One-Shot Learning with Triplet Loss for Vegetation Classification Tasks

• URL: http://arxiv.org/abs/2012.07403v2
• Date: Fri, 15 Jan 2021 19:34:55 GMT
• Title: One-Shot Learning with Triplet Loss for Vegetation Classification Tasks
• Authors: Alexander Uzhinskiy (1), Gennady Ososkov (1), Pavel Goncharov (1), Andrey Nechaevskiy (1), Artem Smetanin (2) ((1) Joint Institute for Nuclear Research, Dubna, Moscow region, Russia, (2) ITMO University, Saint Petersburg, Russia)
• Abstract summary: Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification.
• Score: 45.82374977939355
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification. In our research, we focused on two tasks related to vegetation. The first one is plant disease detection on 25 classes of five crops (grape, cotton, wheat, cucumbers, and corn). This task is motivated because harvest losses due to diseases is a serious problem for both large farming structures and rural families. The second task is the identification of moss species (5 classes). Mosses are natural bioaccumulators of pollutants; therefore, they are used in environmental monitoring programs. The identification of moss species is an important step in the sample preprocessing. In both tasks, we used self-collected image databases. We tried several deep learning architectures and approaches. Our Siamese network architecture with a triplet loss function and MobileNetV2 as a base network showed the most impressive results in both above-mentioned tasks. The average accuracy for plant disease detection amounted to over 97.8% and 97.6% for moss species classification.

Related papers

• Deep-Wide Learning Assistance for Insect Pest Classification [1.9912919001438378]
  We present DeWi, novel learning assistance for insect pest classification. With a one-stage and alternating training strategy, DeWi simultaneously improves several Convolutional Neural Networks. Experimental results show that DeWi achieves the highest performances on two insect pest classification benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T16:29:41Z)
• Investigation to answer three key questions concerning plant pest identification and development of a practical identification framework [2.388418486046813]
  We develop an accurate, robust, and fast plant pest identification framework using 334K images. Our two-stage plant pest identification framework achieved a highly practical performance of 91.0% and 88.5% in mean accuracy and macro F1 score.
  arXiv  Detail & Related papers  (2024-07-25T12:49:24Z)
• Self-supervised transformer-based pre-training method with General Plant Infection dataset [3.969851116372513]
  This study proposes an advanced network architecture that combines Contrastive Learning and Masked Image Modeling (MIM) The proposed network architecture demonstrates effectiveness in addressing plant pest and disease recognition tasks, achieving notable detection accuracy. Our code and dataset will be publicly available to advance research in plant pest and disease recognition.
  arXiv  Detail & Related papers  (2024-07-20T15:48:35Z)
• Identification of Abnormality in Maize Plants From UAV Images Using Deep Learning Approaches [0.6226366855893847]
  Early identification of abnormalities in plants is an important task for ensuring proper growth and achieving high yields from crops. We have developed a methodology which can detect different levels of abnormality in maize plants independently of their growth stage. Preliminary results show an 88.89% detection accuracy of low abnormality and 100% detection accuracy of no abnormality.
  arXiv  Detail & Related papers  (2023-10-20T00:06:42Z)
• The Power of Transfer Learning in Agricultural Applications: AgriNet [1.9087335681007478]
  We propose AgriNet dataset, a collection of 160k agricultural images from more than 19 geographical locations. We also introduce AgriNet models, a set of pretrained models on five ImageNet architectures. All proposed models were found to accurately classify the 423 classes of plant species, diseases, pests, and weeds with a minimum accuracy of 87%.
  arXiv  Detail & Related papers  (2022-07-08T13:15:16Z)
• Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection [60.83360138070649]
  The paper presents an approach for analyzing aerial images of a potato crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of a healthy versus stressed crop at a plant level. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average Dice coefficient of 0.74.
  arXiv  Detail & Related papers  (2021-06-14T21:57:40Z)
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery [56.10033255997329]
  We propose a novel deep learning method based on a Convolutional Neural Network (CNN) It simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The proposed method achieved state-of-the-art performance for counting and geolocating plants and plant-rows in UAV images from different types of crops.
  arXiv  Detail & Related papers  (2020-12-31T18:51:17Z)
• Why Do Better Loss Functions Lead to Less Transferable Features? [93.47297944685114]
  This paper studies how the choice of training objective affects the transferability of the hidden representations of convolutional neural networks trained on ImageNet. We show that many objectives lead to statistically significant improvements in ImageNet accuracy over vanilla softmax cross-entropy, but the resulting fixed feature extractors transfer substantially worse to downstream tasks.
  arXiv  Detail & Related papers  (2020-10-30T17:50:31Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)
• Automatic image-based identification and biomass estimation of invertebrates [70.08255822611812]
  Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
  arXiv  Detail & Related papers  (2020-02-05T21:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.