在现代分类任务中,标签数量越来越大,实际上遇到的数据集的大小也越来越大。随着班级数量的增加,阶级的歧义和阶级失衡变得越来越有问题,以达到高顶级1的准确性。同时,TOP-K指标(允许K猜测的指标)变得流行,尤其是用于性能报告。然而,提出为深度学习量身定制的Top-K损失仍然是一个挑战,无论是理论上还是实际的。在本文中,我们引入了由Top-K校准损失的最新发展启发的随机TOP-K铰链损失。我们的建议基于在灵活的“扰动优化器”框架上的Top-K操作员建筑的平滑。我们表明,在平衡数据集的情况下,我们的损失函数的性能非常出色,同时,与最先进的TOP-K损失函数相比,计算时间明显低。此外,我们为不平衡案例提出了一个简单的损失变体。在重尾数据集上的实验表明,我们的损失函数显着优于其他基线损失函数。
translated by 谷歌翻译
Systems for person re-identification (ReID) can achieve a high accuracy when trained on large fully-labeled image datasets. However, the domain shift typically associated with diverse operational capture conditions (e.g., camera viewpoints and lighting) may translate to a significant decline in performance. This paper focuses on unsupervised domain adaptation (UDA) for video-based ReID - a relevant scenario that is less explored in the literature. In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information. State-of-art methods cluster unlabeled target data, yet domain shifts across target cameras (sub-domains) can lead to poor initialization of clustering methods that propagates noise across epochs, thus preventing the ReID model to accurately associate samples of same identity. In this paper, an UDA method is introduced for video person ReID that leverages knowledge on video tracklets, and on the distribution of frames captured over target cameras to improve the performance of CNN backbones trained using pseudo-labels. Our method relies on an adversarial approach, where a camera-discriminator network is introduced to extract discriminant camera-independent representations, facilitating the subsequent clustering. In addition, a weighted contrastive loss is proposed to leverage the confidence of clusters, and mitigate the risk of incorrect identity associations. Experimental results obtained on three challenging video-based person ReID datasets - PRID2011, iLIDS-VID, and MARS - indicate that our proposed method can outperform related state-of-the-art methods. Our code is available at: \url{https://github.com/dmekhazni/CAWCL-ReID}
translated by 谷歌翻译
最先进的腿机器人可以在其驱动系统的输出处测量扭矩,或者具有透明的驱动系统,从而能够从电动电流计算关节扭矩。无论哪种情况,这种传感器模式很少用于状态估计。在本文中,我们建议使用关节扭矩测量值来估计腿部机器人的质心状态。为此,我们将腿部机器人的全身动力学投射到接触约束的无空间中,从而使动力学的表达独立于接触力。使用受约束的动力学和质心动量矩阵,我们能够直接将关节扭矩和质心态动力学联系起来。使用结果模型作为扩展卡尔曼滤波器(EKF)的过程模型,我们将扭矩测量融合在质心状态估计问题中。通过在具有不同步态的四倍机器人上进行的实际实验,我们证明,与直接计算相比,基于扭矩的EKF的估计质心状态大大改善了这些数量的回收率。
translated by 谷歌翻译
本文研究了由$ N $-$ N $ TCONOR代表的非二进制对交互估计的社区成员资格,其值为$ \ MATHCAL S $的元素,其中$ N $是节点的数量和$ \ Mathcal S $是节点之间的成对交互的空间。作为信息理论基准,我们研究由非二进制随机块模型生成的数据集,并导致社区成员资格的基本信息标准作为$ n \ to \ idty $。应用程序的示例包括加权网络($ \ mathcal s = \ mathbb r $),链接标记的网络$(\ mathcal s = \ {0,1,1,\ dots,l \} $),多路复用网络$(\ mathcal s = \ {0,1 \} ^ m $)和时间网络($ \ mathcal s = \ {0,1 \} ^ t $)。对于时间互动,我们表明(i)即使是$ t $的少数增加也可能对社区成员的恢复产生了很大影响,(ii)即使对于非常稀疏的数据(例如\ in in inverly degress),甚至可能存在一致的恢复$ t $足够大。我们还提供了几种离线和在线的估计算法,它充分利用了观察到的数据的时间性。我们在数据稀疏性和可识别性的各种假设下分析所提出的估计算法的准确性。数值实验表明,即使是社区分配的初始估计(例如,盲目随机猜测)也会导致在少量迭代之后通过在线算法获得的高精度,并且在非常稀疏的方案中也是如此。
translated by 谷歌翻译