Inception-v3

2000년 도입 · 논문 98편에서 사용

Inception-v3 is a convolutional neural network architecture from the Inception family that makes several improvements including using Label Smoothing, Factorized 7 x 7 convolutions, and the use of an auxiliary classifer to propagate label information lower down the network (along with the use of batch normalization for layers in the sidehead).

출처: Rethinking the Inception Architecture for Computer Vision

소개 논문: Rethinking the Inception Architecture for Computer Vision