Learning a Facial Expression Embedding Disentangled From Identity

Wei Zhang, Xianpeng Ji, Keyu Chen, Yu Ding, Changjie Fan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 6759-6768

Abstract


The facial expression analysis requires a compact and identity-ignored expression representation. In this paper, we model the expression as the deviation from the identity by a subtraction operation, extracting a continuous and identity-invariant expression embedding. We propose a Deviation Learning Network (DLN) with a pseudo-siamese structure to extract the deviation feature vector. To reduce the optimization difficulty caused by additional fully connection layers, DLN directly provides high-order polynomial to nonlinearly project the high-dimensional feature to a low-dimensional manifold. Taking label noise into account, we add a crowd layer to DLN for robust embedding extraction. Also, to achieve a more compact representation, we use hierarchical annotation for data augmentation. We evaluate our facial expression embedding on the FEC validation set. The quantitative results prove that we achieve the state-of-the-art, both in terms of fine-grained and identity-invariant property. We further conduct extensive experiments to show that our expression embedding is of high quality for emotion recognition, image retrieval, and face manipulation.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2021_CVPR, author = {Zhang, Wei and Ji, Xianpeng and Chen, Keyu and Ding, Yu and Fan, Changjie}, title = {Learning a Facial Expression Embedding Disentangled From Identity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {6759-6768} }