C3-AMP

2000년 도입 · 논문 1편에서 사용

In our proposed concept, we use an Inception layer after a convolutional layer with a kernel size of 1, and then, after performing batch normalization and the SILU activation function, we concatenate the output of this layer with the input of the bottleneck and pass it to the next layer. Moreover, in the other branch of C3-AMP, after performing a convolutional layer, a max pooling layer is employed, and then after concatenating the output of this layer with the output of bottleneck series, another convolutional layer with a kernel size of 1 is utilized.

출처: Inception-YOLO: Computational cost and accuracy improvement of the YOLOv5 model based on employing modified CSP, SPPF, and inception modules

소개 논문: Inception-YOLO: Computational cost and accuracy improvement of the YOLOv5 model based on employing modified CSP, SPPF, and inception modules