深度神经网络的可解释性已成为勘探的主要领域。虽然这些网络在许多任务中实现了最先进的准确性,但极难解释和解释他们的决定。在这项工作中,我们分析了深度卷积网络的最终和倒数第二层,并提供了一种有效的方法,用于识别贡献对网络决定的最大贡献的特征子集。我们证明,与最终层的尺寸相比,每个类的这种特征的数量远低得多,因此深CNN的决定表面位于低维歧管上,并且与网络深度成比例。我们的方法允许将最终层分解为单独的子空间,该子空间远远不可解释,并且与完整网络的最终层相比具有较低的计算成本。
translated by 谷歌翻译
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.
translated by 谷歌翻译
Spatial understanding is a fundamental aspect of computer vision and integral for human-level reasoning about images, making it an important component for grounded language understanding. While recent large-scale text-to-image synthesis (T2I) models have shown unprecedented improvements in photorealism, it is unclear whether they have reliable spatial understanding capabilities. We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the image. To benchmark existing models, we introduce a large-scale challenge dataset SR2D that contains sentences describing two objects and the spatial relationship between them. We construct and harness an automated evaluation pipeline that employs computer vision to recognize objects and their spatial relationships, and we employ it in a large-scale evaluation of T2I models. Our experiments reveal a surprising finding that, although recent state-of-the-art T2I models exhibit high image quality, they are severely limited in their ability to generate multiple objects or the specified spatial relations such as left/right/above/below. Our analyses demonstrate several biases and artifacts of T2I models such as the difficulty with generating multiple objects, a bias towards generating the first object mentioned, spatially inconsistent outputs for equivalent relationships, and a correlation between object co-occurrence and spatial understanding capabilities. We conduct a human study that shows the alignment between VISOR and human judgment about spatial understanding. We offer the SR2D dataset and the VISOR metric to the community in support of T2I spatial reasoning research.
translated by 谷歌翻译
We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste compositional dataset augmentation approach for weakly-supervised instance segmentation using only image-level supervision. The proposed method consists of three main components. The first component generates high-quality foreground object masks. To this end, an EM-like approach is proposed that iteratively refines an initial set of object mask proposals generated by a generic region proposal method. Next, in the second component, high-quality context-aware background images are generated using a text-to-image compositional synthesis method like DALL-E. Finally, the third component creates a large-scale pseudo-labeled instance segmentation training dataset by compositing the foreground object masks onto the original and generated background images. The proposed approach achieves state-of-the-art weakly-supervised instance segmentation results on both the PASCAL VOC 2012 and MS COCO datasets by using only image-level, weak label information. In particular, it outperforms the best baseline by +7.4 and +2.8 mAP0.50 on PASCAL and COCO, respectively. Further, the method provides a new solution to the long-tail weakly-supervised instance segmentation problem (when many classes may only have few training samples), by selectively augmenting under-represented classes.
translated by 谷歌翻译
近年来,《虚假新闻》的数据科学研究已经筹集了很大的势头,可以说是大型公共基准数据集的出现。尽管在媒体研究中,性别偏见是一个遍布新闻媒体的问题,但对性别偏见与虚假新闻之间的关系几乎没有探索。在这项工作中,我们提供了对假新闻的性别偏见的首次实证分析,利用公共基准数据集利用简单且基于透明的词典的方法。我们的分析确定了在三个方面的假新闻中,性别偏见的普遍性增加,即丰富,情感和近端单词。我们分析中的见解提供了一个强有力的论点,即性别偏见需要成为对假新闻研究的重要考虑因素。
translated by 谷歌翻译
我们在室外环境中自动驾驶的背景下研究了视觉和语言导航(VLN)问题。我们通过明确接地与Textual命令相对应的可通道区域来解决问题。在每个时间戳,该模型预测与中间或最终可通道区域相对应的分割掩码。我们的工作与VLN中的现有工作形成鲜明对比,VLN的现有工作将该任务置于节点选择问题,并且给定与环境相对应的离散连接图。我们不假定这种离散的地图的可用性。我们的工作朝着动作领域的连续性发展,通过视觉反馈提供了解释性,并允许在需要更精细的操作的命令上进行VLN,例如“两辆汽车之间的停车”。此外,我们提出了一种新型的元数据carla-nav,以允许有效的训练和验证。该数据集包括预录制的培训序列以及用于验证和测试的实时环境。我们提供广泛的定性和定量经验结果,以验证所提出的方法的功效。
translated by 谷歌翻译
模拟逼真的传感器是自主系统数据生成的挑战,通常涉及精心手工的传感器设计,场景属性和物理建模。为了减轻这一点,我们引入了一条管道,用于对逼真的激光雷达传感器进行数据驱动的模拟。我们提出了一个模型,该模型可以在RGB图像和相应的LIDAR功能(例如Raydrop或每点强度)之间直接从真实数据集中进行映射。我们表明,我们的模型可以学会编码逼真的效果,例如透明表面上的掉落点或反射材料上的高强度回报。当应用于现成的模拟器软件提供的天真播放点云时,我们的模型通过根据场景的外观预测强度和删除点来增强数据,以匹配真实的激光雷达传感器。我们使用我们的技术来学习两个不同的LIDAR传感器的模型,并使用它们相应地改善模拟的LiDAR数据。通过车辆细分的示例任务,我们表明通过我们的技术增强模拟点云可以改善下游任务性能。
translated by 谷歌翻译
最近的波能转化器(WEC)配备了多个腿和发电机,以最大程度地发电。传统控制器显示出捕获复杂波形模式的局限性,并且控制器必须有效地最大化能量捕获。本文介绍了多项式增强学习控制器(MARL),该控制器的表现优于传统使用的弹簧减震器控制器。我们的最初研究表明,问题的复杂性质使训练很难融合。因此,我们提出了一种新颖的跳过训练方法,使MARL训练能够克服性能饱和,并与默认的MARL训练相比,融合到最佳控制器,从而增强发电。我们还提出了另一种新型的混合训练初始化(STHTI)方法,其中最初可以单独针对基线弹簧减震器(SD)控制器对MARL控制器的个别代理进行训练,然后在将来一次或将来培训一个代理商或全部培训加速收敛。我们使用异步参与者-Critic(A3C)算法在基线弹簧减震器控制器上实现了基线弹簧减震器控制器的能源效率的两位数提高。
translated by 谷歌翻译
本文提出了一种新型的非侵入系统故障预测技术,使用来自开发人员的可用信息,以及来自原始日志中的最小信息(而不是挖掘整个日志),但与数据所有者完全保持数据。基于神经网络的多级分类器是为故障预测而开发的,使用人为生成的匿名数据集,应用技术组合,即遗传算法(步骤),模式重复等,以训练和测试网络。提出的机制完全将用于培训过程的数据集与保留私有数据的数据集分解。此外,多标准决策(MCDM)方案用于优先考虑满足业务需求的失败。结果显示在不同参数配置下的故障预测准确性。在更广泛的上下文上,可以使用提出的机制具有人工生成的数据集执行任何分类问题,而无需查看实际数据,只要输入功能可以转换为二进制值(例如,来自私有二进制分类器的输出)并可以提供分类 - 服务。
translated by 谷歌翻译
在线广告最近已发展成为一个竞争激烈且复杂的数十亿美元行业,广告商在大型和高频上竞标广告插槽。这导致对有效的“自动招标”算法的需求日益增长,这些算法确定了传入查询的投标,以最大程度地提高广告商的目标,但受其指定的约束。这项工作探讨了在日益流行的约束下,为单个价值最大化广告商提供有效的在线算法:返回式增长(ROS)。相对于最佳算法,我们对遗憾进行了量化效率,该算法知道所有查询所有查询都是先验的。我们贡献了一种简单的在线算法,该算法在期望中实现了近乎最佳的遗憾,同时始终尊重指定的ROS约束,当查询的输入顺序为i.i.d.来自某些分布的样本。我们还将结果与Balseiro,Lu和Mirrokni [BLM20]的先前工作相结合,以实现近乎最佳的遗憾,同时尊重ROS和固定的预算限制。我们的算法遵循原始的二重式框架,并使用在线镜像下降(OMD)进行双重更新。但是,我们需要使用非典型的OMD设置,因此需要使用OMD的经典低rebret保证,该保证是用于在线学习中的对抗性环境的,不再存在。尽管如此,在我们的情况下,在更普遍的情况下,在算法设计中应用低纤维动力学的情况下,OMD遇到的梯度可能远非对抗性,但受我们的算法选择的影响。我们利用这一关键见解来显示我们的OMD设置在我们的算法领域中造成了低落的遗憾。
translated by 谷歌翻译