We propose a novel teacher-student model for semi-supervised multi-organ segmentation. In teacher-student model, data augmentation is usually adopted on unlabeled data to regularize the consistent training between teacher and student. We start from a key perspective that fixed relative locations and variable sizes of different organs can provide distribution information where a multi-organ CT scan is drawn. Thus, we treat the prior anatomy as a strong tool to guide the data augmentation and reduce the mismatch between labeled and unlabeled images for semi-supervised learning. More specifically, we propose a data augmentation strategy based on partition-and-recovery N$^3$ cubes cross- and within- labeled and unlabeled images. Our strategy encourages unlabeled images to learn organ semantics in relative locations from the labeled images (cross-branch) and enhances the learning ability for small organs (within-branch). For within-branch, we further propose to refine the quality of pseudo labels by blending the learned representations from small cubes to incorporate local attributes. Our method is termed as MagicNet, since it treats the CT volume as a magic-cube and $N^3$-cube partition-and-recovery process matches with the rule of playing a magic-cube. Extensive experiments on two public CT multi-organ datasets demonstrate the effectiveness of MagicNet, and noticeably outperforms state-of-the-art semi-supervised medical image segmentation approaches, with +7% DSC improvement on MACT dataset with 10% labeled images.

For guiding the UAV swarm to pass through narrow openings, a trapezoid virtual tube is designed in our previous work. In this paper, we generalize its application range to the condition that there exist obstacles inside the trapezoid virtual tube and UAVs have strict speed constraints. First, a distributed vector field controller is proposed for the trapezoid virtual tube with no obstacle inside. The relationship between the trapezoid virtual tube and the speed constraints is also presented. Then, a switching logic for the obstacle avoidance is put forward. The key point is to divide the trapezoid virtual tube containing obstacles into several sub trapezoid virtual tubes with no obstacle inside. Formal analyses and proofs are made to show that all UAVs are able to pass through the trapezoid virtual tube safely. Besides, the effectiveness of the proposed method is validated by numerical simulations and real experiments.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such as predicting pseudo labels for new domain datasets. Since pseudo labels are noisy and unreliable, these methods suffer from catastrophic forgetting and error accumulation when dealing with dynamic data distributions. Motivated by the prompt learning in NLP, in this paper, we propose to learn an image-level visual domain prompt for target domains while having the source model parameters frozen. During testing, the changing target datasets can be adapted to the source model by reformulating the input data with the learned visual prompts. Specifically, we devise two types of prompts, i.e., domains-specific prompts and domains-agnostic prompts, to extract current domain knowledge and maintain the domain-shared knowledge in the continual adaptation. Furthermore, we design a homeostasis-based prompt adaptation strategy to suppress domain-sensitive parameters in domain-invariant prompts to learn domain-shared knowledge more effectively. This transition from the model-dependent paradigm to the model-free one enables us to bypass the catastrophic forgetting and error accumulation problems. Experiments show that our proposed method achieves significant performance gains over state-of-the-art methods on four widely-used benchmarks, including CIFAR-10C, CIFAR-100C, ImageNet-C, and VLCS datasets.

The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based image signal processing (ISP) pipeline replacing the standard mobile ISPs that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale Fujifilm UltraISP dataset consisting of thousands of paired photos captured with a normal mobile camera sensor and a professional 102MP medium-format FujiFilm GFX100 camera. The runtime of the resulting models was evaluated on the Snapdragon's 8 Gen 1 GPU that provides excellent acceleration results for the majority of common deep learning ops. The proposed solutions are compatible with all recent mobile GPUs, being able to process Full HD photos in less than 20-50 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.

为了在混乱的环境中引导多代理系统，连接的四边形虚拟管均设计供所有代理保持在其内部移动，其基础称为单梯形虚拟管。管子内部没有障碍物，即管内部的区域可将其视为安全区域。然后，为单个梯形虚拟试管传递问题提出了分布式群体控制器。该问题通过没有局部最小值的梯度矢量场方法解决。做出正式的分析和证明是为了表明所有代理都能够通过单梯形虚拟管。最后，为了方便实际使用，提出了一个修改的控制器。对于连接的四边形虚拟管，提出了修改的开关逻辑，以避免僵局并防止代理在虚拟管外移动。最后，通过数值模拟和实际实验来验证所提出方法的有效性。

尽管做出了巨大的努力，但GigapixelS的分类全扫描图像（WSI）被严重限制在整个幻灯片的约束计算资源中，或者使用不同尺度的知识利用有限。此外，以前的大多数尝试都缺乏不确定性估计的能力。通常，病理学家经常共同分析不同的宏伟速度的WSI。如果通过使用单个放大倍率来不确定病理学家，那么他们将反复更改放大倍率以发现组织的各种特征。受病理学家的诊断过程的激励，在本文中，我们为WSI提出了一个可信赖的多尺度分类框架。我们的框架利用视觉变压器作为多部门的骨干，可以共同分类建模，估计显微镜的每种放大倍率的不确定性，并整合了来自不同放大倍率的证据。此外，为了利用WSIS的歧视性补丁并减少对计算资源的需求，我们建议使用注意力推广和非最大抑制作用提出一种新颖的补丁选择模式。为了从经验研究我们的方法的有效性，使用两个基准数据库对我们的WSI分类任务进行了经验实验。获得的结果表明，与最先进的方法相比，可信赖的框架可以显着改善WSI分类性能。

很少有课堂学习（FSCIL）着重于设计学习算法，这些学习算法可以不断地从几个样本中学习一系列新任务，而不会忘记旧任务。困难是，从新任务中进行一系列有限数据的培训会导致严重的过度拟合问题，并导致众所周知的灾难性遗忘问题。现有研究主要利用图像信息，例如存储以前任务的图像知识或限制分类器更新。但是，他们忽略了分析课堂标签的信息丰富且较少的嘈杂文本信息。在这项工作中，我们建议通过采用内存提示来利用标签文本信息。内存提示可以依次学习新数据，同时存储先前的知识。此外，为了优化内存提示而不破坏存储的知识，我们提出了基于刺激的训练策略。它根据图像嵌入刺激（即嵌入元素的分布）来优化内存提示。实验表明，我们提出的方法的表现优于所有先前的最新方法，从而大大减轻了灾难性的遗忘和过度拟合问题。

神经网络已广泛应用于垃圾邮件和网络钓鱼检测，入侵预防和恶意软件检测等安全应用程序。但是，这种黑盒方法通常在应用中具有不确定性和不良的解释性。此外，神经网络本身通常容易受到对抗攻击的影响。由于这些原因，人们对可信赖和严格的方法有很高的需求来验证神经网络模型的鲁棒性。对抗性的鲁棒性在处理恶意操纵输入时涉及神经网络的可靠性，是安全和机器学习中最热门的主题之一。在这项工作中，我们在神经网络的对抗性鲁棒性验证中调查了现有文献，并在机器学习，安全和软件工程领域收集了39项多元化研究工作。我们系统地分析了它们的方法，包括如何制定鲁棒性，使用哪种验证技术以及每种技术的优势和局限性。我们从正式验证的角度提供分类学，以全面理解该主题。我们根据财产规范，减少问题和推理策略对现有技术进行分类。我们还展示了使用样本模型在现有研究中应用的代表性技术。最后，我们讨论了未来研究的开放问题。