Learning Controllable Disentangled Representations with Decorrelation Regularization
A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the encoder-decoder architecture to address this challenge. To encourage disentanglement, we devise a distance covariance based decorrelation regularization. Further, for the reconstruction step, our model leverages a soft target representation combined with the latent image code. By exploiting the real-valued space of the soft target representations, we are able to synthesize novel images with the designated properties. We also design a classification based protocol to quantitatively evaluate the disentanglement strength of our model. Experimental results show that the proposed model competently disentangles factors of variation, and is able to manipulate face images to synthesize the desired attributes.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderDisentanglementSimilar Papers 제목 키워드 기반
Toward a Controllable Disentanglement Network
This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstr…
DecoderDisentanglementGenerative Adversarial NetworkProgressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis
We present a novel one-shot talking head synthesis method that achieves disentangled and fine-grained control over lip motion, eye gaze&blink, head pose, and emotional expression. We represent different motions via disen…
Contrastive LearningDisentanglementRepresentation LearningGroup-disentangled Representation Learning with Weakly-Supervised Regularization
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representati…
DisentanglementRepresentation LearningTransfer LearningDecorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive alg…
Representation LearningSelf-Supervised LearningEncouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (concepts) for downstream tasks. Two genera…
Data AugmentationDisentanglementFairnessImage Generation+1