[{"data":1,"prerenderedAt":37},["ShallowReactive",2],{"post-document:\u002Fdeep_learning\u002Fcomputer_vision\u002F2026\u002F08\u002F06\u002Fimage-segmentation\u002F":3},{"id":4,"title":5,"body":6,"categories":17,"date":20,"description":21,"extension":22,"image":23,"key_concepts":23,"last_modified_at":23,"legacyPath":24,"meta":25,"navigation":27,"part":23,"path":28,"published":27,"robots":23,"seo":29,"series":23,"stem":30,"strengths":23,"summary":31,"tags":32,"tradeoffs":23,"__hash__":36},"posts\u002Fposts\u002FDeep_Learning\u002FComputer_Vision\u002F2026-08-06-image-segmentation.md","이미지 세그멘테이션 모델과 핵심 개념",{"type":7,"value":8,"toc":13},"minimark",[9],[10,11,12],"p",{},"Semantic, Instance, Panoptic Segmentation\nFCN\nU-Net\nDeepLab 계열\nEncoder–Decoder 구조\nSkip Connection의 역할\nDice Loss와 IoU Loss\nBoundary Refinement\nSmall Object Segmentation\nSAM 계열 모델\nPromptable Segmentation\nOpen-vocabulary Segmentation",{"title":14,"searchDepth":15,"depth":15,"links":16},"",2,[],[18,19],"Deep_Learning","Computer_Vision","2026-08-06 00:00:00 +0900","Semantic, Instance, Panoptic Segmentation의 차이와 주요 이미지 세그멘테이션 모델을 정리한다.","md",null,"\u002Fdeep_learning\u002Fcomputer_vision\u002F2026\u002F08\u002F06\u002Fimage-segmentation\u002F",{"layout":26},"post",true,"\u002Fposts\u002Fdeep_learning\u002Fcomputer_vision\u002F2026-08-06-image-segmentation",{"title":5,"description":21},"posts\u002FDeep_Learning\u002FComputer_Vision\u002F2026-08-06-image-segmentation","이미지 세그멘테이션의 유형과 대표 모델, 학습 개념을 정리한다.",[33,34,35],"Deep Learning","Computer Vision","Image Segmentation","2feOUrIF7gqFWLlfDpxLhf7yO2s8jKBmX-XNFatI1oM",1788744788702]