Semantic Noise Modeling for Better Representation Learning

TL;DR

This paper introduces a semantic noise modeling technique that perturbs latent representations in neural networks to improve their generalization and robustness, demonstrating performance gains over previous methods.

Contribution

It proposes a novel class-conditional noise perturbation in latent space to enhance feature representation and model generalization in deep learning.

Findings

Improved performance on various benchmarks.

Effective semantic augmentation via latent space perturbation.

Visualizations confirm enhanced feature separability.

Abstract

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned latent representation which is obtained from an appropriate training scenario with a task-specific objective on a designed network model. In this work, we propose a novel latent space modeling method to learn better latent representation. We designed a neural network model based on the assumption that good base representation can be attained by maximizing the total correlation between the input, latent, and output variables. From the base model, we introduce a semantic noise modeling method which enables class-conditional perturbation on latent space to enhance the representational power of learned latent feature. During training, latent vector representation can be stochastically perturbed by a modeled class-conditional additive noise while maintaining its original semantic feature. It implicitly brings the effect of semantic augmentation on the latent space. The proposed model can be easily learned by back-propagation with common gradient-based optimization algorithms. Experimental results show that the proposed method helps to achieve performance benefits against various previous approaches. We also provide the empirical analyses for the proposed class-conditional perturbation process including t-SNE visualization.