Over the past few years, Convolutional Neural Networks (CNNs) have shown
promise on facial expression recognition. However, the performance degrades
dramatically under real-world settings due to variations introduced by subtle
facial appearance changes, head pose variations, illumination changes, and
occlusions.
In this paper, a novel island loss is proposed to enhance the discriminative
power of the deeply learned features. Specifically, the IL is designed to
reduce the intra-class variations while enlarging the inter-class differences
simultaneously. Experimental results on four benchmark expression databases
have demonstrated that the CNN with the proposed island loss (IL-CNN)
outperforms the baseline CNN models with either traditional softmax loss or the
center loss and achieves comparable or better performance compared with the
state-of-the-art methods for facial expression recognition.

本文通过引入新的岛津损失函数，在人脸表情识别领域尝试了新的改进方法，从而提高了卷积神经网络的性能。实验结果显示，使用该岛津损失函数的卷积神经网络相比于传统的 softmax loss 和中心损失方法以及同领域最先进方法表现更优，成功解决了真实世界条件下人脸表情识别中的问题。