多输出分类问题中增强语义一致嵌入的四重损失
A Quadruplet Loss for Enforcing Semantically Coherent Embeddings in Multi-output Classification Problems
摘要：
本文描述了一个用于学习多输出分类问题中语义一致特征嵌入的目标函数，即，当响应变量的维数大于1时。特别是，我们认为在视觉监控环境中的身份检索和软生物特征标记的问题，这已经吸引了越来越多的兴趣。受三重损失[34]函数的启发，我们提出了一个推广：1）定义一个考虑元素对之间一致标签数量的度量; 2）忽略锚点的概念，根据对之间一致标签的数量，对于A，B，C，D距离约束，将d（A1，A2）< d（A1，B）替换为d（A，B）< d（C，D）。作为三重损失公式，我们的建议也优先考虑正对之间的小距离，但同时明确规定其他对之间的距离直接对应于它们在一致标签方面的相似性。这产生了在类质心和它们的语义描述之间具有强对应性的特征嵌入，即，其中，元素与共享它们的一些标签的其他元素的距离比与具有完全不相交的标签成员关系的元素的距离更近。作为实际效果，所提出的损失可以被视为特别适合于基于作为k-邻居的简单规则来执行联合粗略（软标签）+精细（ID）推断，这相对于先前相关的损失函数是新颖的。此外，与其三元组对应物相反，所提出的损失对于挖掘学习实例（例如半硬对）的任何苛刻标准都是不可知的。我们的实验在五个不同的数据集（BIODI，LFW，IJB-A，Megaface和PETA）进行，并验证了我们的假设，显示出非常有前途的结果。
英文摘要：
This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the problems of identity retrieval and soft biometrics labelling in visual surveillance environments, which have been attracting growing interests. Inspired by the triplet loss [34] function, we propose a generalization that: 1) defines a metric that considers the number of agreeing labels between pairs of elements; and 2) disregards the notion of anchor, replacing d(A1, A2) < d(A1, B) by d(A, B) < d(C, D), for A, B, C, D distance constraints, according to the number of agreeing labels between pairs. As the triplet loss formulation, our proposal also privileges small distances between positive pairs, but at the same time explicitly enforces that the distance between other pairs corresponds directly to their similarity in terms of agreeing labels. This yields feature embeddings with a strong correspondence between the classes centroids and their semantic descriptions, i.e., where elements are closer to others that share some of their labels than to elements with fully disjoint labels membership. As practical effect, the proposed loss can be seen as particularly suitable for performing joint coarse (soft label) + fine (ID) inference, based on simple rules as k-neighbours, which is a novelty with respect to previous related loss functions. Also, in opposition to its triplet counterpart, the proposed loss is agnostic with regard to any demanding criteria for mining learning instances (such as the semi-hard pairs). Our experiments were carried out in five different datasets (BIODI, LFW, IJB-A, Megaface and PETA) and validate our assumptions, showing highly promising results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
