FIB/SEM断层扫描代表了电池研究和许多其他领域中三维纳米结构表征的必不可少的工具。然而，在许多情况下，对比度和3D分类/重建问题出现，这极大地限制了该技术的适用性，尤其是在多孔材料上，例如电池或燃料电池中用于电极材料的材料。区分不同的组件（例如主动LI存储颗粒和碳/粘合剂材料）很困难，并且通常可以防止对图像数据进行可靠的定量分析，甚至可能导致关于结构 - 质地关系的错误结论。在这项贡献中，我们提出了一种新型的数据分类方法，该方法是通过FIB/SEM断层扫描获得的三维图像数据及其在NMC电池电极材料中的应用。我们使用两个不同的图像信号，即Angled SE2腔室检测器和Inlens检测器信号的信号，将信号组合在一起并训练一个随机森林，即特定的机器学习算法。我们证明，这种方法可以克服适合多相测量的现有技术的当前局限性，并且即使在当前的最新技术失败或对大型训练集的需求之后，它也可以进行定量数据重建。这种方法可能会作为使用FIB/SEM断层扫描的未来研究指南。

在过去的几十年中，人工智能领域大大进展，灵感来自生物学和神经科学领域的发现。这项工作的想法是由来自传入和横向/内部联系的人脑中皮质区域的自组织过程的过程启发。在这项工作中，我们开发了一个原始的脑激发神经模型，将自组织地图（SOM）和Hebbian学习在重新参与索马里（RESOM）模型中。该框架应用于多模式分类问题。与基于未经监督的学习的现有方法相比，该模型增强了最先进的结果。这项工作还通过在名为SPARP（自配置3D蜂窝自适应平台）的专用FPGA的平台上的模拟结果和硬件执行，演示了模型的分布式和可扩展性。头皮板可以以模块化方式互连，以支持神经模型的结构。这种统一的软件和硬件方法使得能够缩放处理并允许来自多个模态的信息进行动态合并。硬件板上的部署提供了在多个设备上并行执行的性能结果，通过专用串行链路在每个板之间的通信。由于多模式关联，所提出的统一架构，由RESOM模型和头皮硬件平台组成的精度显着提高，与集中式GPU实现相比，延迟和功耗之间的良好折衷。

Remote sensing of the Earth's surface water is critical in a wide range of environmental studies, from evaluating the societal impacts of seasonal droughts and floods to the large-scale implications of climate change. Consequently, a large literature exists on the classification of water from satellite imagery. Yet, previous methods have been limited by 1) the spatial resolution of public satellite imagery, 2) classification schemes that operate at the pixel level, and 3) the need for multiple spectral bands. We advance the state-of-the-art by 1) using commercial imagery with panchromatic and multispectral resolutions of 30 cm and 1.2 m, respectively, 2) developing multiple fully convolutional neural networks (FCN) that can learn the morphological features of water bodies in addition to their spectral properties, and 3) FCN that can classify water even from panchromatic imagery. This study focuses on rivers in the Arctic, using images from the Quickbird, WorldView, and GeoEye satellites. Because no training data are available at such high resolutions, we construct those manually. First, we use the RGB, and NIR bands of the 8-band multispectral sensors. Those trained models all achieve excellent precision and recall over 90% on validation data, aided by on-the-fly preprocessing of the training data specific to satellite imagery. In a novel approach, we then use results from the multispectral model to generate training data for FCN that only require panchromatic imagery, of which considerably more is available. Despite the smaller feature space, these models still achieve a precision and recall of over 85%. We provide our open-source codes and trained model parameters to the remote sensing community, which paves the way to a wide range of environmental hydrology applications at vastly superior accuracies and 2 orders of magnitude higher spatial resolution than previously possible.

The detection of anomalies in time series data is crucial in a wide range of applications, such as system monitoring, health care or cyber security. While the vast number of available methods makes selecting the right method for a certain application hard enough, different methods have different strengths, e.g. regarding the type of anomalies they are able to find. In this work, we compare six unsupervised anomaly detection methods with different complexities to answer the questions: Are the more complex methods usually performing better? And are there specific anomaly types that those method are tailored to? The comparison is done on the UCR anomaly archive, a recent benchmark dataset for anomaly detection. We compare the six methods by analyzing the experimental results on a dataset- and anomaly type level after tuning the necessary hyperparameter for each method. Additionally we examine the ability of individual methods to incorporate prior knowledge about the anomalies and analyse the differences of point-wise and sequence wise features. We show with broad experiments, that the classical machine learning methods show a superior performance compared to the deep learning methods across a wide range of anomaly types.

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and LAION have propelled recent dramatic progress in AI. Large neural models trained on such datasets produce impressive results and top many of today's benchmarks. A notable omission within this family of large-scale datasets is 3D data. Despite considerable interest and potential applications in 3D vision, datasets of high-fidelity 3D models continue to be mid-sized with limited diversity of object categories. Addressing this gap, we present Objaverse 1.0, a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category. We demonstrate the large potential of Objaverse via four diverse applications: training generative 3D models, improving tail category segmentation on the LVIS benchmark, training open-vocabulary object-navigation models for Embodied AI, and creating a new benchmark for robustness analysis of vision models. Objaverse can open new directions for research and enable new applications across the field of AI.

Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.

Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer subtyping problems. We extended an AMIL approach to the task of survival prediction by utilizing the classical Cox partial likelihood as a loss function, converting the AMIL model into a nonlinear proportional hazards model. We applied the model to tissue microarray (TMA) slides of 330 lung cancer patients. The results show that AMIL approaches can handle very small amounts of tissue from a TMA and reach similar C-index performance compared to established survival prediction methods trained with highly discriminative clinical factors such as age, cancer grade, and cancer stage

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency parse trees. Our approach achieves competitive results on the Natural Language Inference task, compared to the state of the art. Specifically for smaller models, the method results in a significant performance boost, emphasizing the fact that intelligent pre-training can make up for fewer parameters and help building more efficient models. Combining POS-tagging and synset prediction yields the overall best results.

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip

Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems. In this work, we propose a new paradigm for steering the behavior of neural networks, centered around \textit{task vectors}. A task vector specifies a direction in the weight space of a pre-trained model, such that movement in that direction improves performance on the task. We build task vectors by subtracting the weights of a pre-trained model from the weights of the same model after fine-tuning on a task. We show that these task vectors can be modified and combined together through arithmetic operations such as negation and addition, and the behavior of the resulting model is steered accordingly. Negating a task vector decreases performance on the target task, with little change in model behavior on control tasks. Moreover, adding task vectors together can improve performance on multiple tasks at once. Finally, when tasks are linked by an analogy relationship of the form ``A is to B as C is to D", combining task vectors from three of the tasks can improve performance on the fourth, even when no data from the fourth task is used for training. Overall, our experiments with several models, modalities and tasks show that task arithmetic is a simple, efficient and effective way of editing models.