Efficient CNN Architecture for Multi-Modal Aerial View Object Classification

Casian Miron, Alexandru Pasarica, Radu Timofte; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 560-565

Abstract


The NTIRE 2021 workshop features a Multi-modal Aerial View Object Classification Challenge. Its focus is on multi-sensor imagery classification in order to improve the performance of automatic target recognition (ATR) systems. In this paper we describe our entry in this challenge, a method focused on efficiency and low computational time, while maintaining a high level of accuracy. The method is a convolutional neural network with 11 convolutions, 1 max pooling layers and 3 residual blocks which has a total of 373.130 parameters. The method ranks 3rd in the Track 2 (SAR+EO) of the challenge.

Related Material


[pdf]
[bibtex]
@InProceedings{Miron_2021_CVPR, author = {Miron, Casian and Pasarica, Alexandru and Timofte, Radu}, title = {Efficient CNN Architecture for Multi-Modal Aerial View Object Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {560-565} }