Construction of a virtual reality platform for UAV deep learning

S Wang, J Chen, Z Zhang, G Wang… - 2017 Chinese …, 2017 - ieeexplore.ieee.org
In this paper, based on Unreal Engine 4 (UE4) Unmanned Aerial Vehicle (UAV) simulator
(AirSim), through AirLib, DroneServe, DroneShell and other modules in AirSim, using …

DLANet: a manifold-learning-based discriminative feature learning network for scene classification

Z Feng, L **, D Tao, S Huang - Neurocomputing, 2015 - Elsevier
Abstract This paper presents Discriminative Locality Alignment Network (DLANet), a novel
manifold-learning-based discriminative learnable feature, for wild scene classification …

Beyond spatial pooling: fine-grained representation learning in multiple domains

C Li, A Reiter, GD Hager - Proceedings of the IEEE …, 2015 - openaccess.thecvf.com
Object recognition systems have shown great progress over recent years. However, creating
object representations that are robust to changes in viewpoint while capturing local visual …

Learning to pool high-level features for face representation

R Huang, M Ye, P Xu, T Li, Y Dou - The Visual Computer, 2015 - Springer
The available face descriptors are always generated by a hand-designed pooling scheme or
without a pooling process. We propose to learn a pooling scheme for high-level features …

Fine-grained representation learning in convolutional autoencoders

C Luo, J Wang - Journal of Electronic Imaging, 2016 - spiedigitallibrary.org
Convolutional autoencoders (CAEs) have been widely used as unsupervised feature
extractors for high-resolution images. As a key component in CAEs, pooling is a biologically …

Learning color receptive fields and color differential structure

BM ter Haar Romeny - 2015 11th International Conference on …, 2015 - ieeexplore.ieee.org
In this paper we study the role of brain plasticity, and investigate the emergence and self-
emergence of receptive fields from scalar and color natural images by principal component …

多尺度特征 DCA 融合的海上船舶检测算法研究.

潘慧, 段先华, 罗斌** - Journal of Computer Engineering & …, 2022 - search.ebscohost.com
为了加**海上交通的安全性, 以常见的民用船和军用船为研究对象, 针对原始YOLOV3
算法在船舶数据集上检测精度不高, 目标框出现误检和小目标漏检的问题 …