Training lightweight network from scratch for efficient object detection in aerial images

Ang Su; Pengyu Guo; Banglei Guan

doi:10.1117/12.2535479

7 October 2019 Training lightweight network from scratch for efficient object detection in aerial images

Ang Su, Pengyu Guo, Banglei Guan

Proceedings Volume 11155, Image and Signal Processing for Remote Sensing XXV; 111551P (2019) https://doi.org/10.1117/12.2535479
Event: SPIE Remote Sensing, 2019, Strasbourg, France

Abstract

Object detection in aerial images plays an important role for a wide range of applications. Although many efforts have been done in the last decade, it is still an active and challenging problem because of the highly complex backgrounds and the large variations in the visual appearance of objects caused by viewpoint variation, occlusion, illumination, etc. Recently, many object detectors based on deep learning demonstrate the great advantages for significantly improving the detection performance in aerial images. However, the most accuracy neural networks usually have hundreds of layers and thousands of channels, thus requiring huge computation and memory consumption. Besides, the state-of-the-art object detectors are usually fined-tuned from the models pretrained on classification dataset ImageNet, which limits the modification of network architecture and also leads to learning bias because of the different domains. In this paper we trained a lightweight convolutional neural network from scratch to perform object detection in aerial images. When designing the lightweight network, Concatenated Rectified Linear Units (CReLU) and depthwise separable convolution operation were employed to reduce the computation cost and model size. When training the lightweight network from scratch, we employ Group Normalization (GN) in each convolution layer, which makes smoother optimization landscape and has more stable gradients. A serial of ablation experiments is conducted on the recently published large-scale Dataset for Object detection in Aerial images (DOTA), and the results show that the proposed object detection methods with lightweight network trained from scratch achieves competitive performance but has smaller model size and lower computation cost.

Citation Download Citation

Ang Su, Pengyu Guo, and Banglei Guan "Training lightweight network from scratch for efficient object detection in aerial images", Proc. SPIE 11155, Image and Signal Processing for Remote Sensing XXV, 111551P (7 October 2019); https://doi.org/10.1117/12.2535479

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Network architectures

Sensors

Performance modeling

Data modeling

Neural networks

Defense technologies

Show All Keywords

Keywords/Phrases

Search In:

Publication Years