Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Sien, Wang, Tao, Hu, Ruizhe, Liu, Wenxi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929583626911744
author Li, Sien
Wang, Tao
Hu, Ruizhe
Liu, Wenxi
author_facet Li, Sien
Wang, Tao
Hu, Ruizhe
Liu, Wenxi
contents In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively rare. We note several problems with existing network perturbations in SSS that may contribute to this phenomenon. By revisiting network perturbations, we introduce a new approach for network perturbation to expand the existing weak-to-strong consistency regularization for unlabeled data. Additionally, we present a volatile learning process for labeled data, which is uncommon in existing research. Building upon previous work that includes input-level and feature-level perturbations, we present MLPMatch (Multi-Level-Perturbation Match), an easy-to-implement and efficient framework for semi-supervised semantic segmentation. MLPMatch has been validated on the Pascal VOC and Cityscapes datasets, achieving state-of-the-art performance. Code is available from https://github.com/LlistenL/MLPMatch.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05307
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
Li, Sien
Wang, Tao
Hu, Ruizhe
Liu, Wenxi
Computer Vision and Pattern Recognition
Artificial Intelligence
In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively rare. We note several problems with existing network perturbations in SSS that may contribute to this phenomenon. By revisiting network perturbations, we introduce a new approach for network perturbation to expand the existing weak-to-strong consistency regularization for unlabeled data. Additionally, we present a volatile learning process for labeled data, which is uncommon in existing research. Building upon previous work that includes input-level and feature-level perturbations, we present MLPMatch (Multi-Level-Perturbation Match), an easy-to-implement and efficient framework for semi-supervised semantic segmentation. MLPMatch has been validated on the Pascal VOC and Cityscapes datasets, achieving state-of-the-art performance. Code is available from https://github.com/LlistenL/MLPMatch.
title Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.05307