Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one research focus is to solve the open-set problem by discriminative deep embedding learning in the field of face recognition (FR) and person re-identification (re-ID). Apart from open-set problem, we find that imbalanced training data is another main factor causing the performance degradation of FR and re-ID, and data imbalance widely exists in the real applications. However, very little research explores why and how data imbalance influences the performance of FR and re-ID with softmax or its variants. In this work, we deeply investigate data imbalance in the perspective of neural network optimisation and feature distribution about softmax. We find one main reason of performance degradation caused by data imbalance is that the weights (from the penultimate fully-connected layer) are far from their class centers in feature space. Based on this investigation, we propose a unified framework, Imbalance-Robust Softmax (IR-Softmax), which can simultaneously solve the open-set problem and reduce the influence of data imbalance. IR-Softmax can generalise to any softmax and its variants (which are discriminative for open-set problem) by directly setting the weights as their class centers, naturally solving the data imbalance problem. In this work, we explicitly re-formulate two discriminative softmax (A-Softmax and AM-Softmax) under the framework of IR-Softmax. We conduct extensive experiments on FR databases (LFW, MegaFace) and re-ID database (Market-1501, Duke), and IR-Softmax outperforms many state-of-the-art methods.
翻译:深层嵌入学习预计会学习一个测量空间, 其特征比最软的门间距离要小得多。 近些年来, 一个研究焦点是通过在面部识别( FR) 和人重新识别( Re-ID) 领域有区别的深层嵌入学习来解决开放型问题。 除了开放型问题, 我们发现, 不平衡的培训数据是造成 FR 和 re- ID 性能退化的另一个主要因素, 而数据在实际应用中也广泛存在数据不平衡。 但是, 很少研究探索数据不平衡对FR和再ID的性能和软体间距离影响的原因和方式。 在这项工作中, 我们深入地调查数据不平衡问题, 软体内- 软体- Rexxx( Ift- 软体- 软体- Ift- IDID ) 的性能和软体外变体内变形变形变形( 软性变形) 数据数据库的重量比重要远, 我们提议一个统一的框架, Imax- fal- fal- fal- deal- max- max- max max max max max max) 和直调问题, 。