Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xin, Boyadzhiev, Teodor, Shi, Jinglei, Yang, Jufeng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.13771
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910575875850240
author Zhang, Xin
Boyadzhiev, Teodor
Shi, Jinglei
Yang, Jufeng
author_facet Zhang, Xin
Boyadzhiev, Teodor
Shi, Jinglei
Yang, Jufeng
contents In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation. The design philosophy is based on the observation that different pixel regions within an image exhibit varying levels of complexity, with higher complexities posing a greater challenge for accurate segmentation. We thus introduce image complexity as prior guidance and propose the Image Complexity prior-guided Feature Refinement Network (ICFRNet). This network aggregates both complexity and segmentation features to produce an attention map for refining segmentation features within an Image Complexity Guided Attention (ICGA) module. We optimize the network in terms of both segmentation and image complexity prediction tasks with a combined loss function. Experimental results on the Cityscapes and CamViD datasets have shown that our ICFRNet achieves higher accuracy with a competitive efficiency for real-time segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13771
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation
Zhang, Xin
Boyadzhiev, Teodor
Shi, Jinglei
Yang, Jufeng
Computer Vision and Pattern Recognition
In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation. The design philosophy is based on the observation that different pixel regions within an image exhibit varying levels of complexity, with higher complexities posing a greater challenge for accurate segmentation. We thus introduce image complexity as prior guidance and propose the Image Complexity prior-guided Feature Refinement Network (ICFRNet). This network aggregates both complexity and segmentation features to produce an attention map for refining segmentation features within an Image Complexity Guided Attention (ICGA) module. We optimize the network in terms of both segmentation and image complexity prediction tasks with a combined loss function. Experimental results on the Cityscapes and CamViD datasets have shown that our ICFRNet achieves higher accuracy with a competitive efficiency for real-time segmentation.
title ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.13771