$$CONVOLUTION AND POOLING OPERATION MODULE WITH ADAPTIVE STRIDE PROCESSING EFFEC$$

雪枫 刘, 志勇 林

Keywords: convolution, pooling, adaptive, stride

Abstract:

$$Convolutional neural network is one of the representative models of deep learning,
which has a wide range of applications. Convolution and pooling are two key op-
erations in convolutional neural networks. They play an important role in extract-
ing input features and mapping low-level semantic features to high-level semantic
features. Stride is an important parameter involved in convolution and pooling
operations, which refers to the distance of each slide of the convolution kernel
(pooling kernel) during the convolution (pooling) operation. The stride has an
impact on the granularity of feature extraction and the selection (filtering) of fea-
tures, thus affecting the performance of convolutional neural networks. At present,
in the training of convolutional neural networks, the content of convolution ker-
nel and pooling kernel can be determined by the optimization algorithm based
on gradient descent. However, the stride usually cannot be treated similarly, and
can only be selected manually as a hyperparameter. Most of the existing related
works choose a fixed stride, for example, the value is 1. In fact, different tasks
or inputs may require different stride for better model processing. Therefore, this
paper views the role of stride in convolution and pooling operation from the per-
spective of sampling, and proposes a convolution and pooling operation module
with adaptive stride processing effect. The feature of the proposed module is that
the feature map finally obtained by convolution or pooling operation is no longer
limited to equal interval downsampling (feature extraction) according to a fixed
stride, but adaptively extracted according to the changes of input features. We ap-
ply the proposed module on many convolutional neural network models, including
VGG, Alexnet and MobileNet for image classification, YOLOX-S for object de-
tection, Unet for image segmentation, and so on. Simulation results show that the
proposed module can effectively improve the perform$$

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning