由于新型神经网络体系结构的设计和大规模数据集的可用性，对象检测方法在过去几年中取得了令人印象深刻的改进。但是，当前的方法有一个重要的限制：他们只能检测到在训练时间内观察到的类，这只是检测器在现实世界中可能遇到的所有类的子集。此外，在训练时间通常不考虑未知类别的存在，从而导致方法甚至无法检测到图像中存在未知对象。在这项工作中，我们解决了检测未知对象的问题，称为开放集对象检测。我们提出了一种名为Unkad的新颖培训策略，能够预测未知的对象，而无需对其进行任何注释，利用训练图像背景中已经存在的非注释对象。特别是，unkad首先利用更快的R-CNN的四步训练策略，识别和伪标签未知对象，然后使用伪通量来训练其他未知类。尽管UNKAD可以直接检测未知的对象，但我们将其与以前未知的检测技术相结合，表明它不成本就可以提高其性能。

语义细分对于使自动驾驶车辆自动驾驶至关重要，从而使他们能够通过将单个像素分配给已知类别来理解周围环境。但是，它可以根据用户汽车收集的明智数据运行；因此，保护​​客户的隐私成为主要问题。出于类似的原因，最近将联邦学习作为一种新的机器学习范式引入，旨在学习全球模型，同时保留隐私并利用数百万个远程设备的数据。尽管在这个主题上进行了几项努力，但尚未明确解决语义细分中联合学习在迄今为止驾驶的挑战。为了填补这一空白，我们提出了FedDrive，这是一个由三个设置和两个数据集组成的新基准，其中包含了统计异质性和域概括的现实世界挑战。我们通过深入的分析基于联合学习文献的最新算法，将它们与样式转移方法相结合以提高其概括能力。我们证明，正确处理标准化统计数据对于应对上述挑战至关重要。此外，在处理重大外观变化时，样式转移会提高性能。官方网站：https：//feddrive.github.io。

增量学习代表了空中图像处理中的一个关键任务，特别是给出了大规模注释数据集的有限可用性。关于当前深度神经结构的一个主要问题被称为灾难性遗忘，即无能忠实地维护过去的知识，一旦提供了一种新的数据来刷新。多年来，已经提出了几种技术来减轻图像分类和对象检测的这个问题。但是，只有最近，焦点已经转移到更复杂的下游任务，例如实例或语义细分。从增量级学习的语义分割任务开始，我们的目标是将此策略调整到空中域，利用与自然图像不同的特殊功能，即定向。除了标准知识蒸馏方法之外，我们还提出了一种对比规范化，其中任何给定的输入与其增强版本（即翻转和旋转）进行了比较，以便最小化两个输入产生的分段特征之间的差异。我们展示了我们解决Potsdam数据集的效果，表现出每次测试中的增量基线。可用的代码：https：//github.com/edornd/contrastive-distillation。

虽然现有的语义分割方法实现令人印象深刻的结果，但它们仍然努力将其模型逐步更新，因为新类别被发现。此外，逐个像素注释昂贵且耗时。本文提出了一种新颖的对语义分割学习弱增量学习的框架，旨在学习从廉价和大部分可用的图像级标签进行新课程。与现有的方法相反，需要从下线生成伪标签，我们使用辅助分类器，用图像级标签培训并由分段模型规范化，在线获取伪监督并逐步更新模型。我们通过使用由辅助分类器生成的软标签来应对过程中的内在噪声。我们展示了我们对Pascal VOC和Coco数据集的方法的有效性，表现出离线弱监督方法，并获得了具有全面监督的增量学习方法的结果。

Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simple tactics to subvert ML-driven systems, and as a result security practitioners have not prioritized adversarial ML defenses. Motivated by the apparent gap between researchers and practitioners, this position paper aims to bridge the two domains. We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next we analyze all adversarial ML papers recently published in top security conferences, highlighting positive trends and blind spots. Finally, we state positions on precise and cost-driven threat modeling, collaboration between industry and academia, and reproducible research. We believe that our positions, if adopted, will increase the real-world impact of future endeavours in adversarial ML, bringing both researchers and practitioners closer to their shared goal of improving the security of ML systems.

When simulating soft robots, both their morphology and their controllers play important roles in task performance. This paper introduces a new method to co-evolve these two components in the same process. We do that by using the hyperNEAT algorithm to generate two separate neural networks in one pass, one responsible for the design of the robot body structure and the other for the control of the robot. The key difference between our method and most existing approaches is that it does not treat the development of the morphology and the controller as separate processes. Similar to nature, our method derives both the "brain" and the "body" of an agent from a single genome and develops them together. While our approach is more realistic and doesn't require an arbitrary separation of processes during evolution, it also makes the problem more complex because the search space for this single genome becomes larger and any mutation to the genome affects "brain" and the "body" at the same time. Additionally, we present a new speciation function that takes into consideration both the genotypic distance, as is the standard for NEAT, and the similarity between robot bodies. By using this function, agents with very different bodies are more likely to be in different species, this allows robots with different morphologies to have more specialized controllers since they won't crossover with other robots that are too different from them. We evaluate the presented methods on four tasks and observe that even if the search space was larger, having a single genome makes the evolution process converge faster when compared to having separated genomes for body and control. The agents in our population also show morphologies with a high degree of regularity and controllers capable of coordinating the voxels to produce the necessary movements.

Filming sport videos from an aerial view has always been a hard and an expensive task to achieve, especially in sports that require a wide open area for its normal development or the ones that put in danger human safety. Recently, a new solution arose for aerial filming based on the use of Unmanned Aerial Vehicles (UAVs), which is substantially cheaper than traditional aerial filming solutions that require conventional aircrafts like helicopters or complex structures for wide mobility. In this paper, we describe the design process followed for building a customized UAV suitable for sports aerial filming. The process includes the requirements definition, technical sizing and selection of mechanical, hardware and software technologies, as well as the whole integration and operation settings. One of the goals is to develop technologies allowing to build low cost UAVs and to manage them for a wide range of usage scenarios while achieving high levels of flexibility and automation. This work also shows some technical issues found during the development of the UAV as well as the solutions implemented.

We describe a Physics-Informed Neural Network (PINN) that simulates the flow induced by the astronomical tide in a synthetic port channel, with dimensions based on the Santos - S\~ao Vicente - Bertioga Estuarine System. PINN models aim to combine the knowledge of physical systems and data-driven machine learning models. This is done by training a neural network to minimize the residuals of the governing equations in sample points. In this work, our flow is governed by the Navier-Stokes equations with some approximations. There are two main novelties in this paper. First, we design our model to assume that the flow is periodic in time, which is not feasible in conventional simulation methods. Second, we evaluate the benefit of resampling the function evaluation points during training, which has a near zero computational cost and has been verified to improve the final model, especially for small batch sizes. Finally, we discuss some limitations of the approximations used in the Navier-Stokes equations regarding the modeling of turbulence and how it interacts with PINNs.

How would you fairly evaluate two multi-object tracking algorithms (i.e. trackers), each one employing a different object detector? Detectors keep improving, thus trackers can make less effort to estimate object states over time. Is it then fair to compare a new tracker employing a new detector with another tracker using an old detector? In this paper, we propose a novel performance measure, named Tracking Effort Measure (TEM), to evaluate trackers that use different detectors. TEM estimates the improvement that the tracker does with respect to its input data (i.e. detections) at frame level (intra-frame complexity) and sequence level (inter-frame complexity). We evaluate TEM over well-known datasets, four trackers and eight detection sets. Results show that, unlike conventional tracking evaluation measures, TEM can quantify the effort done by the tracker with a reduced correlation on the input detections. Its implementation is publicly available online at https://github.com/vpulab/MOT-evaluation.

Reinforcement learning allows machines to learn from their own experience. Nowadays, it is used in safety-critical applications, such as autonomous driving, despite being vulnerable to attacks carefully crafted to either prevent that the reinforcement learning algorithm learns an effective and reliable policy, or to induce the trained agent to make a wrong decision. The literature about the security of reinforcement learning is rapidly growing, and some surveys have been proposed to shed light on this field. However, their categorizations are insufficient for choosing an appropriate defense given the kind of system at hand. In our survey, we do not only overcome this limitation by considering a different perspective, but we also discuss the applicability of state-of-the-art attacks and defenses when reinforcement learning algorithms are used in the context of autonomous driving.