虽然深度学习方法近年来取得了高级视频对象识别性能,但在视频中感知封闭对象仍然是一个非常具有挑战性的任务。为促进遮挡理解的发展,我们在遮挡方案中收集一个名为OVIS的大规模数据集,用于遮挡方案中的视频实例分段。 ovis由296K高质量的屏幕和901个遮挡场景组成。虽然我们的人类视觉系统可以通过语境推理和关联来感知那些遮挡物体,但我们的实验表明当前的视频了解系统不能。在ovis数据集上,所有基线方法都遇到了大约80%的大约80%的大约80%,这表明仍然有很长的路要走在复杂的真实情景中理解模糊物体和视频。为了促进对视频理解系统的新范式研究,我们基于OVI数据集启动了挑战。提交的顶级执行算法已经比我们的基线实现了更高的性能。在本文中,我们将介绍OVIS数据集,并通过分析基线的结果和提交的方法来进一步剖析。可以在http://songbai.site/ovis找到ovis数据集和挑战信息。
translated by 谷歌翻译
我们的视频是否可以在场景中存在沉重的遮挡时感知对象?为了回答这个问题,我们收集一个名为OVIS的大型数据集,用于遮挡视频实例分段,即同时检测,段和跟踪遮挡场景中的实例。 OVIS由25个语义类别的296K高质量的掩码组成,通常发生对象遮挡。虽然我们的人类视觉系统可以通过语境推理和关联来理解那些被遮挡的情况,但我们的实验表明当前的视频理解系统不能。在ovis数据集上,最先进的算法实现的最高AP仅为16.3,这揭示了我们仍然处于创建对象,实例和视频中的新生阶段。我们还提出了一个简单的即插即用模块,执行时间特征校准,以补充闭塞引起的缺失对象线索。基于MaskTrack R-CNN和SIPMASK构建,我们在OVIS数据集中获得了显着的AP改进。 ovis数据集和项目代码可在http://songbai.site/ovis获得。
translated by 谷歌翻译
Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning.
translated by 谷歌翻译
Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent years to overcome the adversarial attacks. In this paper, we propose a multi-head uncertainty inference (MH-UI) framework for detecting adversarial attack examples. We adopt a multi-head architecture with multiple prediction heads (i.e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI. Using independent heads at different depths, the normalized predictions are assumed to follow the same Dirichlet distribution, and we estimate distribution parameter of it by moment matching. Cognitive uncertainty brought by the adversarial attacks will be reflected and amplified on the distribution. Experimental results show that the proposed MH-UI framework can outperform all the referred UI methods in the adversarial attack detection task with different settings.
translated by 谷歌翻译
预审前的语言模型已被证明在许多与软件有关的一代任务中都是有效的。但是,它们不适合编辑任务,因为它们不是为了推理编辑的原因。为了解决这个问题,我们提出了一个新颖的预处理目标,该目标明确地对编辑进行了建模并使用它来构建Coditt5,这是一种用于软件相关编辑任务的大型语言模型,该任务是在大量源代码和自然语言评论中鉴定的。我们将其对各种下游编辑任务进行微调,包括评论更新,错误修复和自动代码审核。通过优于基于纯生成的模型,我们证明了方法的普遍性及其对编辑任务的适用性。我们还展示了纯生成模型和我们的基于编辑的模型如何通过简单的重读策略相互补充,我们可以通过该策略实现三个下游编辑任务的最新性能。
translated by 谷歌翻译
最近,社区对模型缩放的关注越来越多,并有助于开发具有广泛尺度的模型家族。当前的方法要么简单地采用单发NAS的方式来构建非结构性和不可缩放的模型家族,要么依靠手动固定的缩放策略来扩展不必要的最佳基础模型。在本文中,我们桥接了两个组件,并将Scalenet提出到共同搜索基础模型和缩放策略,以便缩放大型模型可以具有更有希望的性能。具体来说,我们设计了一个超级植物,以体现具有不同尺寸频谱(例如拖鞋)的模型。然后,可以通过基于马尔可夫链的进化算法与基本模型进行交互学习缩放策略,并概括以开发更大的模型。为了获得一个体面的超级植物,我们设计了一种分层抽样策略,以增强其训练充足并减轻干扰。实验结果表明,我们的缩放网络在各种失败的方面都具有显着的性能优势,但搜索成本至少降低了2.53倍。代码可在https://github.com/luminolx/scalenet上找到。
translated by 谷歌翻译
通过利用预熟gan的潜在空间,已经提出了许多最近的作品来进行面部图像编辑。但是,很少有尝试将它们直接应用于视频,因为1)他们不能保证时间一致性,2)他们的应用受到视频的处理速度的限制,3)他们无法准确编码面部运动和表达的细节。为此,我们提出了一个新颖的网络,将面部视频编码到Stylegan的潜在空间中,以进行语义面部视频操纵。基于视觉变压器,我们的网络重复了潜在向量的高分辨率部分,以实现时间一致性。为了捕捉微妙的面部运动和表情,我们设计了涉及稀疏面部地标和密集的3D脸部网眼的新颖损失。我们已经彻底评估了我们的方法,并成功证明了其对各种面部视频操作的应用。特别是,我们提出了一个新型网络,用于3D坐标系中的姿势/表达控制。定性和定量结果都表明,我们的方法可以显着优于现有的单图方法,同时实现实时(66 fps)速度。
translated by 谷歌翻译
Code review is an integral part of any mature software development process, and identifying the best reviewer for a code change is a well accepted problem within the software engineering community. Selecting a reviewer who lacks expertise and understanding can slow development or result in more defects. To date, most reviewer recommendation systems rely primarily on historical file change and review information; those who changed or reviewed a file in the past are the best positioned to review in the future. We posit that while these approaches are able to identify and suggest qualified reviewers, they may be blind to reviewers who have the needed expertise and have simply never interacted with the changed files before. To address this, we present CORAL, a novel approach to reviewer recommendation that leverages a socio-technical graph built from the rich set of entities (developers, repositories, files, pull requests, work-items, etc.) and their relationships in modern source code management systems. We employ a graph convolutional neural network on this graph and train it on two and a half years of history on 332 repositories. We show that CORAL is able to model the manual history of reviewer selection remarkably well. Further, based on an extensive user study, we demonstrate that this approach identifies relevant and qualified reviewers who traditional reviewer recommenders miss, and that these developers desire to be included in the review process. Finally, we find that "classical" reviewer recommendation systems perform better on smaller (in terms of developers) software projects while CORAL excels on larger projects, suggesting that there is "no one model to rule them all."
translated by 谷歌翻译
图形神经网络(GNN)在学习强大的节点表示中显示了令人信服的性能,这些表现在保留节点属性和图形结构信息的强大节点表示中。然而,许多GNNS在设计有更深的网络结构或手柄大小的图形时遇到有效性和效率的问题。已经提出了几种采样算法来改善和加速GNN的培训,但他们忽略了解GNN性能增益的来源。图表数据中的信息的测量可以帮助采样算法来保持高价值信息,同时消除冗余信息甚至噪声。在本文中,我们提出了一种用于GNN的公制引导(MEGUIDE)子图学习框架。 MEGUIDE采用两种新颖的度量:功能平滑和连接失效距离,以指导子图采样和迷你批次的培训。功能平滑度专为分析节点的特征而才能保留最有价值的信息,而连接失败距离可以测量结构信息以控制子图的大小。我们展示了MEGUIDE在多个数据集上培训各种GNN的有效性和效率。
translated by 谷歌翻译
在过去十年中,深度神经网络在各种任务中取得了令人印象深刻的性能,例如自主驾驶,人脸识别和医学诊断。然而,事先作证表明,深度神经网络通过后门攻击将恶意小隐藏触发器注入模型培训,提高严重的安全威胁。要确定触发的神经元并防止反卧系攻击,我们利用福利价值并开发一种名为福利修剪(Shappruning)的新方法,该方法成功地从数据不足的情况下从模型中攻击(每级甚至没有数据) 。考虑到神经元之间的相互作用,Shappruning鉴定了少数感染的神经元(在所有神经元的1%以下),并在修剪诸如许多感染神经元后保护模型的结构和准确性。为了加速Shappruning,我们进一步提出了丢弃的阈值和$ \ epsilon $ -greedy策略以加速福利估计,使得只有几分钟的时间就可以修复中毒模型。实验证明了与现有方法相比,我们对各种攻击和任务的方法的有效性和鲁棒性。
translated by 谷歌翻译