A Plug-in Method for Representation Factorization in Connectionist Models
arXiv:1905.11088 · doi:10.1109/TNNLS.2021.3054480
Abstract
In this article, we focus on decomposing latent representations in generative adversarial networks or learned feature representations in deep autoencoders into semantically controllable factors in a semisupervised manner, without modifying the original trained models. Particularly, we propose factors' decomposer-entangler network (FDEN) that learns to decompose a latent representation into mutually independent factors. Given a latent representation, the proposed framework draws a set of interpretable factors, each aligned to independent factors of variations by minimizing their total correlation in an information-theoretic means. As a plug-in method, we have applied our proposed FDEN to the existing networks of adversarially learned inference and pioneer network and performed computer vision tasks of image-to-image translation in semantic ways, e.g., changing styles, while keeping the identity of a subject, and object classification in a few-shot learning scheme. We have also validated the effectiveness of the proposed method with various ablation studies in the qualitative, quantitative, and statistical examination.
in IEEE Transactions on Neural Networks and Learning Systems, 2021
References in corpus (21)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Prototypical Networks for Few-shot Learning
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Improved Techniques for Training GANs
- Data Augmentation Generative Adversarial Networks
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Equitability, mutual information, and the maximal information coefficient
- Adversarial Feature Learning
- Disentangling by Factorising
- Adversarially Learned Inference
- Towards a Definition of Disentangled Representations
- Learning Factorized Multimodal Representations
- Neural Voice Cloning with a Few Samples
- Invertible Residual Networks
- Learning Deep Disentangled Embeddings with the F-Statistic Loss
- A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
- Formal Limitations on the Measurement of Mutual Information
- Adapted Deep Embeddings: A Synthesis of Methods for -Shot Inductive Transfer Learning
- Generative Adversarial Networks (GANs): What it can generate and What it cannot?
- MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning