paper-with-me

홈 › Papers

Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders

2018-04-27 · ECCV 2018 9 · Ananya Harsh Jha, Saket Anand, Maneesh Singh, V. S. R. Veeravasarapu

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity labels. Inspired by the recent success of cycle-consistent adversarial architectures, we use cycle-consistency in a variational auto-encoder framework. Our non-adversarial approach is in contrast with the recent works that combine adversarial training with auto-encoders to disentangle representations. We show compelling results of disentangled latent subspaces on three datasets and compare with recent works that leverage adversarial training.

📄 PDF Abstract BibTeX arXiv:1804.10469

Code (5)

Akash-Sharma-1/Disentangling-Factors-of-Variation-in-Images-with-Cycle-Consistent-VAE pytorch
ananyahjha93/challenges-in-disentangling pytorch
ananyahjha93/cycle-consistent-vae pytorch
ananyahjha93/disentangling-factors-of-variation-using-adversarial-training pytorch
viditjain99/DL-Cycle-Consistent-Variational-Autoencoder

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Disentangling Video with Independent Prediction

2019-01-17 · William F. Whitney, Rob Fergus

We propose an unsupervised variational model for disentangling video into independent factors, i.e. each factor's future can be predicted from its past without considering the others. We show that our approach often lear…

Prediction

JADE: Joint Autoencoders for Dis-Entanglement

2017-11-24 · Ershad Banijamali, Amir-Hossein Karimi, Alexander Wong, Ali Ghodsi

The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangling feature representations rely on the …

DisentanglementGeneral Classification

Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation

2023-04-17 · Siyu Wang, Xiaocong Chen, Quan Z. Sheng, Yihong Zhang 외

Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these …

Decision MakingDisentanglementRecommendation Systems

Disentangling shared and private latent factors in multimodal Variational Autoencoders

2024-03-10 · Kaspar Märtens, Christopher Yau

Generative models for multimodal data permit the identification of latent factors that may be associated with important determinants of observed data heterogeneity. Common or shared factors could be important for explain…

Disentanglement

Disentangling Latent Hands for Image Synthesis and Pose Estimation

2018-12-03 · CVPR 2019 6 · Linlin Yang, Angela Yao

Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better an…

Image GenerationPose Estimation