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
Temporal Action Localization (TAL) methods typically operate on top of feature sequences from a frozen snippet encoder that is pretrained with the Trimmed Action Classification (TAC) tasks, resulting in a task discrepancy problem. While existing TAL methods mitigate this issue either by retraining the encoder with a pretext task or by end-to-end fine-tuning, they commonly require an overload of high memory and computation. In this work, we introduce Soft-Landing (SoLa) strategy, an efficient yet effective framework to bridge the transferability gap between the pretrained encoder and the downstream tasks by incorporating a light-weight neural network, i.e., a SoLa module, on top of the frozen encoder. We also propose an unsupervised training scheme for the SoLa module; it learns with inter-frame Similarity Matching that uses the frame interval as its supervisory signal, eliminating the need for temporal annotations. Experimental evaluation on various benchmarks for downstream TAL tasks shows that our method effectively alleviates the task discrepancy problem with remarkable computational efficiency.
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
近年来,由于海洋漏油事故严重影响环境,自然资源和沿海居民的生活,近年来,漏油事件引起了人们的关注。高光谱遥感图像提供了丰富的光谱信息,这对在复杂的海洋场景中监测漏油物有益。但是,大多数现有方法都是基于受监督和半监督的框架来检测高光谱图像(HSIS)的漏油事件,这些框架需要大量努力来注释一定数量的高质量训练集。在这项研究中,我们首次尝试基于HSIS的隔离森林开发无监督的漏油检测方法。首先,考虑到噪声水平在不同的频段之间有所不同,因此利用了噪声方差估计方法来评估不同频段的噪声水平,并且消除了因严重噪声而损坏的频段。其次,使用内核主成分分析(KPCA)来降低HSIS的高维度。然后,用隔离林估计属于海水和油泄漏之一的每个像素的概率,并且使用群集算法在检测到的概率上自动生产一组伪标记的训练样品。最后,可以通过在减少尺寸的数据上执行支持向量机(SVM)来获得初始检测图,然后,使用扩展的随机Walker(ERW)模型进一步优化初始检测结果,以改善检测检测漏油的准确性。关于我们自己创建的空气传播高光谱漏油数据(HOSD)的实验表明,该方法在其他最先进的检测方法方面获得了卓越的检测性能。
translated by 谷歌翻译
多人在线战场(MOBA)是最成功的游戏类型之一。像英雄联盟这样的MOBA游戏具有竞争性环境,玩家竞争他们的排名。在大多数MOBA游戏中,玩家的排名取决于比赛结果(获胜或输)。由于团队合作的本质,这似乎很自然,但是从某种意义上说,这是不公平的,因为在损失的情况下,付出很多努力的球员失去了排名胜利。为了减少基于团队的排名系统的副作用并公正地评估球员的表现,我们提出了一种新颖的嵌入模型,该模型将球员的动作转换为基于动作对球队胜利的各自贡献的定量分数。我们的模型是使用基于序列的深度学习模型构建的,其新型损失功能在团队比赛中起作用。基于序列的深度学习模型处理从游戏开始到团队游戏中的动作序列,使用GRU单元从上一步和当前输入选择性地采用隐藏状态。损失功能旨在帮助动作得分反映球队的最终成绩和成功。我们表明,我们的模型可以公平地评估玩家的个人表现,并分析玩家各自动作的贡献。
translated by 谷歌翻译
基于生成模型的图像无损压缩算法在改善压缩比方面取得了巨大的成功。但是,即使使用最先进的AI加速芯片,它们中大多数的吞吐量也小于1 Mb/s,从而阻止了它们的大多数现实应用应用,通常需要100 MB/s。在本文中,我们提出了PILC,这是一种端到端图像无损压缩框架,使用单个NVIDIA TESLA V100 GPU实现200 Mb/s的压缩和减压,比以前最有效的速度快10倍。为了获得此结果,我们首先开发了一个AI编解码器,该AI编解码器结合了自动回归模型和VQ-VAE,在轻质设置中性能很好,然后我们设计了一个低复杂性熵编码器,可与我们的编解码器配合使用。实验表明,在多个数据集中,我们的框架压缩比PNG高30%。我们认为,这是将AI压缩推向商业用途的重要步骤。
translated by 谷歌翻译
在医疗保健系统中,需要患者使用可穿戴设备进行远程数据收集和对健康数据的实时监控以及健康状况的状态。可穿戴设备的这种采用导致收集和传输的数据量显着增加。由于设备由较小的电池电源运行,因此由于设备的高处理要求以进行数据收集和传输,因此可以快速减少它们。鉴于医疗数据的重要性,必须所有传输数据遵守严格的完整性和可用性要求。减少医疗保健数据的量和传输频率将通过使用推理算法改善设备电池寿命。有一个以准确性和效率改善传输指标的问题,彼此之间的权衡,例如提高准确性会降低效率。本文表明,机器学习可用于分析复杂的健康数据指标,例如数据传输的准确性和效率,以使用Levenberg-Marquardt算法来克服权衡问题,从而增强这两个指标,从而通过少较少的样本来传输,同时保持维护准确性。使用标准心率数据集测试该算法以比较指标。结果表明,LMA最好以3.33倍的效率进行样本数据尺寸和79.17%的精度,在7种不同的采样案例中具有相似的准确性,用于测试,但表明效率提高。与具有高效率的现有方法相比,这些提出的方法使用机器学习可以显着改善两个指标,而无需牺牲其他指标。
translated by 谷歌翻译
分配概括的任务涉及在看不见的环境中对响应的可靠预测。结构性因果模型被证明可用于通过干预模型变化。受基本不变性原则的激励,通常假定响应的条件分布在整个环境之间保持相同。但是,当响应干预时,在实际情况下可能会违反此假设。在这项工作中,我们研究了一类具有中间响应的模型。我们通过将某些特征的估计值合并为其他预测因子来确定一种新型的不变性形式。有效地,我们表明这种不变性等同于具有使概括成为可能的确定性线性匹配。我们提供了线性匹配的明确表征,并在各种干预设置下介绍了我们的仿真结果。
translated by 谷歌翻译
预测组合在预测社区中蓬勃发展,近年来,已经成为预测研究和活动主流的一部分。现在,由单个(目标)系列产生的多个预测组合通过整合来自不同来源收集的信息,从而提高准确性,从而减轻了识别单个“最佳”预测的风险。组合方案已从没有估计的简单组合方法演变为涉及时间变化的权重,非线性组合,组件之间的相关性和交叉学习的复杂方法。它们包括结合点预测和结合概率预测。本文提供了有关预测组合的广泛文献的最新评论,并参考可用的开源软件实施。我们讨论了各种方法的潜在和局限性,并突出了这些思想如何随着时间的推移而发展。还调查了有关预测组合实用性的一些重要问题。最后,我们以当前的研究差距和未来研究的潜在见解得出结论。
translated by 谷歌翻译
在生物医学自然语言处理中,命名实体识别(NER)和命名实体归一化(NEN)是能够从不断增长的生物医学文献中自动提取生物医学实体(例如,疾病和化学品)的关键任务。在本文中,我们展示了伯尔尼(高级生物医学实体识别和归一化),这是一种改善以前的基于神经网络的NER工具的工具(Kim等,2019),采用多任务NER模型和基于神经网络的NEN模型实现更快,更准确的推理。我们希望我们的工具可以帮助为各种任务等诸如生物医学知识图形建设等各种任务来诠释大规模生物医学文本。
translated by 谷歌翻译