Supervised Paragraph Vector: Distributed Representations of Words, Documents and Class Labels

LambdaNet: A Fully Convolutional Architecture for Directional Change Detection

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.8.imawm-114 ◽

2020 ◽

Vol 2020 (8) ◽

pp. 114-1-114-7

Author(s):

Bryan Blakeslee ◽

Andreas Savakis

Keyword(s):

Change Detection ◽

Satellite Imagery ◽

Classification Scheme ◽

Deep Architecture ◽

Binary Process ◽

Directional Change ◽

Class Labels ◽

Image Pairs

Change detection in image pairs has traditionally been a binary process, reporting either “Change” or “No Change.” In this paper, we present LambdaNet, a novel deep architecture for performing pixel-level directional change detection based on a four class classification scheme. LambdaNet successfully incorporates the notion of “directional change” and identifies differences between two images as “Additive Change” when a new object appears, “Subtractive Change” when an object is removed, “Exchange” when different objects are present in the same location, and “No Change.” To obtain pixel annotated change maps for training, we generated directional change class labels for the Change Detection 2014 dataset. Our tests illustrate that LambdaNet would be suitable for situations where the type of change is unstructured, such as change detection scenarios in satellite imagery.

Download Full-text

COVIMOS: A Coastal Video Monitoring System

Journal of Electrical Electronics and Informatics ◽

10.24843/jeei.2017.v01.i01.p01 ◽

2017 ◽

Vol 1 (1) ◽

pp. 1

Author(s):

I Made Oka Widyantara ◽

I Made Dwi Asana Putra ◽

Ida Bagus Putu Adnyana

Keyword(s):

Monitoring System ◽

Nearest Neighbor ◽

Low Cost ◽

Video Image ◽

Video Monitoring ◽

Reference Object ◽

Self Organizing Map ◽

K Nearest Neighbor ◽

Ip Camera ◽

Class Labels

This paper intends to explain the development of Coastal Video Monitoring System (CoViMoS) with the main characteristics including low-cost and easy implementation. CoViMoS characteristics have been realized using the device IP camera for video image acquisition, and development of software applications with the main features including detection of shoreline and it changes are automatically. This capability was based on segmentation and classification techniques based on data mining. Detection of shoreline is done by segmenting a video image of the beach, to get a cluster of objects, namely land, sea and sky, using Self Organizing Map (SOM) algorithms. The mechanism of classification is done using K-Nearest Neighbor (K-NN) algorithms to provide the class labels to objects that have been generated on the segmentation process. Furthermore, the classification of land used as a reference object in the detection of costline. Implementation CoViMoS system for monitoring systems in Cucukan Beach, Gianyar regency, have shown that the developed system is able to detect the shoreline and its changes automatically.

Download Full-text

BiLabel-Specific Features for Multi-Label Classification

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3458283 ◽

2021 ◽

Vol 16 (1) ◽

pp. 1-23

Author(s):

Min-Ling Zhang ◽

Jun-Peng Fang ◽

Yi-Bo Wang

Keyword(s):

Predictive Models ◽

Comparative Studies ◽

State Of The Art ◽

Classification Model ◽

Generation Process ◽

Prototype Selection ◽

Class Label ◽

Benchmark Datasets ◽

Label Correlations ◽

Class Labels

In multi-label classification, the task is to induce predictive models which can assign a set of relevant labels for the unseen instance. The strategy of label-specific features has been widely employed in learning from multi-label examples, where the classification model for predicting the relevancy of each class label is induced based on its tailored features rather than the original features. Existing approaches work by generating a group of tailored features for each class label independently, where label correlations are not fully considered in the label-specific features generation process. In this article, we extend existing strategy by proposing a simple yet effective approach based on BiLabel-specific features. Specifically, a group of tailored features is generated for a pair of class labels with heuristic prototype selection and embedding. Thereafter, predictions of classifiers induced by BiLabel-specific features are ensembled to determine the relevancy of each class label for unseen instance. To thoroughly evaluate the BiLabel-specific features strategy, extensive experiments are conducted over a total of 35 benchmark datasets. Comparative studies against state-of-the-art label-specific features techniques clearly validate the superiority of utilizing BiLabel-specific features to yield stronger generalization performance for multi-label classification.

Download Full-text

UAV Image Multi-Labeling with Data-Efficient Transformers

Applied Sciences ◽

10.3390/app11093974 ◽

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.

Download Full-text

Tag N’ Train: a technique to train improved classifiers on unlabeled data

Journal of High Energy Physics ◽

10.1007/jhep01(2021)153 ◽

2021 ◽

Vol 2021 (1) ◽

Cited By ~ 2

Author(s):

Oz Amram ◽

Cristina Mantilla Suarez

Keyword(s):

Real Data ◽

Unlabeled Data ◽

Machine Learning Techniques ◽

Jet Physics ◽

Classification Problems ◽

Weak Classifier ◽

Potential Applications ◽

Substantial Progress ◽

Resonance Search ◽

Class Labels

Abstract There has been substantial progress in applying machine learning techniques to classification problems in collider and jet physics. But as these techniques grow in sophistication, they are becoming more sensitive to subtle features of jets that may not be well modeled in simulation. Therefore, relying on simulations for training will lead to sub-optimal performance in data, but the lack of true class labels makes it difficult to train on real data. To address this challenge we introduce a new approach, called Tag N’ Train (TNT), that can be applied to unlabeled data that has two distinct sub-objects. The technique uses a weak classifier for one of the objects to tag signal-rich and background-rich samples. These samples are then used to train a stronger classifier for the other object. We demonstrate the power of this method by applying it to a dijet resonance search. By starting with autoencoders trained directly on data as the weak classifiers, we use TNT to train substantially improved classifiers. We show that Tag N’ Train can be a powerful tool in model-agnostic searches and discuss other potential applications.

Download Full-text

ImbTreeEntropy and ImbTreeAUC: Novel R Packages for Decision Tree Learning on the Imbalanced Datasets

Electronics ◽

10.3390/electronics10060657 ◽

2021 ◽

Vol 10 (6) ◽

pp. 657

Author(s):

Krzysztof Gajowniczek ◽

Tomasz Ząbkowski

Keyword(s):

Imbalanced Data ◽

Misclassification Cost ◽

Learning Time ◽

Misclassification Costs ◽

Split Point ◽

Speed Up ◽

R Packages ◽

Class Labels ◽

Entropy Functions ◽

Support Cost

This paper presents two R packages ImbTreeEntropy and ImbTreeAUC to handle imbalanced data problems. ImbTreeEntropy functionality includes application of a generalized entropy functions, such as Rényi, Tsallis, Sharma–Mittal, Sharma–Taneja and Kapur, to measure impurity of a node. ImbTreeAUC provides non-standard measures to choose an optimal split point for an attribute (as well the optimal attribute for splitting) by employing local, semi-global and global AUC (Area Under the ROC curve) measures. Both packages are applicable for binary and multiclass problems and they support cost-sensitive learning, by defining a misclassification cost matrix, and weighted-sensitive learning. The packages accept all types of attributes, including continuous, ordered and nominal, where the latter type is simplified for multiclass problems to reduce the computational overheads. Both applications enable optimization of the thresholds where posterior probabilities determine final class labels in a way that misclassification costs are minimized. Model overfitting can be managed either during the growing phase or at the end using post-pruning. The packages are mainly implemented in R, however some computationally demanding functions are written in plain C++. In order to speed up learning time, parallel processing is supported as well.

Download Full-text

Neural Components of Reading Revealed by Distributed and Symbolic Computational Models

Neurobiology of Language ◽

10.1162/nol_a_00018 ◽

2020 ◽

Vol 1 (4) ◽

pp. 381-401

Author(s):

Ryan Staples ◽

William W. Graves

Keyword(s):

Neural Activity ◽

Neural Coding ◽

Computational Models ◽

Ann Model ◽

Distributed Representations ◽

Neural Data ◽

Cognitive Components ◽

Components Of Reading ◽

Artificial Neural Network Ann ◽

Models Of Reading

Determining how the cognitive components of reading—orthographic, phonological, and semantic representations—are instantiated in the brain has been a long-standing goal of psychology and human cognitive neuroscience. The two most prominent computational models of reading instantiate different cognitive processes, implying different neural processes. Artificial neural network (ANN) models of reading posit nonsymbolic, distributed representations. The dual-route cascaded (DRC) model instead suggests two routes of processing, one representing symbolic rules of spelling–to–sound correspondence, the other representing orthographic and phonological lexicons. These models are not adjudicated by behavioral data and have never before been directly compared in terms of neural plausibility. We used representational similarity analysis to compare the predictions of these models to neural data from participants reading aloud. Both the ANN and DRC model representations corresponded to neural activity. However, the ANN model representations correlated to more reading-relevant areas of cortex. When contributions from the DRC model were statistically controlled, partial correlations revealed that the ANN model accounted for significant variance in the neural data. The opposite analysis, examining the variance explained by the DRC model with contributions from the ANN model factored out, revealed no correspondence to neural activity. Our results suggest that ANNs trained using distributed representations provide a better correspondence between cognitive and neural coding. Additionally, this framework provides a principled approach for comparing computational models of cognitive function to gain insight into neural representations.

Download Full-text