scholarly journals Partial Label Learning by Semantic Difference Maximization

2019 ◽  
Author(s):  
Lei Feng ◽  
Bo An
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
Positive Answer ◽  
Learning Framework ◽  
Novel Approach ◽  
Semantic Difference ◽  
Weakly Supervised ◽  
Partial Label Learning ◽  
The Given ◽  
First Time

Partial label learning is a weakly supervised learning framework, in which each instance is provided with multiple candidate labels while only one of them is correct. Most of the existing approaches focus on leveraging the instance relationships to disambiguate the given noisy label space, while it is still unclear whether we can exploit potentially useful information in label space to alleviate the label ambiguities. This paper gives a positive answer to this question for the first time. Specifically, if two instances do not share any common candidate labels, they cannot have the same ground-truth label. By exploiting such dissimilarity relationships from label space, we propose a novel approach that aims to maximize the latent semantic differences of the two instances whose ground-truth labels are definitely different, while training the desired model simultaneously, thereby continually enlarging the gap of label confidences between two instances of different classes. Extensive experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts.

scholarly journals Regularized Instance Embedding for Deep Multi-Instance Learning

2019 ◽  
Vol 10 (1) ◽  
pp. 64
Author(s):  
Yi Lin ◽  
Honggang Zhang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Supervised Learning ◽  
Regularization Method ◽  
Gradient Descent ◽  
State Of The Art ◽  
Stochastic Gradient Descent ◽  
Learning Framework ◽  
Weakly Supervised ◽  
The Cost

In the era of Big Data, multi-instance learning, as a weakly supervised learning framework, has various applications since it is helpful to reduce the cost of the data-labeling process. Due to this weakly supervised setting, learning effective instance representation/embedding is challenging. To address this issue, we propose an instance-embedding regularizer that can boost the performance of both instance- and bag-embedding learning in a unified fashion. Specifically, the crux of the instance-embedding regularizer is to maximize correlation between instance-embedding and underlying instance-label similarities. The embedding-learning framework was implemented using a neural network and optimized in an end-to-end manner using stochastic gradient descent. In experiments, various applications were studied, and the results show that the proposed instance-embedding-regularization method is highly effective, having state-of-the-art performance.

A Novel Feature Correlation Approach for Brand Spam Detection

2021 ◽  
pp. 149-161
Author(s):  
Bharat Tidke ◽  
Swati Tidke
Keyword(s):  
State Of The Art ◽  
The Internet ◽  
Spam Detection ◽  
Feature Engineering ◽  
Novel Approach ◽  
Feature Correlation ◽  
The Given ◽  
Improve State

In this age of the internet, no person wants to make his decision on his own. Be it for purchasing a product, watching a movie, reading a book, a person looks out for reviews. People are unaware of the fact that these reviews may not always be true. It is the age of paid reviews, where the reviews are not just written to promote one's product but also to demote a competitor's product. But the ones which are turning out to be the most critical are given on brand of a certain product. This chapter proposed a novel approach for brand spam detection using feature correlation to improve state-of-the-art approaches. Correlation-based feature engineering is considered as one of the finest methods for determining the relations among the features. Several features attached with reviews are important, keeping in focus customer and company needs in making strong decisions, user for purchasing, and company for improving sales and services. Due to severe spamming these days, it has become nearly impossible to judge whether the given review is a trusted or a fake review.

scholarly journals Exploitation of deep learning in the automatic detection of cracks on paved roads

GEOMATICA ◽  
2019 ◽  
Vol 73 (2) ◽  
pp. 29-44
Author(s):  
Won Mo Jung ◽  
Faizaan Naveed ◽  
Baoxin Hu ◽  
Jianguo Wang ◽  
Ningyuan Li
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Ground Truth ◽  
Learning Networks ◽  
Test Image ◽  
Convolutional Network ◽  
Image Patches ◽  
Severity Levels ◽  
First Time ◽  
Different Levels

With the advance of deep learning networks, their applications in the assessment of pavement conditions are gaining more attention. A convolutional neural network (CNN) is the most commonly used network in image classification. In terms of pavement assessment, most existing CNNs are designed to only distinguish between cracks and non-cracks. Few networks classify cracks in different levels of severity. Information on the severity of pavement cracks is critical for pavement repair services. In this study, the state-of-the-art CNN used in the detection of pavement cracks was improved to localize the cracks and identify their distress levels based on three categories (low, medium, and high). In addition, a fully convolutional network (FCN) was, for the first time, utilized in the detection of pavement cracks. These designed architectures were validated using the data acquired on four highways in Ontario, Canada, and compared with the ground truth that was provided by the Ministry of Transportation of Ontario (MTO). The results showed that with the improved CNN, the prediction precision on a series of test image patches were 72.9%, 73.9%, and 73.1% for cracks with the severity levels of low, medium, and high, respectively. The precision for the FCN was tested on whole pavement images, resulting in 62.8%, 63.3%, and 66.4%, respectively, for cracks with the severity levels of low, medium, and high. It is worth mentioning that the ground truth contained some uncertainties, which partially contributed to the relatively low precision.

scholarly journals Partial Label Learning with Self-Guided Retraining

2019 ◽  
Vol 33 ◽  
pp. 3542-3549 ◽  
Author(s):  
Lei Feng ◽  
Bo An
Keyword(s):  
Real World ◽  
Optimization Problem ◽  
State Of The Art ◽  
Ground Truth ◽  
Learning Approaches ◽  
High Confidence ◽  
Infinity Norm ◽  
Real World Datasets ◽  
Partial Label Learning ◽  
Optimization Efficiency

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with proper constraints to train the desired model and perform pseudo-labeling jointly. For pseudo-labeling, unlike traditional self-training that manually differentiates the ground-truth label with enough high confidence, we introduce the maximum infinity norm regularization on the modeling outputs to automatically achieve this consideratum, which results in a convex-concave optimization problem. We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems. By proposing an upper-bound surrogate objective function, we turn to solving only one QP problem for improving the optimization efficiency. Extensive experiments on synthesized and real-world datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art partial label learning approaches.

scholarly journals Towards Enabling Binary Decomposition for Partial Label Learning

2018 ◽  
Author(s):  
Xuan Wu ◽  
Min-Ling Zhang
Keyword(s):  
Learning Algorithm ◽  
Experimental Studies ◽  
Ground Truth ◽  
Binary Classifier ◽  
Decomposition Approach ◽  
Novel Approach ◽  
Binary Decomposition ◽  
Binary Classifiers ◽  
Training Examples ◽  
Partial Label Learning

The task of partial label (PL) learning is to learn a multi-class classifier from training examples each associated with a set of candidate labels, among which only one corresponds to the ground-truth label. It is well known that for inducing multi-class predictive model, the most straightforward solution is binary decomposition which works by either one-vs-rest or one-vs-one strategy. Nonetheless, the ground-truth label for each PL training example is concealed in its candidate label set and thus not accessible to the learning algorithm, binary decomposition cannot be directly applied under partial label learning scenario. In this paper, a novel approach is proposed to solving partial label learning problem by adapting the popular one-vs-one decomposition strategy. Specifically, one binary classifier is derived for each pair of class labels, where PL training examples with distinct relevancy to the label pair are used to generate the corresponding binary training set. After that, one binary classifier is further derived for each class label by stacking over predictions of existing binary classifiers to improve generalization. Experimental studies on both artificial and real-world PL data sets clearly validate the effectiveness of the proposed binary decomposition approach w.r.t state-of-the-art partial label learning techniques.

scholarly journals Weakly-Supervised Opinion Summarization by Leveraging External Information

2020 ◽  
Vol 34 (05) ◽  
pp. 9644-9651
Author(s):  
Chao Zhao ◽  
Snigdha Chaturvedi
Keyword(s):  
Explicit Memory ◽  
Domain Knowledge ◽  
State Of The Art ◽  
External Information ◽  
Product Reviews ◽  
Opinion Summarization ◽  
External Sources ◽  
Human Effort ◽  
Weakly Supervised ◽  
The Given

Opinion summarization from online product reviews is a challenging task, which involves identifying opinions related to various aspects of the product being reviewed. While previous works require additional human effort to identify relevant aspects, we instead apply domain knowledge from external sources to automatically achieve the same goal. This work proposes AspMem, a generative method that contains an array of memory cells to store aspect-related knowledge. This explicit memory can help obtain a better opinion representation and infer the aspect information more precisely. We evaluate this method on both aspect identification and opinion summarization tasks. Our experiments show that AspMem outperforms the state-of-the-art methods even though, unlike the baselines, it does not rely on human supervision which is carefully handcrafted for the given tasks.

scholarly journals Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

2020 ◽  
Vol 34 (07) ◽  
pp. 12765-12772
Author(s):  
Bingfeng Zhang ◽  
Jimin Xiao ◽  
Yunchao Wei ◽  
Mingjie Sun ◽  
Kaizhu Huang
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Step Method ◽  
Pascal Voc ◽  
Segmentation Approach ◽  
Level Information ◽  
One Step ◽  
End To End ◽  
Weakly Supervised

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent state-of-the-art approaches propose to adopt two-step solutions, i.e. 1) learn to generate pseudo pixel-level masks, and 2) engage FCNs to train the semantic segmentation networks with the pseudo masks. However, the two-step solutions usually employ many bells and whistles in producing high-quality pseudo masks, making this kind of methods complicated and inelegant. In this work, we harness the image-level labels to produce reliable pixel-level annotations and design a fully end-to-end network to learn to predict segmentation maps. Concretely, we firstly leverage an image classification branch to generate class activation maps for the annotated categories, which are further pruned into confident yet tiny object/background regions. Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization. Despite its apparent simplicity, our one-step solution achieves competitive mIoU scores (val: 62.6, test: 62.9) on Pascal VOC compared with those two-step state-of-the-arts. By extending our one-step method to two-step, we get a new state-of-the-art performance on the Pascal VOC (val: 66.3, test: 66.5).

Root with Alternation of -ravn-/-rovn- (From Materials of the Academic Description of Russian Spelling)

2020 ◽  
Vol 81 (6) ◽  
pp. 90-96
Author(s):  
E. V. Arutiunova ◽  
E. V. Beshenkova ◽  
O. E. Ivanova
Keyword(s):  
Russian Language ◽  
Study Guides ◽  
Russian Academy Of Sciences ◽  
Academy Of Sciences ◽  
The Given ◽  
First Time ◽  
The Russian Language

The study investigates the rule of spelling the root -ravn-/-rovn- and is considered to be a fragment of the academic description of Russian spelling, which is currently being under investigation at the Russian Language Institute of the Russian Academy of Sciences. The authors clarify the meanings that determine the spelling of the unstressed root, supplement the lists of exceptions, denote words with meanings not corresponding to the given values-criteria, and, for the first time in linguistics, investigate the words that can be correlated with different values-criteria, that is, they have double motivation. The rule codifies the spelling of words that have double motivation and fluctuate in usus, dictionaries, study guides and reference books. Spelling recommendations for these words correspond to the current linguistic norm and were approved by the Spelling Commission of the Russian Academy of Sciences in 2019. The linguistic commentary to the rule contains the most significant etymological facts concerning the root -ravn-/-rovn- and summarises the scientific and methodological attempts to figure out the distribution of vocabulary with root -ravn-/-rovn- based on the meanings selected in the spelling rules. In the paper it is shown that the instability in spelling of various verbs with the root -ravn-/-rovn- in modern writing and dictionaries is determined by the double motivation of words, as well as contradictory recommendations and gaps in the rules.

LUMINESCENCE OF THE BLACK SEA MICROSCOPIC FUNGI CULTURES

2017 ◽  
Author(s):  
Olga Mashukova ◽  
Olga Mashukova ◽  
Yuriy Tokarev ◽  
Yuriy Tokarev ◽  
Nadejda Kopytina ◽  
...  
Keyword(s):  
Fresh Water ◽  
Black Sea ◽  
Ethyl Alcohol ◽  
Light Emission ◽  
Sea Water ◽  
Control Culture ◽  
Chemical Stimulation ◽  
The Black Sea ◽  
The Given ◽  
First Time

We studied for the first time luminescence characteristics of the some micromycetes, isolated from the bottom sediments of the Black sea from the 27 m depth. Luminescence parameters were registered at laboratory complex “Svet” using mechanical and chemical stimulations. Fungi cultures of genera Acremonium, Aspergillus, Penicillium were isolated on ChDA medium which served as control. Culture of Penicillium commune gave no light emission with any kind of stimulation. Culture of Acremonium sp. has shown luminescence in the blue – green field of spectrum. Using chemical stimulation by fresh water we registered signals with luminescence energy (to 3.24 ± 0.11)•108 quantum•cm2 and duration up to 4.42 s, which 3 times exceeded analogous magnitudes in a group, stimulated by sea water (p < 0.05). Under chemical stimulation by ethyl alcohol fungi culture luminescence was not observed. Culture of Aspergillus fumigatus possessed the most expressed properties of luminescence. Stimulation by fresh water culture emission with energy of (3.35 ± 0.11)•108 quantum•cm2 and duration up to 4.96 s. Action of ethyl alcohol to culture also stimulated signals, but intensity of light emission was 3–4 times lower than under mechanical stimulation. For sure the given studies will permit not only to evaluate contribution of marine fungi into general bioluminescence of the sea, but as well to determine places of accumulation of opportunistic species in the sea.

scholarly journals G-Tric: generating three-way synthetic datasets with triclustering solutions

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
João Lobo ◽  
Rui Henriques ◽  
Sara C. Madeira
Keyword(s):  
State Of The Art ◽  
Synthetic Data ◽  
Ground Truth ◽  
Real Data ◽  
Three Dimensions ◽  
Additional Advantage ◽  
Urban Dynamics ◽  
Data Generator ◽  
Real World Datasets ◽  
Synthetic Datasets

Abstract Background Three-way data started to gain popularity due to their increasing capacity to describe inherently multivariate and temporal events, such as biological responses, social interactions along time, urban dynamics, or complex geophysical phenomena. Triclustering, subspace clustering of three-way data, enables the discovery of patterns corresponding to data subspaces (triclusters) with values correlated across the three dimensions (observations $$\times$$ × features $$\times$$ × contexts). With increasing number of algorithms being proposed, effectively comparing them with state-of-the-art algorithms is paramount. These comparisons are usually performed using real data, without a known ground-truth, thus limiting the assessments. In this context, we propose a synthetic data generator, G-Tric, allowing the creation of synthetic datasets with configurable properties and the possibility to plant triclusters. The generator is prepared to create datasets resembling real 3-way data from biomedical and social data domains, with the additional advantage of further providing the ground truth (triclustering solution) as output. Results G-Tric can replicate real-world datasets and create new ones that match researchers needs across several properties, including data type (numeric or symbolic), dimensions, and background distribution. Users can tune the patterns and structure that characterize the planted triclusters (subspaces) and how they interact (overlapping). Data quality can also be controlled, by defining the amount of missing, noise or errors. Furthermore, a benchmark of datasets resembling real data is made available, together with the corresponding triclustering solutions (planted triclusters) and generating parameters. Conclusions Triclustering evaluation using G-Tric provides the possibility to combine both intrinsic and extrinsic metrics to compare solutions that produce more reliable analyses. A set of predefined datasets, mimicking widely used three-way data and exploring crucial properties was generated and made available, highlighting G-Tric’s potential to advance triclustering state-of-the-art by easing the process of evaluating the quality of new triclustering approaches.

Sign in / Sign up

Export Citation Format

Share Document