The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images. While deep metric learning has yielded impressive performance gains by extracting high level abstractions from image data, a proper objective loss function becomes the central issue to boost the performance. In this paper, we propose a novel angular loss, which takes angle relationship into account, for learning better similarity metric. Whereas previous metric learning methods focus on optimizing the similarity (contrastive loss) or relative similarity (triplet loss) of image pairs, our proposed method aims at constraining the angle at the negative point of triplet triangles. Several favorable properties are observed when compared with conventional methods. First, scale invariance is introduced, improving the robustness of objective against feature variance. Second, a third-order geometric constraint is inherently imposed, capturing additional local structure of triplet triangles than contrastive loss or triplet loss. Third, better convergence has been demonstrated by experiments on three publicly available datasets.
DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio
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);Macau University of Science and Technology(澳门科技大学)
Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval
Beihang University(北京航空航天大学);Research Institute of Beihang University in Shenzhen(北京航空航天大学深圳研究院);Beijing Advanced Innovation Center for Big Data and Brain Computing(北京大数据与脑计算先进创新中心)
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
Tsinghua University(清华大学);SenseTime Research(商汤科技研究院);The Chinese University of Hong Kong(香港中文大学);Qing Yuan Research Institute, Shanghai Jiao Tong University(上海交通大学清源研究院)
ABFL: Angular Boundary Discontinuity Free Loss for Arbitrary Oriented Object Detection in Aerial Images
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences(中国科学院空间应用工程与技术中心);University of Chinese Academy of Sciences(中国科学院大学)
Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning
Begum Rokeya University, Rangpur(贝古姆·罗基亚大学,朗布尔);Wilmington University(威尔明顿大学);Washington University of Science and Technology(华盛顿科学与技术大学);Central Michigan University(中密歇根大学)
Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification
Tencent YouTu Lab(腾讯优图实验室);Sun Yat-sen University(中山大学);Southern University of Science and Technology(南方科技大学)
虽然最近在监督人重新识别(Re-ID)方面取得了很大进展,但由于人的视角变化,Re-ID仍然是一个巨大的视觉挑战。大多数现有的基于视点的人Re-ID方法将来自每个视点的图像投影到分离且不相关的子特征空间中。它们只对个体视点内部的身份级别分布进行建模,而忽略了不同视点之间的潜在关系。为了解决这个问题,我们提出了一种新的方法,称为\textit{Viewpoint-Aware Loss with Angular Regularization }(\textbf{VA-reID})。而不是一个子空间为每个视点,我们的方法项目的功能从不同的观点到一个统一的超球,并有效地建模的特征分布的身份级别和视点级别。此外,而不是建模不同的观点作为硬标签用于传统的视点分类,我们引入了视点感知的自适应标签平滑正则化(VALSR),分配自适应软标签的功能表示。VALSR算法能有效地解决视点簇标签分配的模糊性问题。在Market 1501和DukeMTMC-reID数据集上进行的大量实验表明,我们的方法优于最先进的监督Re-ID方法。
Scalable Angular Discriminative Deep Metric Learning for Face Recognition
Nankai University(南开大学);Tianjin University(天津大学)
随着深度学习的发展,深度度量学习(Deep Metric Learning,DML)在人脸识别方面取得了很大的进步。具体来说,在训练过程中广泛使用的softmax损失往往会带来很大的类内变化,而特征归一化只在测试过程中使用,以计算对相似度。为了弥补这一差距,我们在训练步骤中将softmax损失中的特征和权重向量之间的类内余弦相似性设置为大于一个裕度,并从四个方面对其进行了扩展。首先,我们探讨了硬样本挖掘策略的效果。为了减轻调整超参数的人工劳动,提出了一种自适应的边缘更新策略。然后,一个规范化的版本,以充分利用余弦相似性约束。此外,我们加强了前一个约束,迫使类内余弦相似度大于平均类间余弦相似度,在指数特征投影空间中有一个保证金。在Labeled Face in the Wild(LFW)、Youtube Faces(YTF)和IARPA Janus Benchmark A(IJB-A)数据集上进行的大量实验表明,本文提出的方法优于主流的DML方法,接近最先进的性能。