Scene Structure Guidance Network: Unfolding Graph Partitioning into Pixel-Wise Feature Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shin, Jisu, Shin, Seunghyun, Jeon, Hae-Gon
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910980827512832
author Shin, Jisu
Shin, Seunghyun
Jeon, Hae-Gon
author_facet Shin, Jisu
Shin, Seunghyun
Jeon, Hae-Gon
contents Understanding the informative structures of scenes is essential for low-level vision tasks. Unfortunately, it is difficult to obtain a concrete visual definition of the informative structures because influences of visual features are task-specific. In this paper, we propose a single general neural network architecture for extracting task-specific structure guidance for scenes. To do this, we first analyze traditional spectral clustering methods, which computes a set of eigenvectors to model a segmented graph forming small compact structures on image domains. We then unfold the traditional graph-partitioning problem into a learnable network, named \textit{Scene Structure Guidance Network (SSGNet)}, to represent the task-specific informative structures. The SSGNet yields a set of coefficients of eigenvectors that produces explicit feature representations of image structures. In addition, our SSGNet is light-weight ($\sim$ 56K parameters), and can be used as a plug-and-play module for off-the-shelf architectures. We optimize the SSGNet without any supervision by proposing two novel training losses that enforce task-specific scene structure generation during training. Our main contribution is to show that such a simple network can achieve state-of-the-art results for several low-level vision applications. We also demonstrate that our network generalizes well on unseen datasets, compared to existing methods which use structural embedding frameworks. We further propose a lighter version of SSGNet ($\sim$ 29K parameters) for depth computation, SSGNet-D, and successfully execute it on edge computing devices like Jetson AGX Orin, improving the performance of baseline network, even in the wild, with little computational delay.
format Preprint
id arxiv_https___arxiv_org_abs_2301_00555
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Scene Structure Guidance Network: Unfolding Graph Partitioning into Pixel-Wise Feature Learning
Shin, Jisu
Shin, Seunghyun
Jeon, Hae-Gon
Computer Vision and Pattern Recognition
Artificial Intelligence
Understanding the informative structures of scenes is essential for low-level vision tasks. Unfortunately, it is difficult to obtain a concrete visual definition of the informative structures because influences of visual features are task-specific. In this paper, we propose a single general neural network architecture for extracting task-specific structure guidance for scenes. To do this, we first analyze traditional spectral clustering methods, which computes a set of eigenvectors to model a segmented graph forming small compact structures on image domains. We then unfold the traditional graph-partitioning problem into a learnable network, named \textit{Scene Structure Guidance Network (SSGNet)}, to represent the task-specific informative structures. The SSGNet yields a set of coefficients of eigenvectors that produces explicit feature representations of image structures. In addition, our SSGNet is light-weight ($\sim$ 56K parameters), and can be used as a plug-and-play module for off-the-shelf architectures. We optimize the SSGNet without any supervision by proposing two novel training losses that enforce task-specific scene structure generation during training. Our main contribution is to show that such a simple network can achieve state-of-the-art results for several low-level vision applications. We also demonstrate that our network generalizes well on unseen datasets, compared to existing methods which use structural embedding frameworks. We further propose a lighter version of SSGNet ($\sim$ 29K parameters) for depth computation, SSGNet-D, and successfully execute it on edge computing devices like Jetson AGX Orin, improving the performance of baseline network, even in the wild, with little computational delay.
title Scene Structure Guidance Network: Unfolding Graph Partitioning into Pixel-Wise Feature Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2301.00555