Page
%P
![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Rethinking the Value of Local Feature Fusion in Convolutional Neural Networks
Traditional CNN head for classification tasks typically consists of a global average pooling layer before the last fully-connected classifier. However, such a simple and light-weighted head lacks the ability o...
-
Article
Root quantization: a self-adaptive supplement STE
Low precision deep neural network model quantization can further reveal stronger abilities of models such as shorter inference time, lower energy consumption and memory usage, but meanwhile induce performance ...