The survival analysis on histological whole-slide images (WSIs) is one of the most important means to estimate patient prognosis. Although many weakly-supervised deep learning models have been developed for gigapixel WSIs, their potential is generally restricted by classical survival analysis rules and fully-supervision requirements. As a result, these models provide patients only with a completely-certain point estimation of time-to-event, and they could only learn from the well-annotated WSI data currently at a small scale. To tackle these problems, we propose a novel adversarial multiple instance learning (AdvMIL) framework. This framework is based on adversarial time-to-event modeling, and it integrates the multiple instance learning (MIL) that is much necessary for WSI representation learning. It is a plug-and-play one, so that most existing WSI-based models with embedding-level MIL networks can be easily upgraded by applying this framework, gaining the improved ability of survival distribution estimation and semi-supervised learning. Our extensive experiments show that AdvMIL could not only bring performance improvement to mainstream WSI models at a relatively low computational cost, but also enable these models to learn from unlabeled data with semi-supervised learning. Our AdvMIL framework could promote the research of time-to-event modeling in computational pathology with its novel paradigm of adversarial MIL.
translated by 谷歌翻译
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been shown to be not robust to noisy labels due to its unboundedness. To alleviate this issue, existing works typically design specialized robust losses with the symmetric condition, which usually lead to the underfitting issue. In this paper, our key idea is to induce a loss bound at the logit level, thus universally enhancing the noise robustness of existing losses. Specifically, we propose logit clipping (LogitClip), which clamps the norm of the logit vector to ensure that it is upper bounded by a constant. In this manner, CE loss equipped with our LogitClip method is effectively bounded, mitigating the overfitting to examples with noisy labels. Moreover, we present theoretical analyses to certify the noise-tolerant ability of LogitClip. Extensive experiments show that LogitClip not only significantly improves the noise robustness of CE loss, but also broadly enhances the generalization performance of popular robust losses.
translated by 谷歌翻译
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms. To study the generalization of OOD detection, in this paper, we investigate the probably approximately correct (PAC) learning theory of OOD detection, which is proposed by researchers as an open problem. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we also offer theoretical supports for several representative OOD detection works based on our OOD theory.
translated by 谷歌翻译
人的大脑可以毫不费力地识别和定位对象,而基于激光雷达点云的当前3D对象检测方法仍然报告了较低的性能,以检测闭塞和远处的对象:点云的外观由于遮挡而变化很大,并且在沿线的固有差异沿点固有差异变化。传感器的距离。因此,设计功能表示对此类点云至关重要。受到人类联想识别的启发,我们提出了一个新颖的3D检测框架,该框架通过域的适应来使对象完整特征。我们弥合感知域之间的差距,其中特征是从具有亚最佳表示的真实场景中得出的,以及概念域,其中功能是从由不批准对象组成的增强场景中提取的,并具有丰富的详细信息。研究了一种可行的方法,可以在没有外部数据集的情况下构建概念场景。我们进一步介绍了一个基于注意力的重新加权模块,该模块可适应地增强更翔实区域的特征。该网络的功能增强能力将被利用,而无需在推理过程中引入额外的成本,这是各种3D检测框架中的插件。我们以准确性和速度都在Kitti 3D检测基准上实现了新的最先进性能。关于Nuscenes和Waymo数据集的实验也验证了我们方法的多功能性。
translated by 谷歌翻译
在现实世界中,尽管对该领域的兴趣激增,但在稀疏回报协同环境下进行的加强学习仍然具有挑战性。先前的尝试表明,内在的奖励可以减轻稀疏引起的问题。在本文中,我们提出了一种新颖的固有奖励,该奖励受人类学习的启发,因为人类通过将当前的观察结果与历史知识进行比较来评估好奇心。具体而言,我们训练一个自我监督的预测模型,并保存一组模型参数的快照,而不会产生加法培训成本。然后,我们采用核规范来评估不同快照的预测之间的时间不一致,这可以进一步部署为内在的奖励。此外,提出了一种变异的加权机制,以自适应方式将权重分配给不同的快照。我们证明了所提出的方法在各种基准环境中的功效。结果表明,与其他基于奖励的方法相比,我们的方法可以提供压倒性的最先进性能,而不会产生额外的培训成本并保持更高的噪声耐受性。我们的代码将公开发布以提高可重复性。
translated by 谷歌翻译
外部奖励的稀疏性对加强学习(RL)构成了严重的挑战。当前,对好奇心已经做出了许多努力,这些努力可以为有效探索提供代表性的内在奖励。但是,挑战尚未得到解决。在本文中,我们提出了一种名为Dymecu的RL的好奇心,它代表了基于动态记忆的好奇心。受到人类好奇心和信息理论的启发,Dymecu由动态记忆和双重在线学习者组成。好奇心引起的话,如果记忆的信息无法处理当前状态,并且双重学习者之间的信息差距可以作为对代理的内在奖励进行表述,然后可以将这些状态信息巩固到动态内存中。与以前的好奇方法相比,dymecu可以更好地模仿人类的好奇心与动态记忆,并且可以根据双重学习者的引导范式动态地生长内存模块。在包括DeepMind Control Suite和Atari Suite在内的多个基准测试中,进行了大规模的经验实验,结果表明,Dymecu在有或没有外部奖励的情况下优于基于好奇心的方法。我们将发布代码以增强可重复性。
translated by 谷歌翻译
目标条件加固学习(GCRL)具有广泛的潜在现实应用程序,包括机器人技术中的操纵和导航问题。尤其是在这样的机器人技术任务中,对GCRL的样本效率至关重要,因为默认情况下,只有在实现其目标时才会获得奖励。尽管已经提出了几种方法来提高GCRL的样品效率,但一种相对研究的方法是设计神经体系结构以支持样品效率。在这项工作中,我们引入了一种新型的GCRL神经结构,该神经结构比常用的单片网络体系结构可实现的样品效率明显更好。他们的关键见解是,最佳动作值函数q^*(s,a,g)必须在特定意义上满足三角形不平等。此外,我们引入了度量残留网络(MRN),该度量剩余网络(MRN)故意将动作值函数q(s,a,g)分解到否定的度量总和和残留不对称组件中。 MRN可证明近似于任何最佳动作值函数q^*(S,A,G),从而使其成为GCRL的拟合神经结构。我们在GCRL中的12个标准基准环境中进行了全面的实验。经验结果表明,就样本效率而言,MRN均匀地优于其他最先进的GCRL神经体系结构。
translated by 谷歌翻译
多对象跟踪(MOT)是计算机视觉领域的重要技术,该技术广泛用于自动驾驶,智能监控,行为识别和其他方向。在基于深度学习的当前流行MOT方法中,基于检测的跟踪(DBT)是行业中最广泛使用的,它们的性能取决于其对象检测网络。目前,性能良好,使用最广泛的DBT算法是Yolov5-Deepsort。受Yolov5-Deepsort的启发,Yolov7网络的建议在对象检测方面的性能更好,我们将Yolov7应用于DeepSort,并提出Yolov7-Deepsort。经过实验评估后,与以前的Yolov5-Deepsort相比,Yolov7-Deepsort的表现更好地跟踪准确性。
translated by 谷歌翻译
最近,许多半监督的对象检测(SSOD)方法采用教师学生框架并取得了最新的结果。但是,教师网络与学生网络紧密相结合,因为教师是学生的指数移动平均值(EMA),这会导致表现瓶颈。为了解决耦合问题,我们为SSOD提出了一个周期自我训练(CST)框架,该框架由两个老师T1和T2,两个学生S1和S2组成。基于这些网络,构建了一个周期自我训练机制​​,即S1 $ {\ rightarrow} $ t1 $ {\ rightArow} $ s2 $ {\ rightArrow} $ t2 $ {\ rightArrow} $ s1。对于S $ {\ Rightarrow} $ T,我们还利用学生的EMA权重来更新老师。对于t $ {\ rightarrow} $ s,而不是直接为其学生S1(S2)提供监督,而是老师T1(T2)为学生S2(S1)生成伪标记,从而松散耦合效果。此外,由于EMA的财产,老师最有可能积累学生的偏见,并使错误变得不可逆转。为了减轻问题,我们还提出了分配一致性重新加权策略,在该策略中,根据教师T1和T2的分配一致性,将伪标记重新加权。通过该策略,可以使用嘈杂的伪标签对两个学生S2和S1进行训练,以避免确认偏见。广泛的实验证明了CST的优势,通过将AP比基线优于最先进的方法提高了2.1%的绝对AP改进,并具有稀缺的标记数据,而胜过了2.1%的绝对AP。
translated by 谷歌翻译
机上的机器学习使本地客户端推荐模型的轻量级部署可以减轻基于云的推荐人的负担,并同时结合了更多实时用户功能。然而,考虑到其强大的模型能力以及从十亿级项目库中产生的有效候选人,该行业的基于云的建议仍然非常重要。以前的尝试将两种范式的优点整合起来主要诉诸于顺序机制,该机制在基于云的建议之上构建了在设备上的推荐人。但是,当用户兴趣发生巨大变化时,这种设计是不灵活的:设备模型被有限的项目缓存粘住,而基于大型项目池的基于云的推荐则没有新的重新汇总反馈。为了克服这个问题,我们提出了一个元控制器,以动态管理推荐装置推荐人与基于云的推荐人之间的协作,并从因果角度引入一种新颖的有效样本构造,以解决元控制者的数据集缺失问题。在反事实样本和扩展培训的基础上,在工业推荐方案中进行的广泛实验显示了在设备云协作中Meta控制器的承诺。
translated by 谷歌翻译