Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
Disentanglement learning is a core issue for understanding and re-using trained information in Variational AutoEncoder (VAE), and effective inductive bias has been reported as a key factor. However, the actual implementation of such bias is still vague. In this paper, we propose a novel method, called Multiple Invertible and partial-equivariant transformation (MIPE-transformation), to inject inductive bias by 1) guaranteeing the invertibility of latent-to-latent vector transformation while preserving a certain portion of equivariance of input-to-latent vector transformation, called Invertible and partial-equivariant transformation (IPE-transformation), 2) extending the form of prior and posterior in VAE frameworks to an unrestricted form through a learnable conversion to an approximated exponential family, called Exponential Family conversion (EF-conversion), and 3) integrating multiple units of IPE-transformation and EF-conversion, and their training. In experiments on 3D Cars, 3D Shapes, and dSprites datasets, MIPE-transformation improves the disentanglement performance of state-of-the-art VAEs.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementInductive BiasSimilar Papers 제목 키워드 기반
LIA: Latently Invertible Autoencoder with Adversarial Learning
Deep generative models such as Variational AutoEncoder (VAE) and Generative Adversarial Network (GAN) play an increasingly important role in machine learning and computer vision. However, there are two fundamental issues…
DecoderGenerative Adversarial NetworkVariational InferenceE(n) Equivariant Normalizing Flows
This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E(n) graph neural networks and integrate them as a …
Disentangled Inference for GANs with Latently Invertible Autoencoder
Generative Adversarial Networks (GANs) play an increasingly important role in machine learning. However, there is one fundamental issue hindering their practical applications: the absence of capability for encoding real-…
DecoderInvertible Residual Network with Regularization for Effective Medical Image Segmentation
Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly ofte…
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationEquivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
We propose Equivariance by Contrast (EbC) to learn equivariant embeddings from observation pairs $(\mathbf{y}, g \cdot \mathbf{y})$, where $g$ is drawn from a finite group acting on the data. Our method jointly learns a …