To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers $13$ common text generation tasks and their corresponding $83$ datasets and further incorporates $45$ PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement $4$ efficient training strategies and provide $4$ generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: https://github.com/RUCAIBox/TextBox.
translated by 谷歌翻译
The modern dynamic and heterogeneous network brings differential environments with respective state transition probability to agents, which leads to the local strategy trap problem of traditional federated reinforcement learning (FRL) based network optimization algorithm. To solve this problem, we propose a novel Differentiated Federated Reinforcement Learning (DFRL), which evolves the global policy model integration and local inference with the global policy model in traditional FRL to a collaborative learning process with parallel global trends learning and differential local policy model learning. In the DFRL, the local policy learning model is adaptively updated with the global trends model and local environment and achieves better differentiated adaptation. We evaluate the outperformance of the proposal compared with the state-of-the-art FRL in a classical CartPole game with heterogeneous environments. Furthermore, we implement the proposal in the heterogeneous Space-air-ground Integrated Network (SAGIN) for the classical traffic offloading problem in network. The simulation result shows that the proposal shows better global performance and fairness than baselines in terms of throughput, delay, and packet drop rate.
translated by 谷歌翻译
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units like microcontrollers. ML operators exhibit heterogeneous efficiency profiles on power-efficient hardware. Given the exact theoretical computation cost, int8 operators are more computation-effective than float operators, and linear layers are often more efficient than other layers. The proposed LiCo-Net is a dual-phase system that uses the efficient int8 linear operators at the inference phase and applies streaming convolutions at the training phase to maintain a high model capacity. The experimental results show that LiCo-Net outperforms single-value decomposition filter (SVDF) on hardware efficiency with on-par detection performance. Compared to SVDF, LiCo-Net reduces cycles by 40% on HiFi4 DSP.
translated by 谷歌翻译
2D低剂量单板腹部计算机断层扫描(CT)切片可直接测量身体成分,这对于对衰老的健康关系进行定量表征至关重要。然而,由于不同年内获得的纵向切片之间的位置方差,使用2D腹部切片对人体成分变化的纵向分析具有挑战性。为了减少位置差异,我们将条件生成模型扩展到我们的C-斜肌,该模型在腹部区域进行任意轴向切片作为条件,并通过估计潜在空间的结构变化来生成定义的椎骨水平切片。对来自内部数据集的1170名受试者的实验和BTCV Miccai挑战赛的50名受试者的实验表明,我们的模型可以从现实主义和相似性方面产生高质量的图像。来自巴尔的摩纵向研究(BLSA)数据集的20名受试者的外部实验,其中包含纵向单腹部切片验证了我们的方法可以在肌肉和内脏脂肪面积方面与切片的位置方差进行协调。我们的方法提供了一个有希望的方向,将切片从不同的椎骨水平映射到目标切片,以减少单个切片纵向分析的位置差异。源代码可在以下网址获得:https://github.com/masilab/c-slicegen。
translated by 谷歌翻译
Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realize global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissues structures. Inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting anatomies of 133 structures in brain, 14 organs in abdomen, 4 hierarchical components in kidney, and inter-connected kidney tumors). We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in single network, outperforms prior state-of-the-art method SLANT27 ensembled with 27 network tiles, our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively.
translated by 谷歌翻译
从心脏病学到神经病学的疾病中,代谢健康越来越多地成为危险因素,身体成分的效率评估对于定量表征这些关系至关重要。 2D低剂量单切层扫描术(CT)提供了高分辨率,定量组织图,尽管视野有限。尽管在量化图像上下文时已经提出了许多潜在的分析,但尚无对低剂量单切片CT纵向变异性进行自动分割的全面研究。我们使用受监督的基于深度学习的细分和无监督的聚类方法研究了1469个巴尔的摩纵向研究(BLSA)腹部数据集的1469名纵向研究(BLSA)腹部数据集的1816片。在前两次扫描中有两年差距的1469名受试者中有300名被选出,以评估纵向变异性,其中包括类内相关系数(ICC)和变异系数(CV),以组织/器官的大小和平均强度为单位。我们表明,我们的分割方法在纵向环境中是稳定的,骰子范围为13个目标腹部组织结构的0.821至0.962。我们观察到ICC <0.5的大多数器官的较高变异性,肌肉,腹壁,脂肪和体膜的变化较低,平均ICC> 0.8。我们发现器官的变异性与2D切片的横截面位置高度相关。我们的努力铺平了定量探索和质量控制,以减少纵向分析中的不确定性。
translated by 谷歌翻译
立体声匹配是许多视觉和机器人应用程序的基本构建块。信息性和简洁的成本量表示对于高准确性和效率的立体声匹配至关重要。在本文中,我们提出了一种新颖的成本量构建方法,称为“注意串联量”(ACV),该方法从相关线索中产生了注意力权重,以抑制冗余信息并增强串联体积中与匹配相关的信息。 ACV可以无缝嵌入大多数立体声匹配网络中,所得网络可以使用更轻巧的聚合网络,同时获得更高的精度。我们进一步设计了快速版本的ACV版本以实现实时性能,名为FAST-ACV,它产生了很高的可能性差异假设,以及来自低分辨率相关线索的相应注意力权重,可显着降低计算和记忆成本,同时保持令人满意的精度。我们快速ACV的核心思想是音量注意传播(VAP),它可以自动从上采样相关量中选择准确的相关值,并将这些准确的值传播到周围环境像素具有模棱两可的相关线索。此外,我们分别基于我们的ACV和Fast-ACV设计了高度准确的网络ACVNET和实时网络快速ACVNET,该网络在几个基准上实现了最新性能(即,我们的ACVNET排名第二,第二名在Kitti 2015和场景流以及所有已发布方法中的Kitti 2012和Eth3d的第三次;我们的快速ACVNET几乎优于现场流的所有最新实时方法,Kitti 2012和2015年,与此同时,与此同时更好的概括能力)
translated by 谷歌翻译
解决组合优化(CO)问题的传统求解器通常是由人类专家设计的。最近,人们对利用深度学习,尤其是深度强化学习的兴趣激增,自动为CO学习有效的求解器。由此产生的新范式称为神经组合优化(NCO)。但是,在经验或理论上,NCO的优势和缺点与其他方法的优势尚未得到很好的研究。在这项工作中,我们介绍了NCO求解器和替代求解器的全面比较研究。具体而言,将旅行推销员问题作为测试床问题,我们根据五个方面(即有效性,效率,稳定性,可扩展性和概括能力)评估求解器的性能。我们的结果表明,通常,NCO方法学到的求解器几乎在所有这些方面仍然没有传统求解器。前者的潜在好处将是在有足够的培训实例时,他们在小规模的问题实例上的卓越时间和能源效率。我们希望这项工作将有助于更好地理解NCO的优势和劣势,并提供全面的评估协议,以进一步对NCO进行针对其他方法的基准测试。
translated by 谷歌翻译
顺序面部图像编辑中存在三个问题:不连续的编辑,不一致的编辑和不可逆转的编辑。不连续的编辑是当前的编辑无法保留先前编辑的属性。不一致的编辑是交换属性编辑订单不能产生相同的结果。不可逆转的编辑意味着在面部图像上操作是不可逆的,尤其是在顺序的面部图像编辑中。在这项工作中,我们提出了三个概念和相应的定义:编辑连续性,一致性和可逆性。然后,我们提出了一个新型模型,以实现编辑连续性,一致性和可逆性的目标。定义了足够的标准以确定模型是否是连续,一致和可逆的。广泛的定性和定量实验结果验证了我们提出的模型,并表明连续,一致和可逆的编辑模型具有更灵活的编辑功能,同时保留面部身份。此外,我们认为我们提出的定义和模型将在多媒体处理中具有广泛而有希望的应用。代码和数据可在https://github.com/mickoluan/ccr上找到。
translated by 谷歌翻译
在过去的几年中,用于计算机视觉的深度学习技术的快速发展极大地促进了医学图像细分的性能(Mediseg)。但是,最近的梅赛格出版物通常集中于主要贡献的演示(例如,网络体系结构,培训策略和损失功能),同时不知不觉地忽略了一些边缘实施细节(也称为“技巧”),导致了潜在的问题,导致了潜在的问题。不公平的实验结果比较。在本文中,我们为不同的模型实施阶段(即,预培训模型,数据预处理,数据增强,模型实施,模型推断和结果后处理)收集了一系列Mediseg技巧,并在实验中探索了有效性这些技巧在一致的基线模型上。与仅关注分割模型的优点和限制分析的纸驱动调查相比,我们的工作提供了大量的可靠实验,并且在技术上更可操作。通过对代表性2D和3D医疗图像数据集的广泛实验结果,我们明确阐明了这些技巧的效果。此外,根据调查的技巧,我们还开源了一个强大的梅德西格存储库,其每个组件都具有插件的优势。我们认为,这项里程碑的工作不仅完成了对最先进的Mediseg方法的全面和互补的调查,而且还提供了解决未来医学图像处理挑战的实用指南,包括但不限于小型数据集学习,课程不平衡学习,多模式学习和领域适应。该代码已在以下网址发布:https://github.com/hust-linyi/mediseg
translated by 谷歌翻译