人脑解剖图像的专家解释是神经放射学的中心部分。已经提出了几种基于机器学习的技术来协助分析过程。但是，通常需要对ML模型进行培训以执行特定的任务，例如脑肿瘤分割或分类。相应的培训数据不仅需要费力的手动注释，而且人脑MRI中可以存在多种异常 - 甚至同时发生，这使得所有可能的异常情况都非常具有挑战性。因此，可能的解决方案是一种无监督的异常检测（UAD）系统，可以从健康受试者的未标记数据集中学习数据分布，然后应用以检测​​分布样本。然后，这种技术可用于检测异常 - 病变或异常，例如脑肿瘤，而无需明确训练该特定病理的模型。过去已经为此任务提出了几种基于变异的自动编码器（VAE）技术。即使它们在人为模拟的异常情况下表现良好，但其中许多在检测临床数据中的异常情况下表现较差。这项研究提出了“上下文编码” VAE（CEVAE）模型的紧凑版本，并结合了预处理和后处理步骤，创建了UAD管道（Strega）（Strega），该步骤对临床数据更强大，并显示其在检测到其检测方面的适用性脑MRI中的肿瘤等异常。 The proposed pipeline achieved a Dice score of 0.642$\pm$0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859$\pm$0.112 while detecting artificially induced anomalies, while the best performing baseline achieved 0.522$\pm$0.135 and 0.783$\ PM分别为0.111美元。

在机器人远程操作中的研究一直围绕着行动规范 - 从连续关节控制到离散的最终效果姿势控制。但是，这些以机器人为中心的接口通常需要具有广泛机器人专业知识的熟练操作员。为了使非专家用户可以访问远程操作，我们提出了框架“场景编辑为teleperation”（座位），其中关键的想法是将传统的“以机器人为中心的”界面转换为“以场景为中心的”界面 - 而是通过控制机器人，用户专注于通过操纵现实世界对象的数字双胞胎来指定任务的目标。结果，用户可以在没有任何机器人硬件的任何专业知识的情况下执行远程关系。为了实现这一目标，我们利用一种类别 - 不合时宜的场景完整算法，该算法将现实世界工作空间（带有未知对象）转换为可操作的虚拟场景表示和一个动作捕捉算法，并在生成机器人的动作计划之前对其进行改进的动作捕捉算法。为了训练算法，我们在过程中生成了一个大规模的，多样的套件组装数据集，其中包含模仿现实世界对象套件任务的对象芯对。我们在模拟和现实世界中的实验表明，我们的框架提高了6DOF套件组装任务的效率和成功率。一项用户研究表明，与替代机器人以机器人为中心的界面相比，座椅框架参与者获得了更高的任务成功率，并报告了主观工作量较低。可以在https://www.youtube.com/watch?v=-ndr3MKPBQQ上找到视频。

Being able to grasp objects is a fundamental component of most robotic manipulation systems. In this paper, we present a new approach to simultaneously reconstruct a mesh and a dense grasp quality map of an object from a depth image. At the core of our approach is a novel camera-centric object representation called the "object shell" which is composed of an observed "entry image" and a predicted "exit image". We present an image-to-image residual ConvNet architecture in which the object shell and a grasp-quality map are predicted as separate output channels. The main advantage of the shell representation and the corresponding neural network architecture, ShellGrasp-Net, is that the input-output pixel correspondences in the shell representation are explicitly represented in the architecture. We show that this coupling yields superior generalization capabilities for object reconstruction and accurate grasp quality estimation implicitly considering the object geometry. Our approach yields an efficient dense grasp quality map and an object geometry estimate in a single forward pass. Both of these outputs can be used in a wide range of robotic manipulation applications. With rigorous experimental validation, both in simulation and on a real setup, we show that our shell-based method can be used to generate precise grasps and the associated grasp quality with over 90% accuracy. Diverse grasps computed on shell reconstructions allow the robot to select and execute grasps in cluttered scenes with more than 93% success rate.

Monitoring water is a complex task due to its dynamic nature, added pollutants, and land build-up. The availability of high-resolu-tion data by Sentinel-2 multispectral products makes implementing remote sensing applications feasible. However, overutilizing or underutilizing multispectral bands of the product can lead to inferior performance. In this work, we compare the performances of ten out of the thirteen bands available in a Sentinel-2 product for water segmentation using eight machine learning algorithms. We find that the shortwave infrared bands (B11 and B12) are the most superior for segmenting water bodies. B11 achieves an overall accuracy of $71\%$ while B12 achieves $69\%$ across all algorithms on the test site. We also find that the Support Vector Machine (SVM) algorithm is the most favourable for single-band water segmentation. The SVM achieves an overall accuracy of $69\%$ across the tested bands over the given test site. Finally, to demonstrate the effectiveness of choosing the right amount of data, we use only B11 reflectance data to train an artificial neural network, BandNet. Even with a basic architecture, BandNet is proportionate to known architectures for semantic and water segmentation, achieving a $92.47$ mIOU on the test site. BandNet requires only a fraction of the time and resources to train and run inference, making it suitable to be deployed on web applications to run and monitor water bodies in localized regions. Our codebase is available at https://github.com/IamShubhamGupto/BandNet.

In this paper, we discuss an imitation learning based method for reducing the calibration error for a mixed reality system consisting of a vision sensor and a projector. Unlike a head mounted display, in this setup, augmented information is available to a human subject via the projection of a scene into the real world. Inherently, the camera and projector need to be calibrated as a stereo setup to project accurate information in 3D space. Previous calibration processes require multiple recording and parameter tuning steps to achieve the desired calibration, which is usually time consuming process. In order to avoid such tedious calibration, we train a CNN model to iteratively correct the extrinsic offset given a QR code and a projected pattern. We discuss the overall system setup, data collection for training, and results of the auto-correction model.

Multi-Scale and U-shaped Networks are widely used in various image restoration problems, including deblurring. Keeping in mind the wide range of applications, we present a comparison of these architectures and their effects on image deblurring. We also introduce a new block called as NFResblock. It consists of a Fast Fourier Transformation layer and a series of modified Non-Linear Activation Free Blocks. Based on these architectures and additions, we introduce NFResnet and NFResnet+, which are modified multi-scale and U-Net architectures, respectively. We also use three different loss functions to train these architectures: Charbonnier Loss, Edge Loss, and Frequency Reconstruction Loss. Extensive experiments on the Deep Video Deblurring dataset, along with ablation studies for each component, have been presented in this paper. The proposed architectures achieve a considerable increase in Peak Signal to Noise (PSNR) ratio and Structural Similarity Index (SSIM) value.

Language-conditioned policies allow robots to interpret and execute human instructions. Learning such policies requires a substantial investment with regards to time and compute resources. Still, the resulting controllers are highly device-specific and cannot easily be transferred to a robot with different morphology, capability, appearance or dynamics. In this paper, we propose a sample-efficient approach for training language-conditioned manipulation policies that allows for rapid transfer across different types of robots. By introducing a novel method, namely Hierarchical Modularity, and adopting supervised attention across multiple sub-modules, we bridge the divide between modular and end-to-end learning and enable the reuse of functional building blocks. In both simulated and real world robot manipulation experiments, we demonstrate that our method outperforms the current state-of-the-art methods and can transfer policies across 4 different robots in a sample-efficient manner. Finally, we show that the functionality of learned sub-modules is maintained beyond the training process and can be used to introspect the robot decision-making process. Code is available at https://github.com/ir-lab/ModAttn.

Human behavior understanding requires looking at minute details in the large context of a scene containing multiple input modalities. It is necessary as it allows the design of more human-like machines. While transformer approaches have shown great improvements, they face multiple challenges such as lack of data or background noise. To tackle these, we introduce the Forced Attention (FAt) Transformer which utilize forced attention with a modified backbone for input encoding and a use of additional inputs. In addition to improving the performance on different tasks and inputs, the modification requires less time and memory resources. We provide a model for a generalised feature extraction for tasks concerning social signals and behavior analysis. Our focus is on understanding behavior in videos where people are interacting with each other or talking into the camera which simulates the first person point of view in social interaction. FAt Transformers are applied to two downstream tasks: personality recognition and body language recognition. We achieve state-of-the-art results for Udiva v0.5, First Impressions v2 and MPII Group Interaction datasets. We further provide an extensive ablation study of the proposed architecture.

Learned locomotion policies can rapidly adapt to diverse environments similar to those experienced during training but lack a mechanism for fast tuning when they fail in an out-of-distribution test environment. This necessitates a slow and iterative cycle of reward and environment redesign to achieve good performance on a new task. As an alternative, we propose learning a single policy that encodes a structured family of locomotion strategies that solve training tasks in different ways, resulting in Multiplicity of Behavior (MoB). Different strategies generalize differently and can be chosen in real-time for new tasks or environments, bypassing the need for time-consuming retraining. We release a fast, robust open-source MoB locomotion controller, Walk These Ways, that can execute diverse gaits with variable footswing, posture, and speed, unlocking diverse downstream tasks: crouching, hopping, high-speed running, stair traversal, bracing against shoves, rhythmic dance, and more. Video and code release: https://gmargo11.github.io/walk-these-ways/

Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation (MT), these examples are typically randomly sampled from the development dataset with a similar distribution as the evaluation set. However, it is unclear how the choice of these in-context examples and their ordering impacts the output translation quality. In this work, we aim to understand the properties of good in-context examples for MT in both in-domain and out-of-domain settings. We show that the translation quality and the domain of the in-context examples matter and that 1-shot noisy unrelated example can have a catastrophic impact on output quality. While concatenating multiple random examples reduces the effect of noise, a single good prompt optimized to maximize translation quality on the development dataset can elicit learned information from the pre-trained language model. Adding similar examples based on an n-gram overlap with the test source significantly and consistently improves the translation quality of the outputs, outperforming a strong kNN-MT baseline in 2 out of 4 out-of-domain datasets.