Font generation is a difficult and time-consuming task, especially in those languages using ideograms that have complicated structures with a large number of characters, such as Chinese. To solve this problem, few-shot font generation and even one-shot font generation have attracted a lot of attention. However, most existing font generation methods may still suffer from (i) large cross-font gap challenge; (ii) subtle cross-font variation problem; and (iii) incorrect generation of complicated characters. In this paper, we propose a novel one-shot font generation method based on a diffusion model, named Diff-Font, which can be stably trained on large datasets. The proposed model aims to generate the entire font library by giving only one sample as the reference. Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character. To our best knowledge, the proposed Diff-Font is the first work that developed diffusion models to handle the font generation task. The well-trained Diff-Font is not only robust to font gap and font variation, but also achieved promising performance on difficult character generation. Compared to previous font generation methods, our model reaches state-of-the-art performance both qualitatively and quantitatively.
translated by 谷歌翻译
Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing, and recommender systems. Even though many approaches have been proposed, how well these approaches balance different tasks on each parameter still remains unclear. In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter. Specifically, we compute the total updates by the exponentially decaying Average of the squared Updates (AU) on a parameter from the corresponding task.Based on this novel metric, we observe that many parameters in existing MTL methods, especially those in the higher shared layers, are still dominated by one or several tasks. The dominance of AU is mainly due to the dominance of accumulative gradients from one or several tasks. Motivated by this, we propose a Task-wise Adaptive learning rate approach, AdaTask in short, to separate the \emph{accumulative gradients} and hence the learning rate of each task for each parameter in adaptive learning rate approaches (e.g., AdaGrad, RMSProp, and Adam). Comprehensive experiments on computer vision and recommender system MTL datasets demonstrate that AdaTask significantly improves the performance of dominated tasks, resulting SOTA average task-wise performance. Analysis on both synthetic and real-world datasets shows AdaTask balance parameters in every shared layer well.
translated by 谷歌翻译
贝叶斯优化(BO)已成为黑框函数的顺序优化。当BO用于优化目标函数时,我们通常可以访问对潜在相关功能的先前评估。这就提出了一个问题,即我们是否可以通过元学习(meta-bo)来利用这些先前的经验来加速当前的BO任务,同时确保稳健性抵抗可能破坏BO融合的潜在有害的不同任务。本文介绍了两种可扩展且可证明的稳健元算法:稳健的元高斯过程 - 加工置信度结合(RM-GP-UCB)和RM-GP-thompson采样(RM-GP-TS)。我们证明,即使某些或所有以前的任务与当前的任务不同,这两种算法在渐近上都是无重组的,并且证明RM-GP-UCB比RM-GP-TS具有更好的理论鲁棒性。我们还利用理论保证,通过通过在线学习最大程度地减少遗憾,优化分配给各个任务的权重,从而减少了相似任务的影响,从而进一步增强了稳健性。经验评估表明,(a)RM-GP-UCB在各种应用程序中都有效,一致地性能,(b)RM-GP-TS,尽管在理论上和实践中都比RM-GP-ucb稳健,但在实践中,在竞争性中表现出色某些方案具有较小的任务,并且在计算上更有效。
translated by 谷歌翻译
深度神经网络(DNN)已经证明了他们在各种域中的表现。但是,它提出了社会问题,如果他们适用于涉及有价值的资源分配的敏感域,如教育,贷款和就业,则会引发社会问题。在DNN可靠地部署到这样的敏感域之前,执行公平性测试至关重要,即,尽可能多地生成以发现公平违规的情况。然而,现有的测试方法仍然有限于三个方面:可解释性,性能和概括性。为了克服挑战,我们提出了一个新的DNN公平测试框架,与以前的工作不同于在几个关键方面的内容:(1)可解释 - 它定量解释DNNS的公平违反偏见决定的公平违规; (2)有效 - 它使用解释结果在更少的时间内引导更多样化的情况; (3)通用 - 它可以处理结构化和非结构化数据。在7个数据集中的广泛评估和相应的DNN展示了神经元的优越性。例如,在结构化数据集上,它会产生更多的实例(〜x5.84)并节省更多时间(平均加速度为534.56%),与最先进的方法相比。此外,还可以利用神经元的情况来改善偏置DNN的公平,这有助于构建更公平和值得信赖的深度学习系统。
translated by 谷歌翻译
虽然深入学习模型取得了前所未有的成功,但他们对逆势袭击的脆弱性引起了越来越关注,特别是在部署安全关键域名时。为了解决挑战,已经提出了鲁棒性改善的许多辩护策略,包括反应性和积极主动。从图像特征空间的角度来看,由于特征的偏移,其中一些人无法达到满足结果。此外,模型学习的功能与分类结果无直接相关。与他们不同,我们考虑基本上从模型内部进行防御方法,并在攻击前后调查神经元行为。我们观察到,通过大大改变为正确标签的神经元大大改变神经元来误导模型。受其激励,我们介绍了神经元影响的概念,进一步将神经元分为前,中间和尾部。基于它,我们提出神经元水平逆扰动(NIP),第一神经元水平反应防御方法对抗对抗攻击。通过强化前神经元并削弱尾部中的弱化,辊隙可以消除几乎所有的对抗扰动,同时仍然保持高良好的精度。此外,它可以通过适应性,尤其是更大的扰动来应对不同的扰动。在三个数据集和六种模型上进行的综合实验表明,NIP优于最先进的基线对抗11个对抗性攻击。我们进一步通过神经元激活和可视化提供可解释的证据,以便更好地理解。
translated by 谷歌翻译
Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors. Code will be released at https://github.com/tiankongzhang/MGA.
translated by 谷歌翻译
我们研究了从连续动作空间到离散动作空间的软参与者批评(SAC)的适应性。我们重新访问香草囊,并在应用于离散设置时对其Q值低估和性能不稳定性问题提供深入的了解。因此,我们建议使用Q-CLIP的熵 - 平均Q学习和双平均Q学习来解决这些问题。对具有离散动作空间(包括Atari游戏和大型MOBA游戏)的典型基准测试的广泛实验显示了我们提出的方法的功效。我们的代码在:https://github.com/coldsummerday/revisiting-discrete-sac。
translated by 谷歌翻译
Active域适应(ADA)查询所选目标样本的标签,以帮助将模型从相关的源域调整为目标域。由于其有希望的表现,标签成本最少,因此最近引起了人们越来越多的关注。然而,现有的ADA方法尚未完全利用查询数据的局部环境,这对ADA很重要,尤其是当域间隙较大时。在本文中,我们提出了一个局部环境感知的活动域适应性(LADA)的新框架,该框架由两个关键模块组成。本地上下文感知的活动选择(LAS)模块选择其类概率预测与邻居不一致的目标样本。局部上下文感知模型适应(LMA)模块完善了具有查询样本及其扩展的邻居的模型,并由上下文保留损失正规化。广泛的实验表明,与现有的主动选择策略相比,LAS选择了更多的信息样本。此外,配备了LMA,整个LADA方法的表现优于各种基准测试的最先进的ADA解决方案。代码可在https://github.com/tsun/lada上找到。
translated by 谷歌翻译
增强对未标记目标数据的模型预测置信度是无监督域适应(UDA)的重要目标。在本文中,我们探讨了关于倒数第二个线性分类层的输入特征的对抗性训练。我们表明,这种策略比以前的作品所使用的对对抗性图像或中间特征的对抗训练更有效,并且与提高预测置信度的目的更加相关。此外,通过在域适应中通常使用激活归一化以减少域间隙,我们得出了两个变体,并系统地分析了归一化对对抗性训练的影响。这在理论上和通过对实际适应任务的经验分析都进行了说明。在标准设置和无源DATA设置下,对流行的UDA基准测试进行了广泛的实验。结果证明了我们的方法可以在以前的艺术中取得最佳分数。
translated by 谷歌翻译
链接预测,推断图形的未发现或潜在链接,被广泛应用于现实世界中。通过促进图表的标记链接作为训练数据,已经研究了许多基于深度学习的链接预测方法,与非深度方法相比,它们具有主导的预测准确性。但是,恶意制作的训练图的威胁将在深层模型中留下特定的后门,因此,当一些特定的示例被馈入模型时,它将做出错误的预测,定义为后门攻击。这是当前文献中忽略的重要方面。在本文中,我们促使后门攻击对链接预测的概念,并提出链接 - 背门以揭示现有链接预测方法的训练漏洞。具体而言,链接 - 贝克门将假节点与目标链接的节点结合在一起,形成触发器。此外,它通过目标模型的梯度信息来优化触发器。因此,在后排数据集中训练的链接预测模型将预测与目标状态触发的链接。在五个基准数据集和五个表现良好的链接预测模型上进行的广泛实验表明,链接 - 贝克门都在白色框(即目标模型参数可用)和黑色框下实现了最新的攻击成功率。框(即目标模型参数不可用)方案。此外,我们在防御性情况下作证了攻击,结果表明,链接 - 背部门仍然可以成功构建对表现良好的链接预测方法的成功攻击。代码和数据可在https://github.com/seaocn/link-backdoor上获得。
translated by 谷歌翻译