學術論文句式（一）

1. As there only two parameters per feature map, the total number of BN parameters comprise less than 1% of the total number of parameters of a pre-trained ResNet.
2. To summarize, our contributions are three fold:
3. Specifically, we applied CBN to a pre-trained ResNet, leading to the proposed MODERN architecture.
4. trainable scalars introduced to keep the representational power of the original network.
5. As we will explain in the next section, adhering to this assumption will give rise to a structure of the discriminator that requires us to take an inner product between the embedded condition vector y and the feature vector
6. \ie可以被替換爲“including”
7. On one hand, our method achieves very good accuracy in all cases despite that there are no clear winner for all cases in our experiment.
8. We empirically set the number of bins for handling point orders in each convolution as 4, 2, 1, respectively, which strikes a good balance between accuracy and speed. This setting ensures that each bin contains points approximately.
9. as a fidelity term …
10. We think of the following reasons.
11. This indicates that simply enlarging the difference without restriction will create turbulence in the training process, resulting in a worse classification performance.
12. In general, the neighborhood has to be large enough for capturing
    the point distribution and features robustly but not too large that causes too much overhead.