My Vision, Computer Vision

MobileNetV2: Inverted Residuals and Linear BottlenecksIn this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of apparxiv.orgAbstractMobileNet V1의 성능을 개선Object detection에 효율적인 적용 방법 SSDLite 소개Semantic seg..

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce tw arxiv.org Abstract MobileNet 탄생 배경 : 모바일 및 임베디드 비전 응용 프로그램..