Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax
원문 초록
Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and contrastive SSRL in general being well-explored, the task of learning representations conforming to a specific distribution (i.e., distribution matching, DM) is still under-addressed. Motivated by the importance of DM to several downstream tasks (including generative modeling, disentanglement, outliers detection and other), we enhance DIM to enable automatic matching of learned representations to a selected prior distribution. To achieve this, we propose injecting an independent noise into the normalized outputs of the encoder, while keeping the same InfoMax training objective. We show that such modification allows for learning uniformly and normally distributed representations, as well as representations of other absolutely continuous distributions. Our approach is tested on various downstream tasks. The results indicate a moderate trade-off between the performance on the downstream tasks and quality of DM.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Disentangled representations of microscopy images
DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing
An Interpretable Representation Learning Approach for Diffusion Tensor Imaging
DOMFN: A Divergence-Orientated Multi-Modal Fusion Network for Resume Assessment
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Dual Dimensions Geometric Representation Learning Based Document Dewarping
토론
이 논문과 연결된 포럼 글이 아직 없습니다.