尽管在现代深度神经网络(DNN)中的解释技术取得了快速的进步,其中主要重点是处理“如何产生解释”,但先进的研究问题,这些问题研究了解释本身的质量(例如,解释是否准确” )并提高解释质量(例如,“如何调整模型以在解释不准确时生成更准确的解释”)仍然相对较小。为了指导该模型朝着更好的解释,解释监督的技术(在模型解释中增加了监督信号)已开始对提高深度神经网络的普遍性和内在解释性的影响显示出令人鼓舞的影响。然而,由于几个固有的挑战,有关监督解释的研究,特别是在通过显着图代表的基于视觉的应用中,正处于早期阶段:1)人类解释注释边界的不准确,2)人类解释注释区域的不完整, 3)人类注释和模型解释图之间的数据分布不一致。为了应对挑战,我们提出了一个通用的RES框架,用于通过开发一个新的目标来指导视觉解释,该目标可以处理人类注释不准确的边界,不完整的区域和不一致的分布,并具有对模型通用性的理论理由。在两个现实世界图像数据集上进行的广泛实验证明了该框架在增强解释的合理性和骨干DNNS模型的性能方面的有效性。
translated by 谷歌翻译
语言模型既展示了定量的改进,又展示了新的定性功能,随着规模的增加。尽管它们具有潜在的变革性影响,但这些新能力的特征却很差。为了为未来的研究提供信息,为破坏性的新模型能力做准备,并改善社会有害的效果,至关重要的是,我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战,我们介绍了超越模仿游戏基准(Big Bench)。 Big Bench目前由204个任务组成,由132家机构的442位作者贡献。任务主题是多样的,从语言学,儿童发展,数学,常识性推理,生物学,物理学,社会偏见,软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号,Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为,跨越了数百万到数十亿个参数。此外,一个人类专家评估者团队执行了所有任务,以提供强大的基准。研究结果包括:模型性能和校准都随规模改善,但绝对的术语(以及与评估者的性能相比);在模型类中的性能非常相似,尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分,而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标;社交偏见通常会随着含糊不清的环境而随着规模而增加,但这可以通过提示来改善。
translated by 谷歌翻译
This paper presents an approach that reconstructs a hand-held object from a monocular video. In contrast to many recent methods that directly predict object geometry by a trained network, the proposed approach does not require any learned prior about the object and is able to recover more accurate and detailed object geometry. The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker. Then, the object geometry can be recovered by solving a multi-view reconstruction problem. We devise an implicit neural representation-based method to solve the reconstruction problem and address the issues of imprecise hand pose estimation, relative hand-object motion, and insufficient geometry optimization for small objects. We also provide a newly collected dataset with 3D ground truth to validate the proposed approach.
translated by 谷歌翻译
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g., regions such as paragraphs or figures), to coarse granularity (e.g., the whole page). The spatial hierarchical relationships between content at different levels of granularity are crucial for document image understanding tasks. Existing methods learn features from either word-level or region-level but fail to consider both simultaneously. Word-level models are restricted by the fact that they originate from pure-text language models, which only encode the word-level context. In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features. To deal with these issues, we propose MGDoc, a new multi-modal multi-granular pre-training framework that encodes page-level, region-level, and word-level information at the same time. MGDoc uses a unified text-visual encoder to obtain multi-modal features across different granularities, which makes it possible to project the multi-granular features into the same hyperspace. To model the region-word correlation, we design a cross-granular attention mechanism and specific pre-training tasks for our model to reinforce the model of learning the hierarchy between regions and words. Experiments demonstrate that our proposed model can learn better features that perform well across granularities and lead to improvements in downstream tasks.
translated by 谷歌翻译
AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making. Moreover, many settings are dynamic, with populations responding to sequential decision policies. We introduce the study of reinforcement learning (RL) with stepwise fairness constraints, requiring group fairness at each time step. Our focus is on tabular episodic RL, and we provide learning algorithms with strong theoretical guarantees in regard to policy optimality and fairness violation. Our framework provides useful tools to study the impact of fairness constraints in sequential settings and brings up new challenges in RL.
translated by 谷歌翻译
In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models (NLMs). To preserve UeDP, we developed a novel algorithm, called UeDP-Alg, optimizing the trade-off between privacy loss and model utility with a tight sensitivity bound derived from seamlessly combining user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.
translated by 谷歌翻译
从3D点云中识别3D零件实例对于3D结构和场景理解至关重要。几种基于学习的方法使用语义细分和实例中心预测作为培训任务,并且无法进一步利用形状语义和部分实例之间的固有关系。在本文中,我们提出了一种用于3D份实例分割的新方法。我们的方法将语义分割利用为融合非本地实例特征(例如中心预测),并以多种和跨层次的方式进一步增强了融合方案。我们还提出了一个语义区域中心预测任务,以训练和利用预测结果来改善实例点的聚类。我们的方法优于现有方法,在Partnet基准测试方面有大幅度的改进。我们还证明,我们的功能融合方案可以应用于其他现有方法,以提高其在室内场景实例细分任务中的性能。
translated by 谷歌翻译
及时调整是将预训练的语言模型调整为下游任务的一种新兴方法。但是,现有的研究主要是为输入序列增加提示。由于中间多头自我注意和馈送网络计算,因此这种方式无法正常工作,从而使模型优化不是很好。因此,我们提出了一种称为“图层调整”的新颖调整方式,旨在在变压器层中添加可学习的参数。具体而言,我们专注于变压器中的馈电网络的图层调整,即FLANing。它将其他单元引入每个馈送网络的隐藏层。我们对公共线索基准进行了广泛的实验。结果表明:1)在几乎所有情况下,我们的FL-tuning tospormports促进了全数据和少量设置下的调整方法。特别是,它在WSC 1.0上的准确性提高了17.93%(全数据设置),而F1上的精度则提高了P-Tuning V2上的Cluener上的精度(几乎没有射击设置)。 2)我们的FL-调整更稳定,收敛速度比P-Tuning V2快约1.17倍。 3)只有大约3%的变压器参数要训练,因此在大多数数据集中进行了微调,并且在几个数据集上的微调(例如,WSC 1.1上的准确性提高了12.9%)。源代码可从https://github.com/genggui001/fl-tuning获得。
translated by 谷歌翻译
我们与中国的援助卫生委员会合作,我们提出了一个预测系统,以根据免疫后不良事件的数据来预测患有不良反应的儿童的住院。我们从数据中提取了多个功能,并选择“住院或不选择”作为分类目标。由于数据是不平衡的,因此我们使用了各种班级不平衡学习方法来培训并改善了Rusboost算法。实验结果表明,在这些算法中,ROC曲线在ROC曲线下的最高面积是最高的。此外,我们将这些平衡的学习方法与一些常见的机器学习算法进行了比较。我们将改进的Rusboost与动态Web资源开发技术结合在一起,以构建一个评估系统,并为相关医生提供信息输入和疫苗接种响应预测能力。
translated by 谷歌翻译
基于密度的分布(OOD)检测最近显示了检测OOD图像的任务不可靠。基于各种密度比的方法实现了良好的经验性能,但是方法通常缺乏原则性的概率建模解释。在这项工作中,我们建议在建立基于能量的模型并采用不同基础分布的新框架下统一基于密度比的方法。在我们的框架下,密度比可以看作是隐式语义分布的非均衡密度。此外,我们建议通过类比率估计直接估计数据样本的密度比。与最近的工作相比,我们报告了有关OOD图像问题的竞争结果,这些工作需要对任务进行深层生成模型的培训。我们的方法使一个简单而有效的途径可以解决OOD检测问题。
translated by 谷歌翻译