基於多模型共識實現類別增量式語意分割問題之研究;M2CB: Incremental Semantic Segmentation via Multiple Model Consensus Building

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/98218

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/98218

题名:	基於多模型共識實現類別增量式語意分割問題之研究;M2CB: Incremental Semantic Segmentation via Multiple Model Consensus Building
作者:	許俊偉;Hsu, Chun-Wei
贡献者:	資訊工程學系
关键词:	增量式學習;語義分割;模型共識;Incremental Learning;Semantic Segmentation;Model Consensus
日期:	2025-07-11
上传时间:	2025-10-17 12:30:28 (UTC+8)
出版者:	國立中央大學
摘要:	隨著深度學習技術快速發展，傳統模型需面對資料量不斷增加所帶來的挑戰。每次更新資料都需重新訓練整個模型，不僅耗費資源，亦可能受限於硬體與隱私問題。相較之下，增量式學習能在不重新訓練的情況下快速吸收新知，大幅降低訓練成本，更適合應對持續變動的資料環境。在眾多應用中，語意分割作為一項像素級別的分類任務，廣泛應用於自動駕駛、醫療影像與智慧監控等領域。然而，隨著任務需求不斷演進，模型必須學習新的類別，這也使得類別增量式語意分割（Class-Incremental Semantic Segmentation, CISS）成為一項重要課題。 CISS 面臨嚴重的挑戰，主要來自於災難性遺忘與背景偏移問題。雖然現有方法多依賴標記資料，逐步微調模型以學習新任務，但當僅有多個已訓練完成的模型可用，且無法取得舊任務或新任務的標記資料時，此類方法將難以實際應用。為了解決此問題，我們提出多模型共識機制（Multiple Model Consensus Building, M2CB），此方法利用多個預訓練模型對無標記資料的輸出結果，透過建立模型間的預測共識及選擇性地蒸餾可信知識，進行模型整合。實驗部分使用 Pascal VOC 2012 作為訓練資料集，並以 MS COCO 2017 作為無標記輔助資料來源。實驗結果顯示， M2CB在三個連續任務下，平均交集比分別較現有方法提升 6.31% 與 16.15%，驗證了所提方法在無標記情境下的有效性。關鍵字：增量式學習、語義分割、模型共識;With the advancement of deep learning technologies, traditional models face increasing challenges as data volumes grow. Re-training the entire model for every update is computationally expensive and may be limited by hardware constraints or data privacy concerns. In contrast, incremental learning enables efficient knowledge acquisition from new data without retraining from scratch, significantly reducing training costs and better accommodating dynamic data environments. Among various applications, semantic segmentation, a pixel-level classification task, is widely used in domains such as autonomous driving, medical imaging and smart surveillance. However, as task demands evolve, models are required to learn new classes over time, giving rise to the challenge of class-incremental semantic segmentation (CISS). CISS faces significant challenges due to catastrophic forgetting and background shift problems. While existing approaches typically rely on labeled data to progressively finetune models for new tasks, these methods become impractical when only multiple pre-trained models are available or when labeled data cannot be accessed for either old or new tasks. To address this issue, we propose a novel approach called Multiple Model Consensus Building (M2CB), which leverages predictions from multiple pre-trained models on unlabeled data. M2CB selectively distills trustworthy knowledge by identifying consensus among the models′ predictions. We evaluate M2CB using the Pascal VOC 2012 dataset as training data and MS COCO 2017 as the source of unlabeled auxiliary data. Experimental results demonstrate the effectiveness of our approach, achieving 6.31% and 16.15% improvement in mean Intersection over Union (mIoU) compared to existing methods after incorporating three consecutive tasks. Keywords: Incremental Learning, Semantic Segmentation, Model Consensus
显示于类别:	[資訊工程研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	15	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....