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.
translated by 谷歌翻译
最近的深层摄影的出现使操纵和生成的内容成为机器学习研究的最前沿。自动检测深击已经看到了许多新的机器学习技术,但是,人类的检测功能的探索功能要少得多。在本文中,我们介绍了比较人类和机器检测用于模仿某人声音的音频深击的能力的结果。为此,我们使用基于Web的应用程序框架作为游戏。要求参与者区分真实和假音频样本。在我们的实验中,有378位唯一用户与最先进的AI DeepFake检测算法竞争,以12540的比赛总数。我们发现,人类和深层检测算法具有相似的优势和劣势,都在努力检测某些类型的攻击。这与许多应用领域(例如对象检测或面部识别)中AI的超人性能形成对比。关于人类的成功因素,我们发现IT专业人员没有非专业人士的优势,但母语人士比非本地人的人具有优势。此外,我们发现年长的参与者往往比年轻的参与者更容易受到影响。在为人类设计未来的网络安全培训以及开发更好的检测算法时,这些见解可能会有所帮助。
translated by 谷歌翻译
数据中毒是对机器学习和数据驱动技术的最相关的安全威胁之一。由于许多应用程序依赖于不受信任的培训数据,因此攻击者可以轻松地将恶意样本轻松地将其注入训练数据集,以降低机器学习模型的性能。正如最近的工作所示,这种拒绝服务(DOS)数据中毒攻击非常有效。为了减轻这种威胁,我们提出了一种检测DOS中毒实例的新方法。与相关工作相比,我们偏离基于聚类和异常检测的方法,这通常遭受维度的诅咒和任意异常阈值选择。相反,我们的防御是基于以这种广义的方式从训练数据中提取信息,使得我们可以基于存在于数据的未被占部分中存在的信息来识别中毒样本。我们评估我们对两个DOS中毒攻击和七个数据集的防御,并发现它可靠地识别中毒实例。与相关的工作相比,我们的防范将误报/假负率提高至少50%,通常更多。
translated by 谷歌翻译
Vision Transformers (ViTs) have become a dominant paradigm for visual representation learning with self-attention operators. Although these operators provide flexibility to the model with their adjustable attention kernels, they suffer from inherent limitations: (1) the attention kernel is not discriminative enough, resulting in high redundancy of the ViT layers, and (2) the complexity in computation and memory is quadratic in the sequence length. In this paper, we propose a novel attention operator, called lightweight structure-aware attention (LiSA), which has a better representation power with log-linear complexity. Our operator learns structural patterns by using a set of relative position embeddings (RPEs). To achieve log-linear complexity, the RPEs are approximated with fast Fourier transforms. Our experiments and ablation studies demonstrate that ViTs based on the proposed operator outperform self-attention and other existing operators, achieving state-of-the-art results on ImageNet, and competitive results on other visual understanding benchmarks such as COCO and Something-Something-V2. The source code of our approach will be released online.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
通用数据模型解决了标准化电子健康记录(EHR)数据的许多挑战,但无法将其集成深度表型所需的资源。开放的生物学和生物医学本体论(OBO)铸造本体论提供了可用于生物学知识的语义计算表示,并能够整合多种生物医学数据。但是,将EHR数据映射到OBO Foundry本体论需要大量的手动策展和域专业知识。我们介绍了一个框架,用于将观察性医学成果合作伙伴关系(OMOP)标准词汇介绍给OBO铸造本体。使用此框架,我们制作了92,367条条件,8,615种药物成分和10,673个测量结果的映射。域专家验证了映射准确性,并且在24家医院进行检查时,映射覆盖了99%的条件和药物成分和68%的测量结果。最后,我们证明OMOP2OBO映射可以帮助系统地识别可能受益于基因检测的未诊断罕见病患者。
translated by 谷歌翻译
深度学习的可解释性被广泛用于评估医学成像模型的可靠性,并降低患者建议不准确的风险。对于超过人类绩效的模型,例如从显微镜图像中预测RNA结构,可解释的建模可以进一步用于发现高度非平凡的模式,而这些模式原本是人眼无法察觉的。我们表明,可解释性可以揭示癌组织的微观外观与其基因表达分析之间的联系。尽管从组织学图像中对所有基因进行详尽的分析仍然具有挑战性,但我们估计了癌症分子亚型,生存和治疗反应的众所周知的基因子集的表达值。我们的方法成功地从图像幻灯片中确定了有意义的信息,突出了高基因表达的热点。我们的方法可以帮助表征基因表达如何塑造组织形态,这可能对病理单位中的患者分层有益。该代码可在GitHub上找到。
translated by 谷歌翻译
精神分裂症是一种慢性神经精神疾病,会引起大脑内部的不同结构改变。我们假设将深度学习应用于结构性神经影像学数据集可以检测到与疾病相关的改变,并提高分类和诊断准确性。我们使用单一可用的,常规的T1加权MRI扫描测试了这一假设,我们使用标准后处理方法从中提取了3D全脑结构。然后在三个开放数据集上开发,优化和评估了一个深度学习模型,并对精神分裂症患者进行T1加权MRI扫描。我们提出的模型优于基准模型,该模型还使用3D CNN体系结构对结构MR图像进行了训练。我们的模型几乎能够完美地(ROC曲线下的区域= 0.987),将精神分裂症患者与看不见的结构MRI扫描中的健康对照区分开。区域分析将皮质下区域和心室局部作为最预测的大脑区域。皮层结构在人类的认知,情感和社会功能中起关键作用,这些区域的结构异常与精神分裂症有关。我们的发现证实了精神分裂症与皮质下大脑结构的广泛改变有关,皮层结构信息在诊断分类中提供了突出的特征。总之,这些结果进一步证明了深度学习的潜力,以改善精神分裂症的诊断,并从单个标准的T1加权脑MRI中确定其结构性神经影像学特征。
translated by 谷歌翻译
深度神经网络(DNNS)从他们学到的表示中汲取了力量。然而,近年来,研究人员发现,DNN在学习复杂的抽象方面非常有效,但由于培训中固有的虚假相关性,也倾向于感染工件,例如偏见,聪明的汉斯(CH)或后门。数据。到目前为止,在训练有素的模型中发现此类人为和恶意行为的现有方法集中在输入数据中查找工件,这既需要数据集的可用性,又需要人为干预。在本文中,我们介绍了dora(数据不可能的表示分析):第一种自动数据敏捷方法,用于检测深神经网络中潜在感染的表示。我们进一步表明,Dora发现的受污染表示形式可用于检测任何给定数据集中的受感染样品。我们在定性和定量评估我们在受控的玩具场景和现实环境中提出的方法的性能,在这里我们证明了Dora在安全至关重要的应用中的好处。
translated by 谷歌翻译
自动生物医学图像分析的领域至关重要地取决于算法验证的可靠和有意义的性能指标。但是,当前的度量使用通常是不明智的,并且不能反映基本的域名。在这里,我们提出了一个全面的框架,该框架指导研究人员以问题意识的方式选择绩效指标。具体而言,我们专注于生物医学图像分析问题,这些问题可以解释为图像,对象或像素级别的分类任务。该框架首先编译域兴趣 - 目标结构 - ,数据集和算法与输出问题相关的属性的属性与问题指纹相关,同时还将其映射到适当的问题类别,即图像级分类,语义分段,实例,实例细分或对象检测。然后,它指导用户选择和应用一组适当的验证指标的过程,同时使他们意识到与个人选择相关的潜在陷阱。在本文中,我们描述了指标重新加载推荐框架的当前状态,目的是从图像分析社区获得建设性的反馈。当前版本是在由60多个图像分析专家的国际联盟中开发的,将在社区驱动的优化之后公开作为用户友好的工具包提供。
translated by 谷歌翻译