基于深度学习的无监督领域自适应语义分割算法综述
电子技术应用
应俊杰1,2,楼陆飞1,2,辛宇1,2
1.宁波大学 信息科学与工程学院, 浙江 宁波315211;2.浙江省移动网应用技术重点实验室,浙江 宁波315211
摘要: 随着现代生活逐步智能化,越来越多的应用需要从图像中推断相应的语义信息再进行后续的处理,如虚拟现实、自动驾驶和视频监控等应用。目前的语义分割模型利用大量标注数据进行有监督训练能达到理想的性能,但模型对与训练数据不同分布的数据进行推理时,其性能严重下降。这意味着一旦应用场景发生变化,就需对新场景的数据进行标注。模型重新利用新数据进行训练,才能达到正常的性能。这无疑是耗时的、代价昂贵的。为此,领域自适应语义分割算法提供了解决模型在分布不一致数据上语义分割性能下降问题的思路。总结了领域自适应语义分割算法的前沿进展,并对未来研究方向进行展望。
中圖分類號:TP391.4 文獻標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.234261
中文引用格式: 應(yīng)俊杰,樓陸飛,辛宇. 基于深度學(xué)習(xí)的無監(jiān)督領(lǐng)域自適應(yīng)語義分割算法綜述[J]. 電子技術(shù)應(yīng)用,2024,50(1):1-9.
英文引用格式: Ying Junjie,Lou Lufei,Xin Yu. A survey of unsupervised domain adaptive semantic segmentation algorithms based on deep learning[J]. Application of Electronic Technique,2024,50(1):1-9.
中文引用格式: 應(yīng)俊杰,樓陸飛,辛宇. 基于深度學(xué)習(xí)的無監(jiān)督領(lǐng)域自適應(yīng)語義分割算法綜述[J]. 電子技術(shù)應(yīng)用,2024,50(1):1-9.
英文引用格式: Ying Junjie,Lou Lufei,Xin Yu. A survey of unsupervised domain adaptive semantic segmentation algorithms based on deep learning[J]. Application of Electronic Technique,2024,50(1):1-9.
A survey of unsupervised domain adaptive semantic segmentation algorithms based on deep learning
Ying Junjie1,2,Lou Lufei1,2,Xin Yu1,2
1.College of Information Science and Engineering, Ningbo University, Ningbo 315211, China; 2.Key Laboratory of Mobile Network Application Technology of Zhejiang Province, Ningbo 315211, China
Abstract: As modern life becomes increasingly intelligent, more and more applications require inferring semantic information from images before proceeding with further processing, such as virtual reality, autonomous driving, and video surveillance. Current semantic segmentation models achieve ideal performance through supervised training with a large amount of annotated data, but their performance severely deteriorates when inferring on data with a distribution different from the training data. This means that once the application scenario changes, new data needs to be annotated and the model needs to be retrained with the new data in order to achieve normal performance. This is undoubtedly time-consuming and expensive. Therefore, domain adaptive semantic segmentation algorithms provide a solution to the problem of the model's performance degradation on data with different distributions. This article summarizes the cutting-edge progress of domain adaptive semantic segmentation algorithms and looks forward to future research directions.
Key words : domain adaptive;semantic segmentation;deep learning
引言
語義分割是計算機視覺的基礎(chǔ)任務(wù)之一,它為圖像的每個像素進行類別預(yù)測,目的是將圖像分割成若干個帶有語義的感興趣區(qū)域,以便后續(xù)的圖像理解和分析工作,推動了自動駕駛、虛擬現(xiàn)實、醫(yī)學(xué)影像分析和衛(wèi)星成像等領(lǐng)域的發(fā)展。近幾年來,語義分割模型的性能有著巨大的提升。然而,模型的性能依賴于大量人工標(biāo)注的訓(xùn)練數(shù)據(jù),這些數(shù)據(jù)的標(biāo)注是十分耗時且代價昂貴的,純?nèi)斯?biāo)注一張圖的時間甚至可能超過一個小時。即使現(xiàn)在使用半自動化標(biāo)注工具自動生成一部分標(biāo)注,可以減少標(biāo)注的時間,但仍然需要人工去調(diào)整和檢查自動生成的標(biāo)注。語義分割模型需要在與訓(xùn)練數(shù)據(jù)分布一致的數(shù)據(jù)上才能獲得優(yōu)異的性能,而為另一不同分布的數(shù)據(jù)進行語義標(biāo)注的代價很大。
本文詳細(xì)內(nèi)容請下載:
http://ihrv.cn/resource/share/2000005825
作者信息:
應(yīng)俊杰1,2,樓陸飛1,2,辛宇1,2
(1.寧波大學(xué) 信息科學(xué)與工程學(xué)院, 浙江 寧波315211;2.浙江省移動網(wǎng)應(yīng)用技術(shù)重點實驗室,浙江 寧波315211)

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
