Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to its elaborately fabricated contents, making it difficult to obtain large-scale annotations for fake news data. Due to such data scarcity issues, detecting fake news tends to fail and overfit in the supervised setting. Recently, graph neural networks (GNNs) have been adopted to leverage the richer relational information among both labeled and unlabeled instances. Despite their promising results, they are inherently focused on pairwise relations between news, which can limit the expressive power for capturing fake news that spreads in a group-level. For example, detecting fake news can be more effective when we better understand relations between news pieces shared among susceptible users. To address those issues, we propose to leverage a hypergraph to represent group-wise interaction among news, while focusing on important news relations with its dual-level attention mechanism. Experiments based on two benchmark datasets show that our approach yields remarkable performance and maintains the high performance even with a small subset of labeled news data.
translated by 谷歌翻译
Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. However, CCR suffers from two main transitive problems: threshold effect and scene drift. In other words, the causal pairs to be spliced may have a conflicting threshold boundary or scenario. To address these issues, we propose a novel Reliable Causal chain reasoning framework~(ReCo), which introduces exogenous variables to represent the threshold and scene factors of each causal pair within the causal chain, and estimates the threshold and scene contradictions across exogenous variables via structural causal recurrent neural networks~(SRNN). Experiments show that ReCo outperforms a series of strong baselines on both Chinese and English CCR datasets. Moreover, by injecting reliable causal chain knowledge distilled by ReCo, BERT can achieve better performances on four downstream causal-related tasks than BERT models enhanced by other kinds of knowledge.
translated by 谷歌翻译
Semantic Change Detection (SCD) refers to the task of simultaneously extracting the changed areas and the semantic categories (before and after the changes) in Remote Sensing Images (RSIs). This is more meaningful than Binary Change Detection (BCD) since it enables detailed change analysis in the observed areas. Previous works established triple-branch Convolutional Neural Network (CNN) architectures as the paradigm for SCD. However, it remains challenging to exploit semantic information with a limited amount of change samples. In this work, we investigate to jointly consider the spatio-temporal dependencies to improve the accuracy of SCD. First, we propose a SCanFormer (Semantic Change Transformer) to explicitly model the 'from-to' semantic transitions between the bi-temporal RSIs. Then, we introduce a semantic learning scheme to leverage the spatio-temporal constraints, which are coherent to the SCD task, to guide the learning of semantic changes. The resulting network (ScanNet) significantly outperforms the baseline method in terms of both detection of critical semantic changes and semantic consistency in the obtained bi-temporal results. It achieves the SOTA accuracy on two benchmark datasets for the SCD.
translated by 谷歌翻译
由于经过验证的2D检测技术的适用性,大多数当前点云检测器都广泛采用了鸟类视图(BEV)。但是,现有方法通过简单地沿高度尺寸折叠的体素或点特征来获得BEV特征,从而导致3D空间信息的重丢失。为了减轻信息丢失,我们提出了一个基于多级特征降低降低策略的新颖点云检测网络,称为MDRNET。在MDRNET中,空间感知的维度降低(SDR)旨在在体素至BEV特征转换过程中动态关注对象的宝贵部分。此外,提出了多级空间残差(MSR),以融合BEV特征图中的多级空间信息。关于Nuscenes的广泛实验表明,该提出的方法的表现优于最新方法。该代码将在出版时提供。
translated by 谷歌翻译
摄像头捕获的文档图像通常会遭受透视和几何变形的影响。在考虑视觉不良美学和OCR系统性能不断恶化时,纠正它们是很大的价值。最近的基于学习的方法将重点放在精确的文档图像上。但是,这可能不足以克服实际挑战,包括具有大边缘区域或没有边缘的文档图像。由于这种不切实际,用户在遇到大边缘区域时努力进行裁剪。同时,没有边距的脱瓦图像仍然是一个无法克服的问题。据我们所知,仍然没有完整有效的管道来纠正野外文档图像。为了解决这个问题,我们提出了一种称为Marior的新方法(删除边缘和\迭代内容纠正)。马里奥(Marior)遵循一种渐进策略,以粗到精细的方式迭代地改善脱水质量和可读性。具体而言,我们将管道分为两个模块:边缘去除模块(MRM)和迭代内容整流模块(ICRM)。首先,我们预测输入图像的分割面膜以删除边缘,从而获得初步结果。然后,我们通过产生密集的位移流以实现内容感知的整流来进一步完善图像。我们可以适应地确定改进的迭代次数。实验证明了我们方法在公共基准测试方面的最先进性能。资源可在https://github.com/zzzhang-jx/marior上获得,以进行进一步比较。
translated by 谷歌翻译
深层神经网络最近使用具有高平行性的香草卷积层成功地完成了数字化力。但是,现有的深层方法无法生成具有令人满意的蓝色属性的半半来,并且需要复杂的训练方案。在本文中,我们提出了一种基于多代理深钢筋学习的半强化方法,称为Halftoners,该方法学会了共同的政策来生成高质量的半半突。具体而言,我们将每个二进制像素值的决定视为虚拟代理的动作,该策略由低变义的策略梯度培训。此外,蓝噪性特性是通过新颖的各向异性抑制损失函数来实现的。实验表明,我们的半强化方法在保持速度相对较快的同时产生高质量的半身。
translated by 谷歌翻译
由于其在隐私保护,文档修复和文本编辑方面的各种应用,因此删除文本引起了越来越多的关注。它显示出深度神经网络的重大进展。但是,大多数现有方法通常会为复杂的背景产生不一致的结果。为了解决此问题,我们提出了一个上下文引导的文本删除网络,称为CTRNET。 Ctrnet探索了低级结构和高级判别上下文特征,作为指导背景恢复过程的先验知识。我们进一步提出了具有CNNS和Transformer-编码器的局部全球含量建模(LGCM)块,以捕获局部特征并在全球像素之间建立长期关系。最后,我们将LGCM与特征建模和解码的上下文指南合并。在基准数据集,Scut-Enstext和Scut-Syn上进行的实验表明,CTRNET显着胜过现有的最新方法。此外,关于考试论文的定性实验也证明了我们方法的概括能力。代码和补充材料可在https://github.com/lcy0604/ctrnet上获得。
translated by 谷歌翻译
基于学习的多视图立体声(MVS)方法取得了令人印象深刻的进步,并且近年来超越了传统方法。但是,它们的准确性和完整性仍在挣扎。在本文中,我们提出了一种新方法,以增强受对比度学习和功能匹配启发的现有网络的性能。首先,我们提出了一个对比匹配损失(CML),该损失将正确的匹配点视为正样品,将正确的匹配点视为正样本,并将其他点视为阴性样本,并根据特征的相似性计算对比度损失。我们进一步提出了一个加权局灶性损失(WFL),以提高分类能力,从而削弱了根据预测的置信度,在不重要的区域中低信任像素对损失的贡献。在DTU,坦克和寺庙和混合MVS数据集上进行的广泛实验表明,我们的方法可实现最先进的性能,并在基线网络上取得了重大改进。
translated by 谷歌翻译
图形离群值检测是一项具有许多应用程序的新兴但至关重要的机器学习任务。尽管近年来算法扩散,但缺乏标准和统一的绩效评估设置限制了它们在现实世界应用中的进步和使用。为了利用差距,我们(据我们所知)(据我们所知)第一个全面的无监督节点离群值检测基准为unod,并带有以下亮点:(1)评估骨架从经典矩阵分解到最新图形神经的骨架的14个方法网络; (2)在现实世界数据集上使用不同类型的注射异常值和自然异常值对方法性能进行基准测试; (3)通过在不同尺度的合成图上使用运行时和GPU存储器使用算法的效率和可扩展性。基于广泛的实验结果的分析,我们讨论了当前渠道方法的利弊,并指出了多个关键和有希望的未来研究方向。
translated by 谷歌翻译
如今,在人员重新识别(Reid)任务的真实数据面临隐私问题,例如,禁止DataSet Dukemtmc-Reid。因此,收集Reid任务的真实数据变得更难。同时,标签的劳动力成本仍然很高,进一步阻碍了Reid研究的发展。因此,许多方法转向为REID算法生成合成图像作为替代方而不是真实图像。然而,合成和真实图像之间存在不可避免的领域差距。在以前的方法中,生成过程基于虚拟场景,并且无法根据不同的目标实际场景自动更改其合成训练数据。为了处理这个问题,我们提出了一种新颖的目标感知一代管道,以产生称为Tagerson的合成人物图像。具体地,它涉及参数化渲染方法,其中参数是可控的,并且可以根据目标场景调整。在Tagperson中,我们从目标场景中提取信息,并使用它们来控制我们的参数化渲染过程以生成目标感知的合成图像,这将使目标域中的实图像保持较小的间隙。在我们的实验中,我们的目标感知的合成图像可以实现比MSMT17上的广义合成图像更高的性能,即秩1精度的47.5%与40.9%。我们将发布此工具包\脚注{\ noindent代码可用于\ href {https://github.com/tagperson/tagperson-blender} {https://github.com/tagperson/tagperson -brender}}为Reid社区以任何所需味道产生合成图像。
translated by 谷歌翻译