[{"data":1,"prerenderedAt":37},["ShallowReactive",2],{"post-document:\u002Fdeep_learning\u002Fcomputer_vision\u002F2026\u002F08\u002F06\u002Fcnn-architectures\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-cnn-architectures.md","CNN 아키텍처 발전 과정",{"type":7,"value":8,"toc":13},"minimark",[9],[10,11,12],"p",{},"CNN 발전 흐름\nCNN의 기본 구조\nAlexNet이 중요했던 이유\nVGG와 깊은 네트워크\nResNet과 Skip Connection\nDenseNet의 Feature Reuse\nMobileNet과 Depthwise Separable Convolution\nEfficientNet과 Compound Scaling\nConvNeXt가 CNN을 현대화한 방법",{"title":14,"searchDepth":15,"depth":15,"links":16},"",2,[],[18,19],"Deep_Learning","Computer_Vision","2026-08-06 00:00:00 +0900","AlexNet부터 VGG, ResNet, DenseNet, MobileNet, EfficientNet, ConvNeXt까지 CNN의 발전 흐름을 정리한다.","md",null,"\u002Fdeep_learning\u002Fcomputer_vision\u002F2026\u002F08\u002F06\u002Fcnn-architectures\u002F",{"layout":26},"post",true,"\u002Fposts\u002Fdeep_learning\u002Fcomputer_vision\u002F2026-08-06-cnn-architectures",{"title":5,"description":21},"posts\u002FDeep_Learning\u002FComputer_Vision\u002F2026-08-06-cnn-architectures","주요 CNN 아키텍처가 발전한 과정과 핵심 아이디어를 정리한다.",[33,34,35],"Deep Learning","Computer Vision","CNN","bTNA6y6J8cSGw7Kkh-RPg0Qv7GfKDcoCRXrXuaYCv2s",1788744788665]