We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels that represents a degree of similarity between a pair. In the training stage, the model is trained with both MDR and an existing loss function of deep metric learning, simultaneously; the two losses interfere with the objective of each other, and it makes the learning process difficult. Moreover, MDR prevents some examples from being ignored or overly influenced in the learning process. These allow the parameters of the embedding network to be settle on a local optima with better generalization. Without bells and whistles, MDR with simple Triplet loss achieves the-state-of-the-art performance in various benchmark datasets: CUB-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval. We extensively perform ablation studies on its behaviors to show the effectiveness of MDR. By easily adopting our MDR, the previous approaches can be improved in performance and generalization ability.
Critical Regularizations for Neural Surface Reconstruction in the Wild
The Hong Kong University of Science and Technology（香港科技大学）；Apple（苹果公司）
神经隐式函数最近在多个视图的表面重建上显示出有希望的结果。然而，现有的方法在重建无界或复杂场景时仍然存在过度的时间复杂度和较差的鲁棒性。在本文中，我们提出了RegSDF，这表明适当的点云监督和几何正则化足以产生高质量和强大的重建结果。具体地说，RegSDF采用额外的定向点云作为输入，并在可微分渲染框架内优化有符号距离场和表面光场。我们还介绍了这种优化的两个关键的正则化。第一个是Hessian正则化，它在给定噪声和不完整输入的情况下将符号距离值平滑地扩散到整个距离场。第二种方法是最小曲面正则化，它对缺失的几何体进行紧致插值和外推。在DTU、BlendedMVS和Tanks and Temples数据集上进行了大量的实验。与最近的神经表面重建方法相比，RegSDF能够重建具有精细细节的表面，即使是具有复杂拓扑结构和非结构化相机轨迹的开放场景。
Rapid Person Re-Identification via Sub-space Consistency Regularization
Nanjing University of Science and Technology（南京理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；National University of Singapore（新加坡国立大学）；Queen Mary University of London（伦敦玛丽女王大学）
Wasserstein Adversarial Regularization (WAR) on label noise
University Bretagne Sud（布列塔尼南部大学）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）；IRISA（法国信息与自动化系统研究所）；InterDigital R&D（InterDigital研发中心）；Université de Paris（巴黎大学）；Wageningen University（瓦赫宁根大学）；École Polytechnique（巴黎综合理工学院）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition
School of Mathematics (Zhuhai) Sun Yat-sen University（中山大学数学学院（珠海））；ODEN Institute for Computational Engineering & Sciences University of Texas at Austin（德克萨斯大学奥斯汀分校ODEN计算工程与科学研究所）；Shenzhen Institute of Advanced Technology Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
