现有的自我监督学习策略被限制在有限的目标或主要针对单峰应用程序的通用下游任务。对于复杂性和域亲和力（例如模因分析）而言，这对命令性的多模式应用有了孤立的进展。在这里，我们介绍了两种自我监督的预训练方法，即ext-pie-net和mm-simclr（i）在预训练期间使用现成的多模式仇恨语音数据，并且（ii）执行自我 - 通过合并多个专业借口任务，有效地迎合模因分析所需的复杂多模式表示学习，从而有效地迎合了学习。我们实验不同的自我实验策略，包括可以帮助学习丰富的跨模式表示并使用流行的线性探测来评估可恨模因任务的潜在变体。拟议的解决方案通过标签有效的培训与完全监督的基线竞争，同时在梅诺特挑战的所有三个任务上明显优于他们，分别为0.18％，23.64％和0.93％的绩效增长。此外，我们通过在Harmeme任务上报告竞争性能来证明所提出的解决方案的普遍性。最后，我们通过分析特定于任务的学习，使用更少的标记培训样本来建立学习表现的质量，并争辩说，自主策略和手头下游任务的复杂性是相关的。我们的努力强调了更好的多模式自学方法的要求，涉及有效的微调和可推广性能的专业借口任务。

Quantum computing (QC) promises significant advantages on certain hard computational tasks over classical computers. However, current quantum hardware, also known as noisy intermediate-scale quantum computers (NISQ), are still unable to carry out computations faithfully mainly because of the lack of quantum error correction (QEC) capability. A significant amount of theoretical studies have provided various types of QEC codes; one of the notable topological codes is the surface code, and its features, such as the requirement of only nearest-neighboring two-qubit control gates and a large error threshold, make it a leading candidate for scalable quantum computation. Recent developments of machine learning (ML)-based techniques especially the reinforcement learning (RL) methods have been applied to the decoding problem and have already made certain progress. Nevertheless, the device noise pattern may change over time, making trained decoder models ineffective. In this paper, we propose a continual reinforcement learning method to address these decoding challenges. Specifically, we implement double deep Q-learning with probabilistic policy reuse (DDQN-PPR) model to learn surface code decoding strategies for quantum environments with varying noise patterns. Through numerical simulations, we show that the proposed DDQN-PPR model can significantly reduce the computational complexity. Moreover, increasing the number of trained policies can further improve the agent's performance. Our results open a way to build more capable RL agents which can leverage previously gained knowledge to tackle QEC challenges.

We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images together with 3D-consistent panoptic segmentation from novel viewpoints. Unlike existing approaches which use 3D input directly or indirectly, our method requires only machine-generated 2D panoptic segmentation masks inferred from a pre-trained network. Our core contribution is a panoptic lifting scheme based on a neural field representation that generates a unified and multi-view consistent, 3D panoptic representation of the scene. To account for inconsistencies of 2D instance identifiers across views, we solve a linear assignment with a cost based on the model's current predictions and the machine-generated segmentation masks, thus enabling us to lift 2D instances to 3D in a consistent way. We further propose and ablate contributions that make our method more robust to noisy, machine-generated labels, including test-time augmentations for confidence estimates, segment consistency loss, bounded segmentation fields, and gradient stopping. Experimental results validate our approach on the challenging Hypersim, Replica, and ScanNet datasets, improving by 8.4, 13.8, and 10.6% in scene-level PQ over state of the art.

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to directly generate volumetric radiance fields. To this end, we propose a 3D denoising model which directly operates on an explicit voxel grid representation. However, as radiance fields generated from a set of posed images can be ambiguous and contain artifacts, obtaining ground truth radiance field samples is non-trivial. We address this challenge by pairing the denoising formulation with a rendering loss, enabling our model to learn a deviated prior that favours good image quality instead of trying to replicate fitting errors like floating artifacts. In contrast to 2D-diffusion models, our model learns multi-view consistent priors, enabling free-view synthesis and accurate shape generation. Compared to 3D GANs, our diffusion-based approach naturally enables conditional generation such as masked completion or single-view 3D synthesis at inference time.

Neglected tropical diseases (NTDs) continue to affect the livelihood of individuals in countries in the Southeast Asia and Western Pacific region. These diseases have been long existing and have caused devastating health problems and economic decline to people in low- and middle-income (developing) countries. An estimated 1.7 billion of the world's population suffer one or more NTDs annually, this puts approximately one in five individuals at risk for NTDs. In addition to health and social impact, NTDs inflict significant financial burden to patients, close relatives, and are responsible for billions of dollars lost in revenue from reduced labor productivity in developing countries alone. There is an urgent need to better improve the control and eradication or elimination efforts towards NTDs. This can be achieved by utilizing machine learning tools to better the surveillance, prediction and detection program, and combat NTDs through the discovery of new therapeutics against these pathogens. This review surveys the current application of machine learning tools for NTDs and the challenges to elevate the state-of-the-art of NTDs surveillance, management, and treatment.

Cement is the most used construction material. The performance of cement hydrate depends on the constituent phases, viz. alite, belite, aluminate, and ferrites present in the cement clinker, both qualitatively and quantitatively. Traditionally, clinker phases are analyzed from optical images relying on a domain expert and simple image processing techniques. However, the non-uniformity of the images, variations in the geometry and size of the phases, and variabilities in the experimental approaches and imaging methods make it challenging to obtain the phases. Here, we present a machine learning (ML) approach to detect clinker microstructure phases automatically. To this extent, we create the first annotated dataset of cement clinker by segmenting alite and belite particles. Further, we use supervised ML methods to train models for identifying alite and belite regions. Specifically, we finetune the image detection and segmentation model Detectron-2 on the cement microstructure to develop a model for detecting the cement phases, namely, Cementron. We demonstrate that Cementron, trained only on literature data, works remarkably well on new images obtained from our experiments, demonstrating its generalizability. We make Cementron available for public use.

现代机器学习研究依赖于相对较少的精心策划数据集。即使在这些数据集中，通常在“不整合”或原始数据中，从业人员也面临着重要的数据质量和多样性问题，这些问题可能会非常强烈地解决。应对这些挑战的现有方法往往会对特定问题做出强烈的假设，并且通常需要先验知识或元数据，例如域标签。我们的工作与这些方法是正交的：相反，我们专注于为元数据考古学提供一个统一和有效的框架 - 在数据集中发现和推断示例的元数据。我们使用简单的转换策划了可能存在的数据集（例如，错误标记，非典型或过度分布示例）中可能存在的数据子集，并利用这些探针套件之间的学习动力学差异来推断感兴趣的元数据。我们的方法与跨不同任务的更复杂的缓解方法相提并论：识别和纠正标签错误的示例，对少数民族样本进行分类，优先考虑与培训相关的点并启用相关示例的可扩展人类审核。

与汽车和其他公路车辆相比，公共汽车和重型车辆由于其尺寸较大而具有更多的盲点。因此，这些重型车辆造成的事故更具致命性，并给其他道路使用者造成严重伤害。这些可能的盲点碰撞可以使用基于视觉的对象检测方法来尽早确定。然而，现有的基于最新视觉的对象检测模型在很大程度上依赖于单个功能描述符来做出决策。在这项研究中，提出了基于高级功能描述符的两个卷积神经网络（CNN）的设计，并提出了它们与更快的R-CNN的集成，以检测重型车辆的盲点碰撞。此外，提出了一种融合方法，以整合两个预训练的网络（即Resnet 50和Resnet 101），用于提取高水平的特征以进行盲点车辆检测。功能的融合显着提高了更快的R-CNN的性能，并优于现有的最新方法。两种方法均在公共汽车的自我录制的盲点车辆检测数据集和用于车辆检测的在线LISA数据集上进行了验证。对于两种提出的方​​法，对于自记录的数据集，可获得3.05％和3.49％的虚假检测率（FDR），使这些方法适用于实时应用。

由于模型列出是现代NLP的核心，因此我们着手提高其效率。通过训练示例的动机通常是多余的，我们设计了一种以流媒体方式过滤示例的算法。我们的关键技术是两个：（1）自动确定跳过向后传播的训练损失阈值；（2）维护一个元预测指标，以进一步跳过正向传播。在各种基准测试的基准上，我们的算法将所需的训练示例降低了5 $ \ times $，而平均仅看到轻微的降级，因此将其化为三阶段的过程。我们的方法即使在一个训练时期也很少有效，每个训练示例一次遇到一次。它易于实现，并且与现有的模型列出优化（例如层冻结）兼容。

在本文中，我们提出了一个新的基于聚类的主动学习框架，即使用基于聚类的采样（ALCS）的主动学习，以解决标记数据的短缺。ALCS采用基于密度的聚类方法来探索数据集群结构，而无需详尽的参数调整。引入了基于双簇边界的样本查询过程，以提高对高度重叠类分类的学习绩效。此外，我们制定了一种有效的多样性探索策略，以解决查询样品之间的冗余。我们的实验结果证明了ALCS方法的疗效。