Absorption Pruning of Deep Neural Network for Object Detection in Remote Sensing Imagery

Abstract

In recent years, deep convolutional neural networks (DCNNs) have been widely used for object detection tasks in remote sensing images. However, the over-parametrization problem of DCNNs hinders their application in resource-constrained remote sensing devices. In order to solve this problem, we propose a network pruning method (named absorption pruning) to compress the remote sensing object detection network. Unlike the classical iterative three-stage pruning pipeline used in existing methods, absorption pruning is designed as a four-stage pruning pipeline that only needs to be executed once, which differentiates it from existing methods. Furthermore, the absorption pruning no longer identifies unimportant filters, as in existing pruning methods, but instead selects filters that are easy to learn. In addition, we design a method for pruning ratio adjustment based on the object characteristics in remote sensing images, which can help absorption pruning to better compress deep neural networks for remote sensing image processing. The experimental results on two typical remote sensing data sets—SSDD and RSOD—demonstrate that the absorption pruning method not only can remove 60% of the filter parameters from CenterNet101 harmlessly but also eliminate the over-fitting problem of the pre-trained network.

G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection

“…For example, Wang et al [40] proposed an adaptive feature-aware method, which performs brilliantly in real-time object detection tasks. Wang et al [41] proposed an absorption pruning method for the object detection network in remote-sensing images. Tong et al [42] designed a compound semantic feature fusion method to generate an effective semantic description for better pixel-wise object center point interpretation.…”

SCCMDet: Adaptive Sparse Convolutional Networks Based on Class Maps for Real-Time Onboard Detection in Unmanned Aerial Vehicle Remote Sensing Images

“…The authors of [1][2][3] mainly focus on reducing the complexity of the computational backbone or designing a backbone suitable for edge devices. In addition, several methods have been proposed to address this issue, including network pruning [4,5] and model distillation, which have been proven effective at accelerating inference. These methods are not novel methods and can be used to accelerate any model by sacrificing performance.…”