Age Progression/Regression by Conditional Adversarial Autoencoder

Abstract

If I provide you a face image of mine (without telling you the actual age when I took the picture) and a large amount of face images that I crawled (containing labeled faces of different ages but not necessarily paired), can you show me what I would look like when I am 80 or what I was like when I was 5?" The answer is probably a "No." Most existing face aging works attempt to learn the transformation between age groups and thus would require the paired samples as well as the labeled query image. In this paper, we look at the problem from a generative modeling perspective such that no paired samples is required. In addition, given an unlabeled image, the generative model can directly produce the image with desired age attribute. We propose a conditional adversarial autoencoder (CAAE) that learns a face manifold, traversing on which smooth age progression and regression can be realized simultaneously. In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator. The latent vector preserves personalized face features (i.e., personality) and the age condition controls progression vs. regression. Two adversarial networks are imposed on the encoder and generator, respectively, forcing to generate more photo-realistic faces. Experimental results demonstrate the appealing performance and flexibility of the proposed framework by comparing with the state-of-the-art and ground truth.

Expression of Concern: Facial feature discovery for ethnicity recognition

“…Based on scale, illumination and pose, Yan and Zhang () used PCA to analyze the facial features on CMU and UCSD databases. Recently, many deep neural network methods are also used for face analysis and recognition (Chen, Zhang, Dong, Le, & Rao, ; Luan et al, ; Trigeorgis, Snape, Kokkinos, & Zafeiriou, ; Zhang, Song, & Qi, ). Srinivas et al () focused on predicting ethnicity using a convolutional neural network (CNN) with the Wild East Asian Face Dataset.…”

Joint Deep Learning of Facial Expression Synthesis and Recognition

“…2 person). In contrast, the synthetic images generated by FG give more smooth transformation than those generated by FG-Dz, which demonstrates that the discriminator D z is beneficial to compact the face representations on the facial manifold [48]. Compared with FG, the results obtained by ExprGAN sometimes cannot effectively preserve identity information and facial details.…”

“…In the first stage, a facial expression synthesis GAN (FES-GAN) consisting of a generator G and two discriminators (i.e., D img and D z ) is pre-trained to generate synthetic facial images. In this paper, the autoencoder structure (including an encoder G enc and a decoder G dec ) [48] is employed as the generator. The generator of FESGAN is used to learn the content style of real facial images.…”

Look Globally, Age Locally: Face Aging With an Attention Mechanism

“…Furthermore, the conditional feature maps are similar to one-hot code in some ways where only one of which is lled with ones while the rest are all lled with zeros. For IPCGANs, we first train the age classier which is netuned based on AlexNet on the CACD [20] and other parameters are set according to [4]. For CAAE, we remove the gender information and use 5 age groups instead of for fair comparison.…”

“…In recent years, face aging has attracted major attention due to its extensive use in numerous applications, entertainment [1], finding missing children [2], cross-age face recognition [3], etc. Although impressive results have been achieved recently [4,5,6,7,8], there are still many challenges due to the intrinsic complexity of aging in nature and the insufficient labeled aging data. Intuitively, the generated face images should be photo-realistic, e.g., without serious ghosting artifacts.…”