Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs). Most existing methods focus on one or run them parallel (series), neglecting the collaboration between the two attentions. In order to better establish the feature interaction between the two types of attention, we propose a plug-and-play attention module, which we term "CAT"-activating the Collaboration between spatial and channel Attentions based on learned Traits. Specifically, we represent traits as trainable coefficients (i.e., colla-factors) to adaptively combine contributions of different attention modules to fit different image hierarchies and tasks better. Moreover, we propose the global entropy pooling (GEP) apart from global average pooling (GAP) and global maximum pooling (GMP) operators, an effective component in suppressing noise signals by measuring the information disorder of feature maps. We introduce a three-way pooling operation into attention modules and apply the adaptive mechanism to fuse their outcomes. Extensive experiments on MS COCO, Pascal-VOC, Cifar-100, and ImageNet show that our CAT outperforms existing state-of-the-art attention mechanisms in object detection, instance segmentation, and image classification. The model and code will be released soon.
translated by 谷歌翻译
准确的牙齿体积分割是计算机辅助牙齿分析的先决条件。基于深度学习的牙齿分割方法已经达到了令人满意的表现,但需要大量的牙齿数据。公开可用的牙科数据是有限的,这意味着无法在临床实践中复制,评估和应用现有方法。在本文中,我们建立了一个3D Dental CBCT数据集Ctooth+,具有22个完全注释的卷和146个未标记的体积。我们进一步评估了基于完全监督的学习,半监督学习和积极学习的几种最先进的牙齿量细分策略,并定义了绩效原则。这项工作为牙齿体积分割任务提供了新的基准,该实验可以作为未来基于AI的牙科成像研究和临床应用开发的基线。
translated by 谷歌翻译
具有大尺度图像文本对的视觉预训练(VLP)在各个领域都表现出卓越的性能。但是,Internet上的图像文本对共存通常缺乏明确的对齐信息,这对于VLP来说是次优的。建议采用现成的对象检测器来利用其他图像标签信息。但是,对象检测器是耗时的,只能识别预定义的对象类别,从而限制了模型容量。受到观察的启发,即文本包含不完整的细粒图像信息,我们介绍了Ideas,该想法代表通过在线多标签识别VLP来增加文本多样性。想法表明,可以在VLP期间共同优化从文本中提取的图像标签的多标签学习。此外,想法可以在线识别有价值的图像标签,以提供更明确的文本监督。全面的实验表明,想法可以显着提高多个下游数据集上的性能,并具有较小的额外计算成本。
translated by 谷歌翻译
如图1所示,光学特征识别(OCR)技术已在各种场景中广泛使用。设计实用的OCR系统仍然是一项有意义但具有挑战性的任务。在以前的工作中,考虑到效率和准确性,我们提出了实用的超轻型OCR系统(PP-OCR)和优化的版本PP-OCRV2。为了进一步提高PP-OCRV2的性能,本文提出了更强大的OCR系统PP-OCRV3。 PP-OCRV3基于PP-OCRV2的9个方面升级了文本检测模型和文本识别模型。对于文本检测器,我们引入了一个带有大型接收场LK-PAN的锅模块,该模块是一个名为RSE-FPN的剩余注意机制的FPN模块和DML蒸馏策略。对于文本识别器,基本模型将从CRNN替换为SVTR,我们介绍了轻量级文本识别网络SVTR LCNET,通过注意力进行CTC的指导培训,数据增强策略TextConaug,由自我审查的TextRotnet,UDML和UDML和UDML和UDML和更好的预培训模型。 UIM加速模型并改善效果。实际数据上的实验表明,在可比的推理速度下,PP-OCRV3的Hmean比PP-OCRV2高5%。上述所有上述型号都是开源的,并且代码可在由PaddlePaddle供电的GitHub存储库Paddleocr中可用。
translated by 谷歌翻译
知识图嵌入(KGE)的有效性在很大程度上取决于建模固有关系模式和映射属性的能力。但是,现有方法只能以不足的建模能力捕获其中的一些。在这项工作中,我们提出了一个名为House的更强大的KGE框架,该框架涉及基于两种家庭转换的新型参数化:(1)住户旋转以实现建模关系模式的较高能力;(2)处理复杂关系映射属性的住户预测。从理论上讲,房屋能够同时建模关键的关系模式和映射属性。此外,房屋是对现有基于旋转的模型的概括,同时将旋转扩展到高维空间。从经验上讲,House在五个基准数据集上实现了新的最新性能。我们的代码可在https://github.com/anrep/house上找到。
translated by 谷歌翻译
双链DNA断裂(DSB)是一种DNA损伤的形式,可导致异常染色体重排。基于高吞吐量实验的最近技术具有明显的高成本和技术挑战。因此,我们设计了一种基于图形的神经网络的方法来预测DSB(GraphDSB),使用DNA序列特征和染色体结构信息。为了提高模型的表达能力,我们引入跳跃知识架构和几种有效的结构编码方法。结构信息对DSB预测的贡献是通过来自正常人体表皮角蛋白细胞(NHEK)和慢性髓性白血病细胞系(K562)的数据集的实验验证,并且消融研究进一步证明了所提出的设计部件的有效性GraphDSB框架。最后,我们使用GNNExplainer分析节点特征和拓扑到DSB预测的贡献,并证明了5-MER DNA序列特征和两种染色质相互作用模式的高贡献。
translated by 谷歌翻译
基于Xornet的低功耗控制器是一种流行的技术,可以减少基于扫描的测试中的电路过渡。然而,现有解决方案构造Xordet均匀用于扫描链控制,并且可能导致次优溶液而没有任何设计指导。在本文中,我们提出了一种具有进化学习的新型可测试性感知的低功率控制器。从所提出的遗传算法(GA)产生的XorNET可以根据其使用,使扫描链的自适应控制能够显着提高XorNET编码容量,从而减少了ATPG的故障情况的数量和降低测试数据量。实验结果表明,在相同的控制比特下,我们的GA引导的Xornet设计可以将故障覆盖率提高至2.11%。所提出的GA引导的XorNET还允许降低控制比特的数量,并且总测试时间平均降低20.78%,与现有设计相比,在不牺牲测试覆盖的情况下相比,相比,高达47.09%。
translated by 谷歌翻译
互联网公司越来越多地使用机器学习模型来创建分配每个人的个性化政策,为每个人提供最佳预测的待遇。它们通常来自黑盒异质处理效果(HTE)模型,预测单个治疗效果。在本文中,我们专注于(1)HTE模型的学习解释;(2)学习规定待遇任务的可解释政策。我们还提出了指导树木,这一方法可以在没有解释性丧失的情况下集合多种可意识到的政策。这些基于规则的可解释策略很容易部署,避免需要在生产环境中维护HTE模型。
translated by 谷歌翻译
With the development of natural language processing techniques(NLP), automatic diagnosis of eye diseases using ophthalmology electronic medical records (OEMR) has become possible. It aims to evaluate the condition of both eyes of a patient respectively, and we formulate it as a particular multi-label classification task in this paper. Although there are a few related studies in other diseases, automatic diagnosis of eye diseases exhibits unique characteristics. First, descriptions of both eyes are mixed up in OEMR documents, with both free text and templated asymptomatic descriptions, resulting in sparsity and clutter of information. Second, OEMR documents contain multiple parts of descriptions and have long document lengths. Third, it is critical to provide explainability to the disease diagnosis model. To overcome those challenges, we present an effective automatic eye disease diagnosis framework, NEEDED. In this framework, a preprocessing module is integrated to improve the density and quality of information. Then, we design a hierarchical transformer structure for learning the contextualized representations of each sentence in the OEMR document. For the diagnosis part, we propose an attention-based predictor that enables traceable diagnosis by obtaining disease-specific information. Experiments on the real dataset and comparison with several baseline models show the advantage and explainability of our framework.
translated by 谷歌翻译
Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking statements that are irrelevant or factually incorrect. To address this problem, we propose a contrastive learning scheme, named MixCL. A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs, and thus reduce their hallucination in conversations. We also examine negative sampling strategies of retrieved hard negatives and model-generated negatives. We conduct experiments on Wizard-of-Wikipedia, a public, open-domain knowledge-grounded dialogue benchmark, and assess the effectiveness of MixCL. MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality. We show that MixCL achieves comparable performance to state-of-the-art KB-based approaches while enjoying notable advantages in terms of efficiency and scalability.
translated by 谷歌翻译