Branchynet: Fast inference via early exiting from deep neural networks

• paper

关键词：提前结束

• 收益：在保持性能的前提下，加速网络推断速度；削减梯度消失现象。
• 评判标准：分类信息熵，信息熵低于设定阈值，则从该退出点退出。（At each exit point, BranchyNet uses the entropy of a classification result (e.g., by softmax) as a measure of confidence in the prediction. If the entropy of a test sample is below a learned threshold value, meaning that the classifier is confident in the prediction, the sample exits the network with the prediction result at this exit point, and is not processed by the higher network layers. If the entropy value is above the threshold, then the classifier at this exit point is deemed not confident, and the sample continues to the next exit point in the network. If the sample reaches the last exit point, which is the last layer of the baseline neural network, it always performs classification.）

• 优化准则：联合优化（BranchyNet jointly optimizes the weighted loss of all exit points）

  
  
  network.png

实现细节

• 退出点的位置，与训练集相关，如果较简单，退出点靠前，反之靠后

• 退出点的阈值，模型训练完成后，根据测试样本选定（fig4）

  
  
  fig4.png

• 训练时样本的通路，每个branch都会走到
  
  其中每个退出点的权值根据实际情况确定，一般靠近入口的退出点权值更大