CVMay 14, 2018

Normal Similarity Network for Generative Modelling

arXiv:1805.05269v12 citations
Originality Incremental advance
AI Analysis

This work addresses the under-explored applicability of Gaussian distributions in deep networks for generative modeling, offering a new approach for computer vision tasks.

The paper tackles the problem of using Gaussian distributions in deep generative models by proposing the Normal Similarity Network (NSN), a novel deep generative model with Gaussian-style filters, and achieves encouraging results in image generation, styling, and reconstruction from occluded images across various computer vision applications.

Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal Similarity Network (NSN) where the layers are constructed with Gaussian-style filters. NSN is trained with a layer-wise non-parametric density estimation algorithm that iteratively down-samples the training images and captures the density of the down-sampled training images in the final layer. Additionally, we propose NSN-Gen for generating new samples from noise vectors by iteratively reconstructing feature maps in the hidden layers of NSN. Our experiments suggest encouraging results of the proposed model for a wide range of computer vision applications including image generation, styling and reconstruction from occluded images.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes