scholarly journals Transfer Incremental Learning Using Data Augmentation

2018 ◽  
Vol 8 (12) ◽  
pp. 2512 ◽  
Author(s):  
Ghouthi Boukli Hacene ◽  
Vincent Gripon ◽  
Nicolas Farrugia ◽  
Matthieu Arzel ◽  
Michel Jezequel
Keyword(s):  
Incremental Learning ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Low Complexity ◽  
Computational Power ◽  
Learning Problem ◽  
Learning Techniques ◽  
Using Data ◽  
Selection Of

Deep learning-based methods have reached state of the art performances, relying on a large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem, which consists of learning incrementally new classes and examples over time. Combining the outstanding performances of Deep Neural Networks (DNNs) with the flexibility of incremental learning techniques is a promising venue of research. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA is based on pre-trained DNNs as feature extractors, robust selection of feature vectors in subspaces using a nearest-class-mean based technique, majority votes and data augmentation at both the training and the prediction stages. Experiments on challenging vision datasets demonstrate the ability of the proposed method for low complexity incremental learning, while achieving significantly better accuracy than existing incremental counterparts.

scholarly journals Redes neurais convolucionais aplicas à detecção de objetos no domínio de futebol de robôs humanoides

2021 ◽  
Author(s):  
◽  
Lucas Ribeiro de Abreu
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Critical System ◽  
Test Set ◽  
Learning Techniques ◽  
Using Data ◽  
Vision Module

The RoboCup Soccer is one of the largest initiatives in the robotics field of research. This initiative considers the soccer match as a challenge for the robots and aims to win a match between humans versus robots by the year of 2050. The vision module is a critical system for the robots because it needs to quickly locate and classify objects of interest for the robot in order to generate the next best action. This work evaluates deep neural networks for the detection of the ball and robots. For such task, five convolutional neural networks architectures were trained for the experiment using data augmentation and transfer learning techniques. The models were evaluated in a test set, yielding promising results in precision and frames per second. The best model achieved an mAP of 0.98 and 14.7 frames per second, running on CPU

scholarly journals Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Nadin Ulrich ◽  
Kai-Uwe Goss ◽  
Andrea Ebert
Keyword(s):  
Partition Coefficient ◽  
Data Augmentation ◽  
Environmental Chemistry ◽  
Chemical Properties ◽  
Predictive Performance ◽  
Chemical Structures ◽  
Tautomeric Forms ◽  
Learning Techniques ◽  
Water Partition Coefficient ◽  
Using Data

AbstractToday more and more data are freely available. Based on these big datasets deep neural networks (DNNs) rapidly gain relevance in computational chemistry. Here, we explore the potential of DNNs to predict chemical properties from chemical structures. We have selected the octanol-water partition coefficient (log P) as an example, which plays an essential role in environmental chemistry and toxicology but also in chemical analysis. The predictive performance of the developed DNN is good with an rmse of 0.47 log units in the test dataset and an rmse of 0.33 for an external dataset from the SAMPL6 challenge. To this end, we trained the DNN using data augmentation considering all potential tautomeric forms of the chemicals. We further demonstrate how DNN models can help in the curation of the log P dataset by identifying potential errors, and address limitations of the dataset itself.

scholarly journals Deep Recurrent Neural Networks for Edge Monitoring of Personal Risk and Warning Situations

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Emanuele Torti ◽  
Mirto Musci ◽  
Federico Guareschi ◽  
Francesco Leporati ◽  
Marco Piastra
Keyword(s):  
Power Consumption ◽  
Hospital Admissions ◽  
State Of The Art ◽  
Computational Power ◽  
Wearable System ◽  
Personal Risk ◽  
Learning Techniques ◽  
Unintentional Falls ◽  
Nonfatal Injuries

Accidental falls are the main cause of fatal and nonfatal injuries, which typically lead to hospital admissions among elderly people. A wearable system capable of detecting unintentional falls and sending remote notifications will clearly improve the quality of the life of such subjects and also helps to reduce public health costs. In this paper, we describe an edge computing wearable system based on deep learning techniques. In particular, we give special attention to the description of the classification and communication modules, which have been developed by keeping in mind the limits in terms of computational power, memory occupancy, and power consumption of the designed wearable device. The system thus developed is capable of classifying 3D-accelerometer signals in real-time and to issue remote alerts while keeping power consumption low and improving on the present state-of-the-art solutions in the literature.

scholarly journals Real-time Ball Detection for Robocup Soccer Using Convolutional Neural Networks

2019 ◽  
Author(s):  
Lucas Ribeiro De Abreu ◽  
Reinaldo Augusto da Costa Bianchi
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Average Precision ◽  
Critical System ◽  
Soccer Ball ◽  
Learning Techniques ◽  
Using Data ◽  
Vision Module ◽  
Ball Detection

The RoboCup Soccer is one of the largest competitions in the robotics field of research. It considers the soccer match as a challenge for the robots and aims to win a match between humans versus robots by the year of 2050. The vision module is a critical system for the robots because it needs to quickly locate and classify objects of interest for the robot in order to generate the next best action. In this paper, an approach using Convolutional Neural Networks for object detection is described. The soccer ball is the chosen object and three state-ofart convolutional neural networks architectures were trained for the experiment using data augmentation and transfer learning techniques. The models were evaluated in a test set, yielding promising results in precision and frames per second. The best model achieved an average precision of 0.972 with an intersection over union of 50% and 9.64 frames per second, running on CPU.

scholarly journals A Survey of Handwritten Character Recognition with MNIST and EMNIST

2019 ◽  
Vol 9 (15) ◽  
pp. 3169 ◽  
Author(s):  
Alejandro Baldominos ◽  
Yago Saez ◽  
Pedro Isasi
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Data Augmentation ◽  
State Of The Art ◽  
Handwritten Digit Recognition ◽  
Test Error ◽  
Digit Recognition ◽  
Original Dataset ◽  
Learning Techniques ◽  
Handwritten Digit

This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST’s. In this paper, EMNIST is explained and some results are surveyed.

scholarly journals VivesDebate: A New Annotated Multilingual Corpus of Argumentation in a Debate Tournament

2021 ◽  
Vol 11 (15) ◽  
pp. 7160
Author(s):  
Ramon Ruiz-Dolz ◽  
Montserrat Nofre ◽  
Mariona Taulé ◽  
Stella Heras ◽  
Ana García-Fornes
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Argument Analysis ◽  
Argument Evaluation ◽  
Learning Techniques ◽  
Multilingual Corpus ◽  
Computational Argumentation

The application of the latest Natural Language Processing breakthroughs in computational argumentation has shown promising results, which have raised the interest in this area of research. However, the available corpora with argumentative annotations are often limited to a very specific purpose or are not of adequate size to take advantage of state-of-the-art deep learning techniques (e.g., deep neural networks). In this paper, we present VivesDebate, a large, richly annotated and versatile professional debate corpus for computational argumentation research. The corpus has been created from 29 transcripts of a debate tournament in Catalan and has been machine-translated into Spanish and English. The annotation contains argumentative propositions, argumentative relations, debate interactions and professional evaluations of the arguments and argumentation. The presented corpus can be useful for research on a heterogeneous set of computational argumentation underlying tasks such as Argument Mining, Argument Analysis, Argument Evaluation or Argument Generation, among others. All this makes VivesDebate a valuable resource for computational argumentation research within the context of massive corpora aimed at Natural Language Processing tasks.

scholarly journals DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images

2021 ◽  
Vol 13 (14) ◽  
pp. 2743
Author(s):  
Kun Sun ◽  
Yi Liang ◽  
Xiaorui Ma ◽  
Yuanyuan Huai ◽  
Mengdao Xing
Keyword(s):  
Target Detection ◽  
Data Augmentation ◽  
State Of The Art ◽  
Low Cost ◽  
Detection Performance ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Constant False Alarm Rate ◽  
Computation Complexity ◽  
Learning Techniques

Traditional constant false alarm rate (CFAR) based ship target detection methods do not work well in complex conditions, such as multi-scale situations or inshore ship detection. With the development of deep learning techniques, methods based on convolutional neural networks (CNN) have been applied to solve such issues and have demonstrated good performance. However, compared with optical datasets, the number of samples in SAR datasets is much smaller, thus limiting the detection performance. Moreover, most state-of-the-art CNN-based ship target detectors that focus on the detection performance ignore the computation complexity. To solve these issues, this paper proposes a lightweight densely connected sparsely activated detector (DSDet) for ship target detection. First, a style embedded ship sample data augmentation network (SEA) is constructed to augment the dataset. Then, a lightweight backbone utilizing a densely connected sparsely activated network (DSNet) is constructed, which achieves a balance between the performance and the computation complexity. Furthermore, based on the proposed backbone, a low-cost one-stage anchor-free detector is presented. Extensive experiments demonstrate that the proposed data augmentation approach can create hard SAR samples artificially. Moreover, utilizing the proposed data augmentation approach is shown to effectively improves the detection accuracy. Furthermore, the conducted experiments show that the proposed detector outperforms the state-of-the-art methods with the least parameters (0.7 M) and lowest computation complexity (3.7 GFLOPs).

scholarly journals Towards Robust Object detection in Floor Plan Images: A Data Augmentation Approach

2021 ◽  
Author(s):  
Shashank Mishra ◽  
Khurram Azeem Hashmi ◽  
Alain Pagani ◽  
Marcus Liwicki ◽  
Didier Stricker ◽  
...  
Keyword(s):  
Object Detection ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
The Novel ◽  
Floor Plan ◽  
Previous State ◽  
Floor Plans ◽  
Public Datasets ◽  
Better Than

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

scholarly journals Fingerspelling Identification for Chinese Sign Language via AlexNet-Based Transfer Learning and Adam Optimizer

2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Xianwei Jiang ◽  
Bo Hu ◽  
Suresh Chandra Satapathy ◽  
Shui-Hua Wang ◽  
Yu-Dong Zhang
Keyword(s):  
Language Learning ◽  
Sign Language ◽  
Transfer Learning ◽  
Gradient Descent ◽  
Data Augmentation ◽  
State Of The Art ◽  
Stochastic Gradient Descent ◽  
Mean Square ◽  
Average Accuracy ◽  
Using Data

As an important component of universal sign language and the basis of other sign language learning, finger sign language is of great significance. This paper proposed a novel fingerspelling identification method for Chinese Sign Language via AlexNet-based transfer learning and Adam optimizer, which tested four different configurations of transfer learning. Besides, in the experiment, Adam algorithm was compared with stochastic gradient descent with momentum (SGDM) and root mean square propagation (RMSProp) algorithms, and comparison of using data augmentation (DA) against not using DA was executed to pursue higher performance. Finally, the best accuracy of 91.48% and average accuracy of 89.48 ± 1.16% were yielded by configuration M1 (replacing the last FCL8) with Adam algorithm and using 181x DA, which indicates that our method can identify Chinese finger sign language effectively and stably. Meanwhile, the proposed method is superior to other five state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document