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
Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization.
translated by 谷歌翻译
Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training which distributes the workload of training across multiple computing nodes. However, the workflows, computational patterns, communication patterns, and optimization techniques of distributed GNN training remain preliminarily understood. In this paper, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks, emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed.
translated by 谷歌翻译
基于多模式方面的情感分类(MABSC)是一项新兴的分类任务,旨在将给定目标的情感分类,例如具有不同模式的数据中提到的实体。在带有文本和图像的典型多模式数据中,以前的方法不能充分利用图像的细颗粒语义,尤其是与文本的语义结合在一起,并且不完全考虑对细粒图像之间的关系进行建模信息和目标,这导致图像的使用不足和不足以识别细粒度的方面和意见。为了应对这些局限性,我们提出了一个新的框架SEQCSG,包括一种构建顺序跨模式语义图和编码器模型的方法。具体而言,我们从原始图像,图像标题和场景图中提取细粒度的信息,并将它们视为跨模式语义图的元素以及文本的令牌。跨模式语义图表示为具有多模式可见矩阵的序列,指示元素之间的关系。为了有效地利用跨模式语义图,我们建议使用目标提示模板的编码器解码器方法。实验结果表明,我们的方法优于现有方法,并在两个标准数据集MABSC上实现了最新方法。进一步的分析证明了每个组件的有效性,我们的模型可以隐含地学习图像的目标和细粒度信息之间的相关性。
translated by 谷歌翻译
手语制作(SLP)旨在将口语语言自动转化为符号序列。 SLP的核心过程是将符号光泽序列转换为其相应的标志姿势序列(G2P)。大多数现有的G2P模型通常以自回归方式执行这种条件的远程生成,这不可避免地导致错误的积累。为了解决这个问题,我们提出了一种量化量子序列序列的生成的矢量量化扩散方法,称为poseVQ扩散,这是一种迭代性非自动入学方法。具体而言,我们首先引入量化量化变量自动编码器(姿势VQVAE)模型,以表示姿势序列作为一系列潜在代码。然后,我们通过最近开发的扩散体系结构的扩展来对潜在离散空间进行建模。为了更好地利用时空信息,我们介绍了一种新颖的体系结构,即CodeUnet,以在离散空间中生成更高质量的姿势序列。此外,利用学习的代码,我们开发了一种新型的顺序k-nearest-neighbours方法,以预测相应的光泽序列的姿势序列的可变长度。因此,与自回旋G2P模型相比,我们的模型具有更快的采样速度,并产生明显更好的结果。与以前的非自动入学G2P方法相比,PoseVQ扩散通过迭代改进改善了预测的结果,从而在SLP评估基准上获得了最新的结果。
translated by 谷歌翻译
自适应梯度算法借用重球加速度的移动平均思想,以估计梯度的准确梯度矩和二阶矩,以加速收敛。然而,在理论上,在理论上,在许多经验情况下,在自适应梯度环境下,Nesterov加速度比重球加速度快的速度快得多。在这项工作中,我们提出了Adan的自适应Nesterov动量算法,以有效加快深层神经网络的训练。 Adan首先重新制定了Nesterov加速度,以开发新的Nesterov动量估计(NME)方法,该方法避免了外推点上计算梯度的额外计算和内存开销。然后,Adan采用NME来估计自适应梯度算法中梯度的一阶和二阶时刻,以进行收敛加速。此外,我们证明Adan在$ O(\ epsilon^{ - 3.5})内找到了$ \ epsilon $ - 附近的一阶固定点,$最著名的下限。广泛的实验结果表明,Adan超过了视觉变压器(VIT)和CNN上的相应SOTA优化器,并为许多流行网络设置了新的SOTA,例如Resnet,Convnext,Vit,Vit,Swin,Mae,Mae,LSTM,LSTM,Transformer-XL和BERT,以及BERT和BERT和BERT 。更令人惊讶的是,Adan可以利用SOTA优化器的一半培训成本(时代)在E.T.C. Vit和Resnet上获得更高或可比的性能,并且还显示出对大型Minibatch尺寸的宽容,例如1K到32K。我们希望Adan能够通过降低培训成本并减轻尝试各种架构的不同优化者的工程负担来为深度学习的发展做出贡献。代码将在https://github.com/sail-sg/adan上发布。
translated by 谷歌翻译
神经体系结构搜索方法寻求具有有效的体重共享超级网训练的最佳候选者。但是,最近的研究表明,关于独立架构和共享重量网络之间的性能的排名一致性差。在本文中,我们提出了提前引导的一声NAS(PGONA),以加强超级网的排名相关性。具体而言,我们首先探讨激活功能的效果,并提出基于三明治规则的平衡采样策略,以减轻超级网中的重量耦合。然后,采用了拖鞋和禅宗得分来指导超级网的训练,并具有排名相关性损失。我们的PGONA在CVPR2022第二轻型NAS挑战赛的SuperNet轨道中排名第三。代码可在https://github.com/pprp/cvpr2022-nas?competition-track1-3th-solution中找到。
translated by 谷歌翻译
最近,我们提供了Wenet,这是一种面向生产的端到端语音识别工具包,它引入了统一的两通道(U2)框架和内置运行时,以解决单个中的流和非流传输模式。模型。为了进一步提高ASR性能并促进各种生产要求,在本文中,我们提出了Wenet 2.0,并提供四个重要的更新。 (1)我们提出了U2 ++,这是一个带有双向注意解码器的统一的两次通行框架,其中包括通过左右注意力解码器的未来上下文信息,以提高共享编码器的代表性和在夺回阶段的表现。 (2)我们将基于N-Gram的语言模型和基于WFST的解码器引入WENET 2.0,从而促进了在生产方案中使用丰富的文本数据。 (3)我们设计了一个统一的上下文偏见框架,该框架利用特定于用户的上下文(例如联系人列表)为生产提供快速适应能力,并提高了使用LM和没有LM场景的ASR准确性。 (4)我们设计了一个统一的IO,以支持大规模数据进行有效的模型培训。总而言之,全新的WENET 2.0可在各种Corpora上的原始WENET上取得高达10 \%的相对识别性能提高,并提供了一些重要的以生产为导向的功能。
translated by 谷歌翻译
最近,基于障碍函数的安全强化学习(RL)与actor-批评结构用于连续控制任务的批评结构已经受到越来越受到关注。使用安全性和收敛保证,学习近最优控制政策仍然挑战。此外,很少有效地解决了在时变的安全约束下的安全RL算法设计。本文提出了一种基于模型的安全RL算法,用于具有时变状态和控制约束的非线性系统的最佳控制。在拟议的方法中,我们构建了一种新的基于障碍的控制策略结构,可以保证控制安全性。提出了一种多步骤策略评估机制,以预测策略在时变的安全限制下的安全风险,并指导政策安全更新。证明了稳定性和稳健性的理论结果。此外,分析了演员 - 评论家学习算法的收敛。所提出的算法的性能优于模拟安全健身房环境中的几种最先进的RL算法。此外,该方法适用于两个现实世界智能车辆的综合路径和碰撞避免问题。差动驱动车辆和Ackermann-Drive分别用于验证离线部署性能和在线学习性能。我们的方法在实验中显示了令人印象深刻的SIM-to-Real的转移能力和令人满意的在线控制性能。
translated by 谷歌翻译
能量收集(EH)间歇性地运行的IOT设备,与深神经网络(DNN)的进步相结合,为实现可持续智能应用开辟了新的机会。然而,由于有限的资源和间歇电源导致频繁故障的挑战,实现了EH设备上的那些计算和内存密集型智能算法非常困难。为了解决这些挑战,本文提出了一种方法,使得具有用于微小能量收集装置的低能量加速器的超快速深度学习。我们首先提出了一种资源感知结构化DNN训练框架,它采用块循环矩阵与ADMM实现高压缩和模型量化,以利用各种矢量操作加速器的优点。然后提出了一种DNN实现方法,即采用低能量加速器来利用具有较小能耗的最大性能的低能量加速器。最后,我们进一步设计Flex,系统支持在能量收集情况下间歇性计算。来自三种不同DNN模型的实验结果表明RAD,ACE和FLEX可以对能源收集设备进行超快速和正确的推断,该设备可降低高达4.26倍的运行时间,高达7.7倍的能量降低,高精度在最高的状态下艺术。
translated by 谷歌翻译