GAMA)。 GAMA展示了剪辑模型作为攻击者的工具的实用性,以训练可强大的扰动发电机为多对象场景。使用联合图像文本功能来训练发电机,我们表明GAMA可以在各种攻击环境中制作有效的可转移扰动,以欺骗受害者分类器。例如,GAMA触发的错误分类比在黑框设置中的最新生成方法高出约16%,在黑框设置中,分类器体系结构和攻击者的数据分布都与受害者不同。我们的代码将很快公开提供。
translated by 谷歌翻译
Blackbox对抗攻击可以分为基于转移和基于查询的攻击。转移方法不需要受害模型的任何反馈,而是与基于查询的方法相比提供较低的成功率。查询攻击通常需要大量的成功查询。为了达到两种方法,最近的努力都试图将它们结合起来,但仍需要数百个查询才能获得高成功率(尤其是针对目标攻击)。在本文中,我们提出了一种通过替代集合搜索(基地)进行黑框攻击的新方法,该方法可以使用极少量的查询来生成非常成功的黑盒攻击。我们首先定义了扰动机,该机器通过在固定的替代模型上最小化加权损失函数来生成扰动的图像。为了为给定受害者模型生成攻击,我们使用扰动机产生的查询搜索损失函数中的权重。由于搜索空间的尺寸很小(与替代模型的数量相同),因此搜索需要少量查询。我们证明,与经过Imagenet训练的不同图像分类器(包括VGG-19,Densenet-121和Resnext-50)上的最新图像分类器相比,我们提出的方法的查询至少少了30倍,其查询至少少了30倍。特别是,我们的方法平均需要每张图像3个查询,以实现目标攻击的成功率超过90%,而对于非目标攻击的成功率超过99%,每个图像的1-2查询。我们的方法对Google Cloud Vision API也有效,并获得了91%的非目标攻击成功率,每张图像2.9查询。我们还表明,我们提出的方法生成的扰动是高度转移的,可以用于硬标签黑盒攻击。
translated by 谷歌翻译
高速,高分辨率的立体视频(H2-STEREO)视频使我们能够在细粒度上感知动态3D内容。然而,对商品摄像机的收购H2-STEREO视频仍然具有挑战性。现有的空间超分辨率或时间框架插值方法分别提供了缺乏时间或空间细节的折衷解决方案。为了减轻这个问题,我们提出了一个双摄像头系统,其中一台相机捕获具有丰富空间细节的高空间分辨率低框架速率(HSR-LFR)视频,而另一个摄像头则捕获了低空间分辨率的高架框架-Rate(LSR-HFR)视频带有光滑的时间细节。然后,我们设计了一个学习的信息融合网络(LIFNET),该网络利用跨摄像机冗余,以增强两种相机视图,从而有效地重建H2-STEREO视频。即使在大型差异场景中,我们也利用一个差异网络将时空信息传输到视图上,基于该视图,我们建议使用差异引导的LSR-HFR视图基于差异引导的流量扭曲,并针对HSR-LFR视图进行互补的扭曲。提出了特征域中的多尺度融合方法,以最大程度地减少HSR-LFR视图中闭塞引起的翘曲幽灵和孔。 LIFNET使用YouTube收集的高质量立体视频数据集以端到端的方式进行训练。广泛的实验表明,对于合成数据和摄像头捕获的真实数据,我们的模型均优于现有的最新方法。消融研究探讨了各个方面,包括时空分辨率,摄像头基线,摄像头解理,长/短曝光和应用程序,以充分了解其对潜在应用的能力。
translated by 谷歌翻译
增量任务学习(ITL)是一个持续学习的类别,试图培训单个网络以进行多个任务(一个接一个),其中每个任务的培训数据仅在培训该任务期间可用。当神经网络接受较新的任务培训时,往往会忘记旧任务。该特性通常被称为灾难性遗忘。为了解决此问题,ITL方法使用情节内存,参数正则化,掩盖和修剪或可扩展的网络结构。在本文中,我们提出了一个基于低级别分解的新的增量任务学习框架。特别是,我们表示每一层的网络权重作为几个等级1矩阵的线性组合。为了更新新任务的网络,我们学习一个排名1(或低级别)矩阵,并将其添加到每一层的权重。我们还引入了一个其他选择器向量,该向量将不同的权重分配给对先前任务的低级矩阵。我们表明,就准确性和遗忘而言,我们的方法的表现比当前的最新方法更好。与基于情节的内存和基于面具的方法相比,我们的方法还提供了更好的内存效率。我们的代码将在https://github.com/csiplab/task-increment-rank-update.git上找到。
translated by 谷歌翻译
In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting. While there is a rich set of techniques for CL, relatively little understanding exists on how representations built by previous tasks benefit new tasks that are added to the network. To address this, we study the problem of continual representation learning (CRL) where we learn an evolving representation as new tasks arrive. Focusing on zero-forgetting methods where tasks are embedded in subnetworks (e.g., PackNet), we first provide experiments demonstrating CRL can significantly boost sample efficiency when learning new tasks. To explain this, we establish theoretical guarantees for CRL by providing sample complexity and generalization error bounds for new tasks by formalizing the statistical benefits of previously-learned representations. Our analysis and experiments also highlight the importance of the order in which we learn the tasks. Specifically, we show that CL benefits if the initial tasks have large sample size and high "representation diversity". Diversity ensures that adding new tasks incurs small representation mismatch and can be learned with few samples while training only few additional nonzero weights. Finally, we ask whether one can ensure each task subnetwork to be efficient during inference time while retaining the benefits of representation learning. To this end, we propose an inference-efficient variation of PackNet called Efficient Sparse PackNet (ESPN) which employs joint channel & weight pruning. ESPN embeds tasks in channel-sparse subnets requiring up to 80% less FLOPs to compute while approximately retaining accuracy and is very competitive with a variety of baselines. In summary, this work takes a step towards data and compute-efficient CL with a representation learning perspective. GitHub page: https://github.com/ucr-optml/CtRL
translated by 谷歌翻译
近年来,图像分类器的BlackBox传输攻击已被广泛研究。相比之下,对对象探测器的转移攻击取得了很小的进展。对象探测器采用图像的整体视图,并检测一个对象(或缺乏)通常取决于场景中的其他对象。这使得这种探测器本质上的上下文感知和对抗的攻击比目标图像分类器更具挑战性。在本文中,我们提出了一种新的方法来为对象检测器生成上下文感知攻击。我们表明,通过使用对象及其相关位置的共同发生和尺寸作为上下文信息,我们可以成功地生成目标的错误分类攻击,该攻击比最先进的Blackbox对象探测器上实现更高的转移成功率。我们在帕斯卡VOC和MS Coco Datasets的各种对象探测器上测试我们的方法,与其他最先进的方法相比,性能提高了高达20美元的百分点。
translated by 谷歌翻译
基于掩模的无透镜相机可以是平坦的,薄型和轻质的,这使得它们适用于具有大表面积和任意形状的计算成像系统的新颖设计。尽管最近在无晶体相机的进展中,由于底层测量系统的不良状态,从透镜相机恢复的图像质量往往差。在本文中,我们建议使用编码照明来提高用无透镜相机重建的图像的质量。在我们的成像模型中,场景/物体被多种编码照明模式照亮,因为无透镜摄像机记录传感器测量。我们设计并测试了许多照明模式,并观察到变速点(和相关的正交)模式提供了最佳的整体性能。我们提出了一种快速和低复杂性的恢复算法,可利用我们系统中的可分离性和块对角线结构。我们提出了仿真结果和硬件实验结果,以证明我们的提出方法可以显着提高重建质量。
translated by 谷歌翻译
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译