识别密集混乱中的物体准确地对各种机器人操纵任务发挥了重要作用,包括抓握,包装,重新安排等。但是,传统的视觉识别模型通常会因为实例之间的严重阻塞而错过对象,并且由于视觉上的歧义与高对象拥挤的歧义导致了不正确的预测。在本文中,我们提出了一个称为Smart Explorer的交互式探索框架,用于识别密集的杂物中的所有对象。我们的Smart Explorer会与混乱物进行物理互动,以最大程度地提高识别性能,同时最大程度地减少动作数量,在这种情况下,可以通过最佳的准确性效率折衷来有效地减轻误报和负面因素。具体而言,我们首先收集混乱的多视图RGB-D图像,然后重建相应的点云。通过跨视图汇总RGB图像的实例分割,我们获得了杂物的实例云分区,该杂物通过该杂物的存在和每个类的对象数量。生成有效物理互动的推动动作可大大减少由实例分割熵和多视图对象分歧组成的识别不确定性。因此,通过迭代实例预测和物理互动实现了对象识别在密集混乱中的最佳精度效率折衷。广泛的实验表明,我们的Smart Explorer仅使用几个动作获得了有希望的识别精度,这也超过了随机推动的大幅度。
translated by 谷歌翻译
近年来见证了自动扬声器验证(ASV)的非凡发展。但是,先前的作品表明,最新的ASV模型非常容易受到语音欺骗的攻击,而最近提出的高性能欺骗对策(CM)模型仅专注于独立的反欺骗任务,而忽略了该模型随后的发言人验证过程。如何将CM和ASV集成在一起仍然是一个悬而未决的问题。最近发生了欺骗意识的说话者验证(SASV)挑战,即当共同优化CM和ASV子系统时,可以提供更好的性能。在挑战的情况下,参与者提出的集成系统必须同时拒绝冒名顶替者和欺骗目标扬声器的攻击,这些攻击者直觉有效地与可靠,欺骗的ASV系统的期望相匹配。这项工作着重于基于融合的SASV解决方案,并提出了一个多模型融合框架,以利用多个最先进的ASV和CM模型的功能。拟议的框架将SASV-EER从8.75%提高到1.17 \%,与SASV挑战中最佳基线系统相比,相对改善为86%。
translated by 谷歌翻译
人类共享的控制允许人类与AI进行互动和协作,以在复杂的环境中完成控制任务。以前的强化学习(RL)方法试图以目标条件的设计来实现可控制的政策,而付出了重新设计奖励功能和培训范式。受到神经科学方法研究灵长类动物皮层的启发,我们开发了一种简单但有效的基于频率的方法,称为\ textit {策略解剖},以使学习神经控制器的中间表示与代理行为的运动属性相结合。在不修改神经控制器或检验模型的情况下,提出的方法可以将给定的RL训练的政策转换为人际关系政策。我们评估了关于自动驾驶和运动的RL任务的建议方法。实验表明,通过政策解剖在驾驶任务中实现的人类共享控制可以大大改善看不见的交通场景的性能和安全性。随着人类的循环,机器人机器人也表现出多功能的可控运动技能,即使他们只接受了前进的训练。我们的结果表明,通过解释自主代理的学习代表来实施人类共享自治的有希望的方向。演示视频和代码将在https://metadriverse.github.io/policydissect上提供。
translated by 谷歌翻译
视觉变压器在识别和检测等实质性视野任务中显示了很大的视觉表示功率,从而在手动设计更有效的架构方面吸引了快速增长的努力。在本文中,我们建议使用神经架构搜索来自动化此过程,不仅可以搜索架构,还可以搜索搜索空间。中央观点是逐步发展使用权重共享超空网的E-T错误引导的不同搜索维度。此外,我们提供了一般视觉变压器的设计指南,根据空间搜索过程进行广泛的分析,这可以促进对视觉变压器的理解。值得注意的是,搜索空间的搜索模型,名为S3(用于搜索空间的短路),从搜索到的空间实现了卓越的性能,以最近提出的型号,例如在ImageNet上进行评估时的Swin,Deit和Vit。 S3的有效性也在对象检测,语义细分和视觉问题上说明,展示其泛度到下游视觉和视觉语言任务。代码和型号将在https://github.com/microsoft/cream中使用。
translated by 谷歌翻译
一个名为语音处理通用性能基准(Superb)的排行榜,它旨在基准测试各种下游语音任务的共享自我监督学习(SSL)语音模型的性能,并推动了研究用于语音表示学习。 SuperB演示语音SSL上游模型通过仅限最小的调整来提高各种下游任务的性能。由于自我监督学习上游模型的范式,其次是下游任务,在语音界引起更多关注,表征此类范例的对抗性稳健性是高优先级的。在本文中,我们首次尝试在零知识对手和有限知识对手的袭击下调查此类范例的对抗脆弱性。实验结果表明,Superb提出的范例严重易受有限的知识对手的影响,零知识对手产生的攻击是可转移性的。 XAB测试验证了制作的对抗性攻击的难以察觉。
translated by 谷歌翻译
以前的作品表明,自动扬声器验证(ASV)严重易受恶意欺骗攻击,例如重播,合成语音和最近出现的对抗性攻击。巨大的努力致力于捍卫ANV反击重播和合成语音;但是,只有几种方法探讨了对抗对抗攻击。所有现有的解决ASV对抗性攻击方法都需要对对抗性样本产生的知识,但是防守者知道野外攻击者应用的确切攻击算法是不切实际的。这项工作是第一个在不知道特定攻击算法的情况下对ASV进行对抗性防御。灵感来自自我监督的学习模型(SSLMS),其具有减轻输入中的浅表噪声并重建中断的浅层样本的优点,这项工作至于对噪声的对抗扰动以及SSLMS对ASV的对抗性防御。具体而言,我们建议从两种角度进行对抗性防御:1)对抗扰动纯化和2)对抗扰动检测。实验结果表明,我们的检测模块通过检测对抗性样本的精度约为80%,有效地屏蔽了ASV。此外,由于对ASV的对抗防御性能没有共同的指标,因此考虑到纯化和基于净化的方法,这项工作也将评估指标正式地进行对抗防御。我们真诚地鼓励未来的作品基于拟议的评估框架基于拟议的评估框架来基准。
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
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
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