One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are difficult to capture and are often of poor quality due to the distortion and loss of colour and contrast in water. This makes it difficult to train supervised deep learning models on large and diverse datasets, which can limit the model's performance. In this paper, we explore an alternative approach to supervised underwater image enhancement. Specifically, we propose a novel unsupervised underwater image enhancement framework that employs a conditional variational autoencoder (cVAE) to train a deep learning model with probabilistic adaptive instance normalization (PAdaIN) and statistically guided multi-colour space stretch that produces realistic underwater images. The resulting framework is composed of a U-Net as a feature extractor and a PAdaIN to encode the uncertainty, which we call UDnet. To improve the visual quality of the images generated by UDnet, we use a statistically guided multi-colour space stretch module that ensures visual consistency with the input image and provides an alternative to training using a ground truth image. The proposed model does not need manual human annotation and can learn with a limited amount of data and achieves state-of-the-art results on underwater images. We evaluated our proposed framework on eight publicly-available datasets. The results show that our proposed framework yields competitive performance compared to other state-of-the-art approaches in quantitative as well as qualitative metrics. Code available at https://github.com/alzayats/UDnet .

基于高质量标签的鱼类跟踪和细分的DNN很昂贵。替代无监督的方法取决于视频数据中自然发生的空间和时间变化来生成嘈杂的伪界图标签。这些伪标签用于训练多任务深神经网络。在本文中，我们提出了一个三阶段的框架，用于强大的鱼类跟踪和分割，其中第一阶段是光流模型，该模型使用帧之间的空间和时间一致性生成伪标签。在第二阶段，一个自我监督的模型会逐步完善伪标签。在第三阶段，精制标签用于训练分割网络。在培训或推理期间没有使用人类注释。进行了广泛的实验来验证我们在三个公共水下视频数据集中的方法，并证明它对视频注释和细分非常有效。我们还评估框架对不同成像条件的鲁棒性，并讨论当前实施的局限性。

海洋生态系统及其鱼类栖息地越来越重要，因为它们在提供有价值的食物来源和保护效果方面的重要作用。由于它们的偏僻且难以接近自然，因此通常使用水下摄像头对海洋环境和鱼类栖息地进行监测。这些相机产生了大量数字数据，这些数据无法通过当前的手动处理方法有效地分析，这些方法涉及人类观察者。 DL是一种尖端的AI技术，在分析视觉数据时表现出了前所未有的性能。尽管它应用于无数领域，但仍在探索其在水下鱼类栖息地监测中的使用。在本文中，我们提供了一个涵盖DL的关键概念的教程，该教程可帮助读者了解对DL的工作原理的高级理解。该教程还解释了一个逐步的程序，讲述了如何为诸如水下鱼类监测等挑战性应用开发DL算法。此外，我们还提供了针对鱼类栖息地监测的关键深度学习技术的全面调查，包括分类，计数，定位和细分。此外，我们对水下鱼类数据集进行了公开调查，并比较水下鱼类监测域中的各种DL技术。我们还讨论了鱼类栖息地加工深度学习的新兴领域的一些挑战和机遇。本文是为了作为希望掌握对DL的高级了解，通过遵循我们的分步教程而为其应用开发的海洋科学家的教程，并了解如何发展其研究，以促进他们的研究。努力。同时，它适用于希望调查基于DL的最先进方法的计算机科学家，以进行鱼类栖息地监测。

由于水下环境复杂，水下鱼类分割以估计鱼体测量值仍然无法解决。依靠完全监督的分割模型需要收集每个像素标签，这很耗时且容易过度拟合。自我监督的学习方法可以帮助避免大型注释的培训数据集的要求，但是，在现实世界中，它们应该达到良好的细分质量。在本文中，我们介绍了一种基于变压器的方法，该方法使用自学意义重大的鱼类分割。我们提出的模型对视频进行了培训 - 没有任何注释，可以在野外现场拍摄的水下视频中进行鱼类分割。我们表明，当对一个数据集的一系列水下视频进行培训时，该建议的模型超过了以前的基于CNN的基于CNN和基于变压器的自我监督方法，并在两个未见的水下视频数据集中相对接近具有监督方法的性能。这表明了我们的模型的概括性以及它不需要预培训模型的事实。此外，我们表明，由于其密集的表示学习，我们的模型是计算效率的。我们提供定量和定性的结果，以证明我们的模型的重要功能。

We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes are competitive on few-shot learning problems with representations learned by special-purpose algorithms designed for such problems. We offer an explanation for this phenomenon based on the concept of class-features variability collapse, which refers to the training dynamics of deep classification networks where the feature embeddings of samples belonging to the same class tend to concentrate around their class means. More specifically, we examine the few-shot error of the learned feature map, which is the classification error of the nearest class-center classifier using centers learned from a small number of random samples from each class. Assuming that the classes appearing in the data are selected independently from a distribution, we show that the few-shot error generalizes from the training data to unseen test data, and we provide an upper bound on the expected few-shot error for new classes (selected from the same distribution) using the average few-shot error for the source classes. Additionally, we show that the few-shot error on the training data can be upper bounded using the degree of class-features variability collapse. This suggests that foundation models can provide feature maps that are transferable to new downstream tasks even with limited data available.

3D reconstruction and novel view synthesis of dynamic scenes from collections of single views recently gained increased attention. Existing work shows impressive results for synthetic setups and forward-facing real-world data, but is severely limited in the training speed and angular range for generating novel views. This paper addresses these limitations and proposes a new method for full 360{\deg} novel view synthesis of non-rigidly deforming scenes. At the core of our method are: 1) An efficient deformation module that decouples the processing of spatial and temporal information for acceleration at training and inference time; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. We evaluate the proposed approach on the established synthetic D-NeRF benchmark, that enables efficient reconstruction from a single monocular view per time-frame randomly sampled from a full hemisphere. We refer to this form of inputs as monocularized data. To prove its practicality for real-world scenarios, we recorded twelve challenging sequences with human actors by sampling single frames from a synchronized multi-view rig. In both cases, our method is trained significantly faster than previous methods (minutes instead of days) while achieving higher visual accuracy for generated novel views. Our source code and data is available at our project page https://graphics.tu-bs.de/publications/kappel2022fast.

For an autonomous vehicle, the ability to sense its surroundings and to build an overall representation of the environment by fusing different sensor data streams is fundamental. To this end, the poses of all sensors need to be accurately determined. Traditional calibration methods are based on: 1) using targets specifically designed for calibration purposes in controlled environments, 2) optimizing a quality metric of the point clouds collected while traversing an unknown but static environment, or 3) optimizing the match among per-sensor incremental motion observations along a motion path fulfilling special requirements. In real scenarios, however, the online applicability of these methods can be limited, as they are typically highly dynamic, contain degenerate paths, and require fast computations. In this paper, we propose an approach that tackles some of these challenges by formulating the calibration problem as a joint but structured optimization problem of all sensor calibrations that takes as input a summary of the point cloud information consisting of ground points and pole detections. We demonstrate the efficiency and quality of the results of the proposed approach in a set of experiments with LiDAR simulation and real data from an urban trip.

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks with fewer data, a quality of meta learning. It is important to highlight that we focus on heterogeneous tasks, which are of distinct kind, in contrast to typically considered homogeneous tasks (e.g., if all tasks are classification or if all tasks are regression tasks). The fundamental idea is to train a multi-task model, such that when an unseen task is introduced, it can learn in fewer steps whilst offering a performance at least as good as conventional single task learning on the new task or inclusion within the MTL. By conducting various experiments, we demonstrate this paradigm on two datasets and four tasks: NYU-v2 and the taskonomy dataset for which we perform semantic segmentation, depth estimation, surface normal estimation, and edge detection. MTML achieves state-of-the-art results for most of the tasks. Although semantic segmentation suffers quantitatively, our MTML method learns to identify segmentation classes absent in the pseudo labelled ground truth of the taskonomy dataset.

这项工作提出了专门针对粒子探测器的低潜伏期图神经网络（GNN）设计的新型可重构体系结构。加速粒子探测器的GNN是具有挑战性的，因为它需要次微秒延迟才能在CERN大型强子撞机实验的级别1触发器中部署网络以进行在线事件选择。本文提出了一种自定义代码转换，并在基于互动网络的GNN中使用完全连接的图表中的矩阵乘法操作降低了强度，从而避免了昂贵的乘法。它利用了稀疏模式以及二进制邻接矩阵，并避免了不规则的内存访问，从而降低了延迟和硬件效率的提高。此外，我们引入了一种基于外部产品的基质乘法方法，该方法通过降低潜伏期设计的强度降低来增强。此外，引入了融合步骤，以进一步降低设计延迟。此外，提出了GNN特异性算法 - 硬件共同设计方法，该方法不仅找到了具有更好延迟的设计，而且在给定的延迟约束下发现了高精度的设计。最后，已经设计和开源了此低延迟GNN硬件体系结构的可自定义模板，该模板可以使用高级合成工具来生成低延迟的FPGA设计，并有效地利用资源。评估结果表明，我们的FPGA实施速度高24倍，并且消耗的功率比GPU实施少45倍。与我们以前的FPGA实施相比，这项工作的延迟降低了6.51至16.7倍。此外，我们的FPGA设计的延迟足以使GNN在亚微秒，实时撞机触发器系统中部署，从而使其能够从提高的精度中受益。

诸如DALL-E 2之类的生成模型可以代表放射学中人工智能研究的图像生成，增强和操纵的有希望的未来工具，前提是这些模型具有足够的医疗领域知识。在这里，我们证明DALL-E 2在零拍的文本到图像生成方面，学习了具有有希望的功能的X射线图像的相关表示，将图像的延续超出其原始边界或删除元素，尽管病理产生或CT，MRI和超声图像仍然受到限制。因此，即使事先需要对这些模型进行进一步的微调和适应，也需要使用生成模型来增强和生成放射学数据似乎是可行的。