Localization-aware Channel Pruning for Object Detection

11/06/2019
by   Zihao Xie, et al.
11

Channel pruning is one of the important methods for deep model compression. Most of existing pruning methods mainly focus on classification. Few of them are designed for object detection. However, object detection is different from classification, which requires not only semantic information but also localization information. In this paper, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources. In order to capture the localization information, we first design the auxiliary network with a local feature extraction layer which can obtain precise localization information of the default boxes by pixel alignment. Then, we propose an algorithm for adaptively adjusting the sampling area which enlarges the receptive fields of the default boxes when pruning shallow layers. Finally, we propose a scale-aware loss function which tends to keep the channels that contain the key information for classification and regression of small objects. Extensive experiments demonstrate the effectiveness of our method. On VOC2007, we prune 70% parameters of the SSD based on ResNet-50 with modest accuracy drop, which outperforms the-state-of-art method.

READ FULL TEXT

page 3

page 7

research
10/28/2018

Discrimination-aware Channel Pruning for Deep Neural Networks

Channel pruning is one of the predominant approaches for deep model comp...
research
06/02/2023

Group channel pruning and spatial attention distilling for object detection

Due to the over-parameterization of neural networks, many model compress...
research
08/31/2021

AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks

With the increase of structure complexity, convolutional neural networks...
research
04/28/2021

MOD: Benchmark for Military Object Detection

Object detection is widely studied in computer vision filed. In recent y...
research
10/09/2022

Precise Single-stage Detector

There are still two problems in SDD causing some inaccurate results: (1)...
research
01/07/2019

Scale-Aware Trident Networks for Object Detection

Scale variation is one of the key challenges in object detection. In thi...
research
03/31/2022

ImpDet: Exploring Implicit Fields for 3D Object Detection

Conventional 3D object detection approaches concentrate on bounding boxe...

Please sign up or login with your details

Forgot password? Click here to reset