Journal Article10.1016/J.COMPAG.2021.106418
Data augmentation for deep learning based semantic segmentation and crop-weed classification in agricultural robotics
96
TL;DR: Comprehensive experimental evaluations and ablation studies show that the proposed framework can effectively improve segmentation accuracies, and the enhancements made over the original RICAP actually contribute to the performance gain.
read more
About: This article is published in Computers and Electronics in Agriculture. The article was published on 01 Nov 2021. The article focuses on the topics: Deep learning & Overfitting.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Data Augmentation in Classification and Segmentation: A Survey and New Strategies
TL;DR: In this article, the random local rotation strategy (RLR) is proposed to select the location and size of circular regions in the image and rotate them with random angles to solve the problem of overfitting.
A comparative study of deep learning and Internet of Things for precision agriculture
TL;DR: In this article , a bootstrapping approach of transfer learning where fine-tuned VGG16 is fused with optimized and improved newly built fully connected layers for pest detection was proposed, which outperformed all other models with an accuracy of 96.58 % and a loss of 0.15%.
106
Practical cucumber leaf disease recognition using improved Swin Transformer and small sample size
TL;DR: In this paper , a backbone network based on improved SwinT was proposed and applied to the data augmentation and recognition of practical cucumber leaf diseases, where patch partitioning of SwinTransformer was improved by step-wise small patch embeddings for enhancing the ability of feature extraction without increasing the number of parameters.
74
Deformable convolution and coordinate attention for fast cattle detection
TL;DR: Li et al. as discussed by the authors proposed a deformable convolution to capture more fine-grained spatial information and coordinate attention to emphasize important features in the detection process, which achieved a mean average precision (mAP) of 72.9% at 62.5 frames per second.
65
Vision systems for harvesting robots: Produce detection and localization
Luis-Enrique Montoya-Cavero,Rocío Díaz de León Torres,Alfonso Gómez-Espinosa,Jesús Arturo Escobedo Cabello +3 more
TL;DR: In this paper, the authors provide up-to-date information regarding the state of harvesting robots' vision subsystems, focusing on produce detection and localization research with special attention to the new technology that is being used.
57
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Posted Content
Explaining and Harnessing Adversarial Examples
TL;DR: The authors argue that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature, which is supported by new quantitative results while giving the first explanation of the most intriguing fact about adversarial examples: their generalization across architectures and training sets.
15.9K
Identity Mappings in Deep Residual Networks
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 08 Oct 2016
TL;DR: In this paper, the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.
•Posted Content
Improving neural networks by preventing co-adaptation of feature detectors
TL;DR: The authors randomly omits half of the feature detectors on each training case to prevent complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors.
Wide Residual Networks
Sergey Zagoruyko,Nikos Komodakis +1 more
- 01 Jan 2016
TL;DR: This paper conducts a detailed experimental study on the architecture of ResNet blocks and proposes a novel architecture where the depth and width of residual networks are decreased and the resulting network structures are called wide residual networks (WRNs), which are far superior over their commonly used thin and very deep counterparts.