In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently learned by artificial neural networks. Our learnable ACE (LACE) transforms the data into a new "whitened" space that improves the inter-class separability and intra-class compactness. We compare our LACE to alternative state-of-the art softmax-based and feature regularization approaches. Our results show that the proposed method can serve as a viable alternative to cross entropy and angular softmax approaches. Our code is publicly available: https://github.com/GatorSense/LACE.
翻译:在这项工作中,我们提出新的损失,以改善特征差异和分类性能。在适应性cosine/cotherence 估测器(ACE)的推动下,我们提议的方法纳入了人工神经网络所固有的三角信息。我们学习的ACE(LACE)将数据转换成一个新的“白色”空间,改善阶级间分离和阶级内紧凑性。我们比较了我们的LACE,以替代最先进的软模基和特征规范化方法。我们的结果显示,拟议的方法可以作为跨对柱和角软模方法的可行替代方法。我们的代码可以公开查阅:https://github.com/GatorSense/LACE。