IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Kebin, Li, Wenbin, Xiao, Xiaofei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929330362253312
author Wu, Kebin
Li, Wenbin
Xiao, Xiaofei
author_facet Wu, Kebin
Li, Wenbin
Xiao, Xiaofei
contents The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to mine the neglected but valuable Inter-Pixel information for semi-supervised learning. Specifically, IPixMatch is constructed as an extension of the standard teacher-student network, incorporating additional loss terms to capture inter-pixel relations. It shines in low-data regimes by efficiently leveraging the limited labeled data and extracting maximum utility from the available unlabeled data. Furthermore, IPixMatch can be integrated seamlessly into most teacher-student frameworks without the need of model modification or adding additional components. Our straightforward IPixMatch method demonstrates consistent performance improvements across various benchmark datasets under different partitioning protocols.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18891
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation
Wu, Kebin
Li, Wenbin
Xiao, Xiaofei
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to mine the neglected but valuable Inter-Pixel information for semi-supervised learning. Specifically, IPixMatch is constructed as an extension of the standard teacher-student network, incorporating additional loss terms to capture inter-pixel relations. It shines in low-data regimes by efficiently leveraging the limited labeled data and extracting maximum utility from the available unlabeled data. Furthermore, IPixMatch can be integrated seamlessly into most teacher-student frameworks without the need of model modification or adding additional components. Our straightforward IPixMatch method demonstrates consistent performance improvements across various benchmark datasets under different partitioning protocols.
title IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.18891