Virtual Class Enhanced Discriminative Embedding Learning

Abstract

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple method \textbf{Virtual Softmax} to enhance the discriminative property of learned features by injecting a dynamic virtual negative class into the original softmax. Injecting virtual class aims to enlarge inter-class margin and compress intra-class distribution by strengthening the decision boundary constraint. Although it seems weird to optimize with this additional virtual class, we show that our method derives from an intuitive and clear motivation, and it indeed encourages the features to be more compact and separable. This paper empirically and experimentally demonstrates the superiority of Virtual Softmax, improving the performances on a variety of object classification and face verification tasks.

NeurIPS 2018

Cited by in corpus (10)

• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Mixed High-Order Attention Network for Person Re-Identification
• Regularizing Class-wise Predictions via Self-knowledge Distillation
• Regular Polytope Networks
• On the Separability of Classes with the Cross-Entropy Loss Function
• Mis-classified Vector Guided Softmax Loss for Face Recognition
• Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture
• Attract or Distract: Exploit the Margin of Open Set
• Recent Advances in Large Margin Learning