Open Access
Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector
Р Ю Чуйков,Д А Юдин +1 more
- Vol. 2, Iss: 4
Reads0
Chats0
About:
The article was published on 2017-01-01 and is currently open access. It has received 1687 citations till now.read more
Citations
More filters
Proceedings ArticleDOI
Focal Loss for Dense Object Detection
TL;DR: This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Posted Content
Feature Pyramid Networks for Object Detection
TL;DR: Feature pyramid networks (FPNets) as mentioned in this paper exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost.
Journal ArticleDOI
SECOND: Sparsely Embedded Convolutional Detection
Yan Yan,Yuxing Mao,Bo Li +2 more
TL;DR: An improved sparse convolution method for Voxel-based 3D convolutional networks is investigated, which significantly increases the speed of both training and inference and introduces a new form of angle loss regression to improve the orientation estimation performance.
Journal ArticleDOI
A State-of-the-Art Survey on Deep Learning Theory and Architectures
Zahangir Alom,Tarek M. Taha,Chris Yakopcic,Stefan Westberg,Paheding Sidike,Mst Shamima Nasrin,Mahmudul Hasan,Brian Van Essen,Abdul A. S. Awwal,Vijayan K. Asari +9 more
TL;DR: This survey presents a brief survey on the advances that have occurred in the area of Deep Learning (DL), starting with the Deep Neural Network and goes on to cover Convolutional Neural Network, Recurrent Neural Network (RNN), and Deep Reinforcement Learning (DRL).
Journal ArticleDOI
A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition
TL;DR: A deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions, and combines each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network.
References
More filters
Proceedings ArticleDOI
Dense feature pyramid network for ship detection in SAR images
TL;DR: Compared with conventional FPN, DenseFPN is integrated into Faster R-CNN framework and thus form a novel detector and experiments on high-resolution SAR images dataset (HRSID) have verified the effectiveness of the enhanced hierarchical feature in the proposed method compared with other typical CNN based methods.
Journal ArticleDOI
Long-term temporal averaging for stochastic optimization of deep neural networks
TL;DR: This work proposes an advanced temporal averaging technique that is capable of stabilizing the convergence of stochastic optimization for neural network training and reduces the risk of stopping the training process when a bad descent step was taken and the learning rate was not appropriately set.
Proceedings ArticleDOI
Multi-Domain Attentive Detection Network
TL;DR: Experimental results on the FLIR dataset demonstrate that the MDADN outperforms state-of-the-art methods in terms of accuracy and speed, and the ablation study shows that the attention module and the fusion of multiple data sources help to considerably improve the accuracy.
Journal ArticleDOI
Instance Segmentation of Traffic Scene Based on YOLACT
TL;DR: The backbone in the YOLACT algorithm is changed from the original resnet50 to the lightweight resnet18 to ensure that the algorithm can be deployed on Jetson-AGX-Xavier, and the processing speed can reach 9.4 frames per second.
Posted ContentDOI
A fully automated deep learning pipeline for high-throughput colony segmentation and classification
Sarah H. Carl,Sarah H. Carl,Lea Duempelmann,Lea Duempelmann,Yukiko Shimada,Marc Bühler,Marc Bühler +6 more
TL;DR: Using cutting-edge neural networks, a fully automated pipeline for colony segmentation and classification is developed, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher.