ABNet
ANDHRA Bandersnatch Network
2000년 도입 · 논문 1편에서 사용
A CNN-based network that uses the ANDHRA module to split the network into multiple parallel branches, leading to multiple network outputs. For a network with three ANDHRA modules with a branching factor of two, the total output heads are 2ˆ3 = 8.
출처: ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities
소개 논문: ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities
Convolutional Neural Networks · Computer Vision