scholarly journals Hierarchical Classification Based on Label Distribution Learning

2019 ◽  
Vol 33 ◽  
pp. 5533-5540 ◽  
Author(s):  
Changdong Xu ◽  
Xin Geng
Keyword(s):  
Hierarchical Classification ◽  
Experimental Results ◽  
Challenging Problem ◽  
Training Set ◽  
True Label ◽  
Major Bottleneck ◽  
Novel Method ◽  
Class Labels ◽  
Label Distribution ◽  
The Given

Hierarchical classification is a challenging problem where the class labels are organized in a predefined hierarchy. One primary challenge in hierarchical classification is the small training set issue of the local module. The local classifiers in the previous hierarchical classification approaches are prone to over-fitting, which becomes a major bottleneck of hierarchical classification. Fortunately, the labels in the local module are correlated, and the siblings of the true label can provide additional supervision information for the instance. This paper proposes a novel method to deal with the small training set issue. The key idea of the method is to represent the correlation among the labels by the label distribution. It generates a label distribution that contains the supervision information of each label for the given instance, and then learns a mapping from the instance to the label distribution. Experimental results on several hierarchical classification datasets show that our method significantly outperforms other state-of-theart hierarchical classification approaches.

scholarly journals Query-Driven Multi-Instance Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 4158-4165
Author(s):  
Yen-Chi Hsu ◽  
Cheng-Yao Hong ◽  
Ming-Sui Lee ◽  
Tyng-Luh Liu
Keyword(s):  
Experimental Results ◽  
Weighted Sum ◽  
Class Label ◽  
Action Classification ◽  
Video Clips ◽  
A New Technique ◽  
Class Labels ◽  
The Given ◽  
Network Component ◽  
Generalized Compatibility

We introduce a query-driven approach (qMIL) to multi-instance learning where the queries aim to uncover the class labels embodied in a given bag of instances. Specifically, it solves a multi-instance multi-label learning (MIML) problem with a more challenging setting than the conventional one. Each MIML bag in our formulation is annotated only with a binary label indicating whether the bag contains the instance of a certain class and the query is specified by the word2vec of a class label/name. To learn a deep-net model for qMIL, we construct a network component that achieves a generalized compatibility measure for query-visual co-embedding and yields proper instance attentions to the given query. The bag representation is then formed as the attention-weighted sum of the instances' weights, and passed to the classification layer at the end of the network. In addition, the qMIL formulation is flexible for extending the network to classify unseen class labels, leading to a new technique to solve the zero-shot MIML task through an iterative querying process. Experimental results on action classification over video clips and three MIML datasets from MNIST, CIFAR10 and Scene are provided to demonstrate the effectiveness of our method.

scholarly journals Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis

2020 ◽  
Vol 34 (05) ◽  
pp. 9122-9129
Author(s):  
Hai Wan ◽  
Yufei Yang ◽  
Jianfeng Du ◽  
Yanan Liu ◽  
Kunxun Qi ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
High Performance ◽  
State Of The Art ◽  
Language Model ◽  
The State ◽  
Experimental Results ◽  
Joint Detection ◽  
Sentiment Detection ◽  
Novel Method ◽  
The Given

Aspect-based sentiment analysis (ABSA) aims to detect the targets (which are composed by continuous words), aspects and sentiment polarities in text. Published datasets from SemEval-2015 and SemEval-2016 reveal that a sentiment polarity depends on both the target and the aspect. However, most of the existing methods consider predicting sentiment polarities from either targets or aspects but not from both, thus they easily make wrong predictions on sentiment polarities. In particular, where the target is implicit, i.e., it does not appear in the given text, the methods predicting sentiment polarities from targets do not work. To tackle these limitations in ABSA, this paper proposes a novel method for target-aspect-sentiment joint detection. It relies on a pre-trained language model and can capture the dependence on both targets and aspects for sentiment prediction. Experimental results on the SemEval-2015 and SemEval-2016 restaurant datasets show that the proposed method achieves a high performance in detecting target-aspect-sentiment triples even for the implicit target cases; moreover, it even outperforms the state-of-the-art methods for those subtasks of target-aspect-sentiment detection that they are competent to.

An approach for outlier and novelty detection for text data based on classifier confidence

2020 ◽  
pp. 1-15
Author(s):  
Nikola Pižurica ◽  
Savo Tomović
Keyword(s):  
Anomaly Detection ◽  
Novelty Detection ◽  
Experimental Results ◽  
Classification Model ◽  
Training Dataset ◽  
Training Phase ◽  
High Confidence ◽  
Text Data ◽  
Class Labels ◽  
The Given

In this paper we present an approach for novelty detection in text data. The approach can also be considered as semi-supervised anomaly detection because it operates with the training dataset containing labelled instances for the known classes only. During the training phase the classification model is learned. It is assumed that at least two known classes exist in the available training dataset. In the testing phase instances are classified as normal or anomalous based on the classifier confidence. In other words, if the classifier cannot assign any of the known class labels to the given instance with sufficiently high confidence (probability), the instance will be declared as novelty (anomaly). We propose two procedures to objectively measure the classifier confidence. Experimental results show that the proposed approach is comparable to methods known in the literature.

scholarly journals Automatic Image Captioning Based on ResNet50 and LSTM with Soft Attention

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Yan Chu ◽  
Xiao Yue ◽  
Lei Yu ◽  
Mikhailov Sergei ◽  
Zhengkui Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Recurrent Neural Network ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Challenging Problem ◽  
Image Captioning ◽  
Training Images ◽  
Fixed Length ◽  
The Given

Captioning the images with proper descriptions automatically has become an interesting and challenging problem. In this paper, we present one joint model AICRL, which is able to conduct the automatic image captioning based on ResNet50 and LSTM with soft attention. AICRL consists of one encoder and one decoder. The encoder adopts ResNet50 based on the convolutional neural network, which creates an extensive representation of the given image by embedding it into a fixed length vector. The decoder is designed with LSTM, a recurrent neural network and a soft attention mechanism, to selectively focus the attention over certain parts of an image to predict the next sentence. We have trained AICRL over a big dataset MS COCO 2014 to maximize the likelihood of the target description sentence given the training images and evaluated it in various metrics like BLEU, METEROR, and CIDEr. Our experimental results indicate that AICRL is effective in generating captions for the images.

scholarly journals Feature-Weighted Sampling for Proper Evaluation of Classification Models

2021 ◽  
Vol 11 (5) ◽  
pp. 2039
Author(s):  
Hyunseok Shin ◽  
Sejong Oh
Keyword(s):  
Random Sampling ◽  
Sampling Method ◽  
Classification Model ◽  
Training Set ◽  
Test Set ◽  
Feature Importance ◽  
Proper Training ◽  
Machine Learning Applications ◽  
Test Sets ◽  
The Given

In machine learning applications, classification schemes have been widely used for prediction tasks. Typically, to develop a prediction model, the given dataset is divided into training and test sets; the training set is used to build the model and the test set is used to evaluate the model. Furthermore, random sampling is traditionally used to divide datasets. The problem, however, is that the performance of the model is evaluated differently depending on how we divide the training and test sets. Therefore, in this study, we proposed an improved sampling method for the accurate evaluation of a classification model. We first generated numerous candidate cases of train/test sets using the R-value-based sampling method. We evaluated the similarity of distributions of the candidate cases with the whole dataset, and the case with the smallest distribution–difference was selected as the final train/test set. Histograms and feature importance were used to evaluate the similarity of distributions. The proposed method produces more proper training and test sets than previous sampling methods, including random and non-random sampling.

scholarly journals UAV Image Multi-Labeling with Data-Efficient Transformers

2021 ◽  
Vol 11 (9) ◽  
pp. 3974
Author(s):  
Laila Bashmal ◽  
Yakoub Bazi ◽  
Mohamad Mahmoud Al Rahhal ◽  
Haikel Alhichri ◽  
Naif Al Ajlan
Keyword(s):  
Data Augmentation ◽  
Feature Representation ◽  
Aerial Image ◽  
Remote Sensing Images ◽  
Training Set ◽  
Proposed Model ◽  
Class Labels ◽  
Using Data ◽  
Uav Image

In this paper, we present an approach for the multi-label classification of remote sensing images based on data-efficient transformers. During the training phase, we generated a second view for each image from the training set using data augmentation. Then, both the image and its augmented version were reshaped into a sequence of flattened patches and then fed to the transformer encoder. The latter extracts a compact feature representation from each image with the help of a self-attention mechanism, which can handle the global dependencies between different regions of the high-resolution aerial image. On the top of the encoder, we mounted two classifiers, a token and a distiller classifier. During training, we minimized a global loss consisting of two terms, each corresponding to one of the two classifiers. In the test phase, we considered the average of the two classifiers as the final class labels. Experiments on two datasets acquired over the cities of Trento and Civezzano with a ground resolution of two-centimeter demonstrated the effectiveness of the proposed model.

scholarly journals A novel method for the analytical solution of fractional Zakharov–Kuznetsov equations

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Rasool Shah ◽  
Hassan Khan ◽  
Dumitru Baleanu ◽  
Poom Kumam ◽  
Muhammad Arif
Keyword(s):  
Present Method ◽  
Decomposition Method ◽  
Fractional Derivatives ◽  
Adomian Decomposition Method ◽  
Current Method ◽  
Analytical Technique ◽  
Suggested Technique ◽  
Adomian Decomposition ◽  
Novel Method ◽  
The Given

AbstractIn this article, an efficient analytical technique, called Laplace–Adomian decomposition method, is used to obtain the solution of fractional Zakharov– Kuznetsov equations. The fractional derivatives are described in terms of Caputo sense. The solution of the suggested technique is represented in a series form of Adomian components, which is convergent to the exact solution of the given problems. Furthermore, the results of the present method have shown close relations with the exact approaches of the investigated problems. Illustrative examples are discussed, showing the validity of the current method. The attractive and straightforward procedure of the present method suggests that this method can easily be extended for the solutions of other nonlinear fractional-order partial differential equations.

scholarly journals An evolutionary approach to the vehicle route planning in e-waste mobile collection on demand

2021 ◽  
Vol 25 (8) ◽  
pp. 6665-6680
Author(s):  
Krzysztof Szwarc ◽  
Piotr Nowakowski ◽  
Urszula Boryczka
Keyword(s):  
Tabu Search ◽  
Quality Evaluation ◽  
Memetic Algorithm ◽  
Route Planning ◽  
Memetic Algorithms ◽  
Approximate Methods ◽  
On Demand ◽  
Suboptimal Solutions ◽  
Novel Method ◽  
The Given

AbstractThe article discusses the utilitarian problem of the mobile collection of waste electrical and electronic equipment. Due to its $$\mathcal {NP}$$ NP -hard nature, implies the application of approximate methods to discover suboptimal solutions in an acceptable time. The paper presents the proposal of a novel method of designing the Evolutionary and Memetic Algorithms, which determine favorable route plans. The recommended methods are determined using quality evaluation indicators for the techniques applied herein, subject to the limits characterizing the given company. The proposed Memetic Algorithm with Tabu Search provides much better results than the metaheuristics described in the available literature.

IMPROVED TIME-MULTIPLEXED FPGA ARCHITECTURE AND ALGORITHM FOR MINIMIZING COMMUNICATION COST DESIGNS

2013 ◽  
Vol 22 (05) ◽  
pp. 1350033
Author(s):  
CHI-CHOU KAO ◽  
YEN-TAI LAI
Keyword(s):  
Greedy Algorithm ◽  
Sequential Circuits ◽  
Precedence Constraints ◽  
Communication Cost ◽  
Experimental Results ◽  
Time Sharing ◽  
Fpga Architecture ◽  
The Given

The Time-Multiplexed FPGA (TMFPGA) architecture can improve dramatically logic utilization by time-sharing logic but it needs a large amount of registers among sub-circuits for partitioning the given sequential circuits. In this paper, we propose an improved TMFPGA architecture to simplify the precedence constraints so that the number of the registers among sub-circuits can be reduced for sequential circuits partitioning. To demonstrate the practicability of the architecture, we also present a greedy algorithm to minimize the maximum number of the registers. Experimental results demonstrate the effectives of the algorithm.

scholarly journals Embedding Undersampling Rotation Forest for Imbalanced Problem

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Huaping Guo ◽  
Xiaoyu Diao ◽  
Hongbing Liu
Keyword(s):  
Imbalanced Data ◽  
Feature Space ◽  
Original Data ◽  
Training Set ◽  
Data Set ◽  
Minority Class ◽  
Rotation Forest ◽  
Novel Method ◽  
Individual Classifier ◽  
The Cost

Rotation Forest is an ensemble learning approach achieving better performance comparing to Bagging and Boosting through building accurate and diverse classifiers using rotated feature space. However, like other conventional classifiers, Rotation Forest does not work well on the imbalanced data which are characterized as having much less examples of one class (minority class) than the other (majority class), and the cost of misclassifying minority class examples is often much more expensive than the contrary cases. This paper proposes a novel method called Embedding Undersampling Rotation Forest (EURF) to handle this problem (1) sampling subsets from the majority class and learning a projection matrix from each subset and (2) obtaining training sets by projecting re-undersampling subsets of the original data set to new spaces defined by the matrices and constructing an individual classifier from each training set. For the first method, undersampling is to force the rotation matrix to better capture the features of the minority class without harming the diversity between individual classifiers. With respect to the second method, the undersampling technique aims to improve the performance of individual classifiers on the minority class. The experimental results show that EURF achieves significantly better performance comparing to other state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document