Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Conditional Adversarial Autoencoder

A conditional adversarial autoencoder is a generative deep learning architecture that combines an autoencoder with adversarial training and conditional attribute controls to generate or transform data according to specified target properties. In this framework, an encoder maps input data into a low-dimensional latent representation that preserves core identity or content features, while a generator reconstructs the data by combining the latent code with conditional attribute vectors. Adversarial discriminators are applied to regularize the latent space and evaluate the generated samples, ensuring that the outputs are realistic and correctly reflect the conditioned attributes. By disentangling invariant content from external conditions, the architecture enables controlled data synthesis and smooth traversal along attribute manifolds, allowing continuous attribute manipulation without requiring paired training data.

1 item

Age Progression/Regression by Conditional Adversarial Autoencoder

Age Progression/Regression by Conditional Adversarial Autoencoder

Zhifei Zhang, Yang Song, Hairong Qi

OrganizationsUniversity of Tennessee

Why you should read this

Proposes a conditional adversarial autoencoder that performs realistic facial age progression and regression from a single unlabeled photograph without requiring paired training data while preserving individual identity.

"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.

Added

2026-09-25