变异因素之间的相关性在现实数据中普遍存在。机器学习算法可能会受益于利用这种相关性，因为它们可以提高噪声数据的预测性能。然而，通常这种相关性不稳定（例如，它们可能在域，数据集或应用程序之间发生变化），我们希望避免利用它们。解剖学方法旨在学习捕获潜伏子空间变化不同因素的表示。常用方法涉及最小化潜伏子空间之间的相互信息，使得每个潜在的底层属性。但是，当属性相关时，这会失败。我们通过强制执行可用属性上的子空间之间的独立性来解决此问题，这允许我们仅删除不导致的依赖性，这些依赖性是由于训练数据中存在的相关结构。我们通过普发的方法实现这一目标，以最小化关于分类变量的子空间之间的条件互信息（CMI）。我们首先在理论上展示了CMI最小化是对高斯数据线性问题的稳健性解剖的良好目标。然后，我们基于MNIST和Celeba在现实世界数据集上应用我们的方法，并表明它会在相关偏移下产生脱屑和强大的模型，包括弱监督设置。

精确了解人造网络中为何对某些刺激作出反应的单位会致力于解释人工智能的一步。一个广泛使用的方法对此目标是通过激活最大化来可视化单元响应。这些合成特征可视化被声称提供了具有关于导致单元被激活的图像特征的精确信息的人类 - 在其他替代方案中具有强烈激活的自然数据集样本的优点。如果人类确实获得了可视化的因果洞察，这应该使它们能够预测干预的效果，例如如何遮挡图像的某些斑块（例如，狗的头部）改变单位的激活。在这里，我们通过询问人类来确定两个方形遮挡中的哪一个来测试这个假设，导致单元的激活更大。具有专家的大规模众群实验和测量结果表明，平均奥拉等人的激活特征可视化。 （2017）确实帮助人类对此任务（68美元\ PM 4 $％的准确性;没有任何可视化的基线表现为60份\ PM 3 $％）。然而，它们不提供其他可视化（例如DataSet样本）的任何实质性优势，其产生类似的性能（66美元，PM3 $％至67美元\ PM3 $％准确性）。我们联合起来，提出了一个客观的心理物理任务来量化单位级别解释性方法对人类的益处，并且没有证据表明，广泛使用的特征可视化方法提供了比简单的替代可视化的单位激活更好的“因果理解”。

We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of large-scale experiments and show consistent improvements irrespective of the model architecture, the pre-training technique or the type of distribution shift. At the same time, self-learning is simple to use in practice because it does not require knowledge or access to the original training data or scheme, is robust to hyperparameter choices, is straight-forward to implement and requires only a few adaptation epochs. This makes self-learning techniques highly attractive for any practitioner who applies machine learning algorithms in the real world. We present state-of-the-art adaptation results on CIFAR10-C (8.5% error), ImageNet-C (22.0% mCE), ImageNet-R (17.4% error) and ImageNet-A (14.8% error), theoretically study the dynamics of self-supervised adaptation methods and propose a new classification dataset (ImageNet-D) which is challenging even with adaptation.

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distil how many of deep learning's problem can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications. This is the preprint version of an article that has been published by Nature Machine Intelligence

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on images with a texture-shape cue conflict. We show that ImageNettrained CNNs are strongly biased towards recognising textures rather than shapes, which is in stark contrast to human behavioural evidence and reveals fundamentally different classification strategies. We then demonstrate that the same standard architecture (ResNet-50) that learns a texture-based representation on ImageNet is able to learn a shape-based representation instead when trained on 'Stylized-ImageNet', a stylized version of ImageNet. This provides a much better fit for human behavioural performance in our well-controlled psychophysical lab setting (nine experiments totalling 48,560 psychophysical trials across 97 observers) and comes with a number of unexpected emergent benefits such as improved object detection performance and previously unseen robustness towards a wide range of image distortions, highlighting advantages of a shape-based representation.

With the advent of Neural Style Transfer (NST), stylizing an image has become quite popular. A convenient way for extending stylization techniques to videos is by applying them on a per-frame basis. However, such per-frame application usually lacks temporal-consistency expressed by undesirable flickering artifacts. Most of the existing approaches for enforcing temporal-consistency suffers from one or more of the following drawbacks. They (1) are only suitable for a limited range of stylization techniques, (2) can only be applied in an offline fashion requiring the complete video as input, (3) cannot provide consistency for the task of stylization, or (4) do not provide interactive consistency-control. Note that existing consistent video-filtering approaches aim to completely remove flickering artifacts and thus do not respect any specific consistency-control aspect. For stylization tasks, however, consistency-control is an essential requirement where a certain amount of flickering can add to the artistic look and feel. Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that can stylize video streams while providing interactive consistency-control. Apart from stylization, our approach also supports various other image processing filters. For achieving interactive performance, we develop a lite optical-flow network that operates at 80 Frames per second (FPS) on desktop systems with sufficient accuracy. We show that the final consistent video-output using our flow network is comparable to that being obtained using state-of-the-art optical-flow network. Further, we employ an adaptive combination of local and global consistent features and enable interactive selection between the two. By objective and subjective evaluation, we show that our method is superior to state-of-the-art approaches.

Vision transformers have emerged as powerful tools for many computer vision tasks. It has been shown that their features and class tokens can be used for salient object segmentation. However, the properties of segmentation transformers remain largely unstudied. In this work we conduct an in-depth study of the spatial attentions of different backbone layers of semantic segmentation transformers and uncover interesting properties. The spatial attentions of a patch intersecting with an object tend to concentrate within the object, whereas the attentions of larger, more uniform image areas rather follow a diffusive behavior. In other words, vision transformers trained to segment a fixed set of object classes generalize to objects well beyond this set. We exploit this by extracting heatmaps that can be used to segment unknown objects within diverse backgrounds, such as obstacles in traffic scenes. Our method is training-free and its computational overhead negligible. We use off-the-shelf transformers trained for street-scene segmentation to process other scene types.

The problem of generating an optimal coalition structure for a given coalition game of rational agents is to find a partition that maximizes their social welfare and is known to be NP-hard. This paper proposes GCS-Q, a novel quantum-supported solution for Induced Subgraph Games (ISGs) in coalition structure generation. GCS-Q starts by considering the grand coalition as initial coalition structure and proceeds by iteratively splitting the coalitions into two nonempty subsets to obtain a coalition structure with a higher coalition value. In particular, given an $n$-agent ISG, the GCS-Q solves the optimal split problem $\mathcal{O} (n)$ times using a quantum annealing device, exploring $\mathcal{O}(2^n)$ partitions at each step. We show that GCS-Q outperforms the currently best classical solvers with its runtime in the order of $n^2$ and an expected worst-case approximation ratio of $93\%$ on standard benchmark datasets.

Cartesian impedance control is a type of motion control strategy for robots that improves safety in partially unknown environments by achieving a compliant behavior of the robot with respect to its external forces. This compliant robot behavior has the added benefit of allowing physical human guidance of the robot. In this paper, we propose a C++ implementation of compliance control valid for any torque-commanded robotic manipulator. The proposed controller implements Cartesian impedance control to track a desired end-effector pose. Additionally, joint impedance is projected in the nullspace of the Cartesian robot motion to track a desired robot joint configuration without perturbing the Cartesian motion of the robot. The proposed implementation also allows the robot to apply desired forces and torques to its environment. Several safety features such as filtering, rate limiting, and saturation are included in the proposed implementation. The core functionalities are in a re-usable base library and a Robot Operating System (ROS) ros_control integration is provided on top of that. The implementation was tested with the KUKA LBR iiwa robot and the Franka Emika Robot (Panda) both in simulation and with the physical robots.

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods in such fields is highly computationally expensive and time consuming which obstructs the progression of research and leads to a lack of comparability between methods. In this work, we propose and investigate a sandbox setup for rapid development and transparent evaluation of active learning in deep object detection. Our experiments with commonly used configurations of datasets and detection architectures found in the literature show that results obtained in our sandbox environment are representative of results on standard configurations. The total compute time to obtain results and assess the learning behavior can thereby be reduced by factors of up to 14 when comparing with Pascal VOC and up to 32 when comparing with BDD100k. This allows for testing and evaluating data acquisition and labeling strategies in under half a day and contributes to the transparency and development speed in the field of active learning for object detection.