scholarly journals Toward Automatically Labeling Situations in Soccer

2021 ◽  
Vol 3 ◽  
Author(s):  
Dennis Fassmeyer ◽  
Gabriel Anzer ◽  
Pascal Bauer ◽  
Ulf Brefeld
Keyword(s):  
Supervised Learning ◽  
Feature Space ◽  
Feature Representation ◽  
Unlabeled Data ◽  
Training Data ◽  
Automatic Annotation ◽  
Learning Problem ◽  
Large Margin ◽  
Variational Autoencoder

We study the automatic annotation of situations in soccer games. At first sight, this translates nicely into a standard supervised learning problem. However, in a fully supervised setting, predictive accuracies are supposed to correlate positively with the amount of labeled situations: more labeled training data simply promise better performance. Unfortunately, non-trivially annotated situations in soccer games are scarce, expensive and almost always require human experts; a fully supervised approach appears infeasible. Hence, we split the problem into two parts and learn (i) a meaningful feature representation using variational autoencoders on unlabeled data at large scales and (ii) a large-margin classifier acting in this feature space but utilize only a few (manually) annotated examples of the situation of interest. We propose four different architectures of the variational autoencoder and empirically study the detection of corner kicks, crosses and counterattacks. We observe high predictive accuracies above 90% AUC irrespectively of the task.

Semi-Supervised Learning

2011 ◽  
pp. 1022-1027
Author(s):  
Tobias Scheffer
Keyword(s):  
Supervised Learning ◽  
Supervised Classification ◽  
Unlabeled Data ◽  
Training Data ◽  
Classification Algorithms ◽  
Classification Problems

For many classification problems, unlabeled training data are inexpensive and readily available, whereas labeling training data imposes costs. Semi-supervised classification algorithms aim at utilizing information contained in unlabeled data in addition to the (few) labeled data.

Clustering-Based Transductive Semi-Supervised Learning for Learning-to-Rank

2019 ◽  
Vol 33 (12) ◽  
pp. 1951007 ◽  
Author(s):  
Ashwini Rahangdale ◽  
Shital Raut
Keyword(s):  
Supervised Learning ◽  
Learning To Rank ◽  
Cost Effective ◽  
Unlabeled Data ◽  
Training Data ◽  
Density Region ◽  
The Arts ◽  
Proposed Model ◽  
Supervised Learning Algorithms ◽  
Multiple Loss

Learning-to-rank (LTR) is a very hot topic of research for information retrieval (IR). LTR framework usually learns the ranking function using available training data that are very cost-effective, time-consuming and biased. When sufficient amount of training data is not available, semi-supervised learning is one of the machine learning paradigms that can be applied to get pseudo label from unlabeled data. Cluster and label is a basic approach for semi-supervised learning to identify the high-density region in data space which is mainly used to support the supervised learning. However, clustering with conventional method may lead to prediction performance which is worse than supervised learning algorithms for application of LTR. Thus, we propose rank preserving clustering (RPC) with PLocalSearch and get pseudo label for unlabeled data. We present semi-supervised learning that adopts clustering-based transductive method and combine it with nonmeasure specific listwise approach to learn the LTR model. Moreover, each cluster follows the multi-task learning to avoid optimization of multiple loss functions. It reduces the training complexity of adopted listwise approach from an exponential order to a polynomial order. Empirical analysis on the standard datasets (LETOR) shows that the proposed model gives better results as compared to other state-of-the-arts.

scholarly journals Time-Series Laplacian Semi-Supervised Learning for Indoor Localization †

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3867 ◽  
Author(s):  
Jaehyun Yoo
Keyword(s):  
Time Series ◽  
Supervised Learning ◽  
Indoor Localization ◽  
Learning Algorithm ◽  
Unlabeled Data ◽  
Training Data ◽  
Practical Implementation ◽  
Additional Information ◽  
Localization Scheme ◽  
The Impact

Machine learning-based indoor localization used to suffer from the collection, construction, and maintenance of labeled training databases for practical implementation. Semi-supervised learning methods have been developed as efficient indoor localization methods to reduce use of labeled training data. To boost the efficiency and the accuracy of indoor localization, this paper proposes a new time-series semi-supervised learning algorithm. The key aspect of the developed method, which distinguishes it from conventional semi-supervised algorithms, is the use of unlabeled data. The learning algorithm finds spatio-temporal relationships in the unlabeled data, and pseudolabels are generated to compensate for the lack of labeled training data. In the next step, another balancing-optimization learning algorithm learns a positioning model. The proposed method is evaluated for estimating the location of a smartphone user by using a Wi-Fi received signal strength indicator (RSSI) measurement. The experimental results show that the developed learning algorithm outperforms some existing semi-supervised algorithms according to the variation of the number of training data and access points. Also, the proposed method is discussed in terms of why it gives better performance, by the analysis of the impact of the learning parameters. Moreover, the extended localization scheme in conjunction with a particle filter is executed to include additional information, such as a floor plan.

scholarly journals SEMI-SUPERVISED SEQUENCE CLASSIFICATION WITH HMMs

2005 ◽  
Vol 19 (02) ◽  
pp. 165-182 ◽  
Author(s):  
SHI ZHONG
Keyword(s):  
Supervised Learning ◽  
Learning Strategies ◽  
Test Data ◽  
Unlabeled Data ◽  
Training Data ◽  
Model Complexity ◽  
Model Parameters ◽  
Training Process ◽  
Transductive Learning ◽  
Model Training

Using unlabeled data to help supervised learning has become an increasingly attractive methodology and proven to be effective in many applications. This paper applies semi-supervised classification algorithms, based on hidden Markov models, to classify sequences. For model-based classification, semi-supervised learning amounts to using both labeled and unlabeled data to train model parameters. We examine three different strategies of using labeled and unlabeled data in the model training process. These strategies differ in how and when labeled and unlabeled data contribute to the model training process. We also compare regular semi-supervised learning, where there are separate unlabeled training data and unlabeled test data, with transductive learning where we do not differentiate between unlabeled training data and unlabeled test data. Our experimental results on synthetic and real EEG time-series show that substantially improved classification accuracy can be achieved by these semi-supervised learning strategies. The effect of model complexity on semi-supervised learning is also studied in our experiments.

KNN Loss and Deep KNN

2021 ◽  
Vol 182 (2) ◽  
pp. 95-110
Author(s):  
Linh Le ◽  
Ying Xie ◽  
Vijay V. Raghavan
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Nearest Neighbor ◽  
Learning Strategy ◽  
Feature Space ◽  
Kernel Functions ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Map Data

The k Nearest Neighbor (KNN) algorithm has been widely applied in various supervised learning tasks due to its simplicity and effectiveness. However, the quality of KNN decision making is directly affected by the quality of the neighborhoods in the modeling space. Efforts have been made to map data to a better feature space either implicitly with kernel functions, or explicitly through learning linear or nonlinear transformations. However, all these methods use pre-determined distance or similarity functions, which may limit their learning capacity. In this paper, we present two loss functions, namely KNN Loss and Fuzzy KNN Loss, to quantify the quality of neighborhoods formed by KNN with respect to supervised learning, such that minimizing the loss function on the training data leads to maximizing KNN decision accuracy on the training data. We further present a deep learning strategy that is able to learn, by minimizing KNN loss, pairwise similarities of data that implicitly maps data to a feature space where the quality of KNN neighborhoods is optimized. Experimental results show that this deep learning strategy (denoted as Deep KNN) outperforms state-of-the-art supervised learning methods on multiple benchmark data sets.

scholarly journals Learning Meta Model for Zero- and Few-Shot Face Anti-Spoofing

2020 ◽  
Vol 34 (07) ◽  
pp. 11916-11923 ◽  
Author(s):  
Yunxiao Qin ◽  
Chenxu Zhao ◽  
Xiangyu Zhu ◽  
Zezheng Wang ◽  
Zitong Yu ◽  
...  
Keyword(s):  
Face Recognition ◽  
Supervised Learning ◽  
Large Scale ◽  
Training Data ◽  
Learning Problem ◽  
Meta Model ◽  
Meta Learning ◽  
Recognition Systems

Face anti-spoofing is crucial to the security of face recognition systems. Most previous methods formulate face anti-spoofing as a supervised learning problem to detect various predefined presentation attacks, which need large scale training data to cover as many attacks as possible. However, the trained model is easy to overfit several common attacks and is still vulnerable to unseen attacks. To overcome this challenge, the detector should: 1) learn discriminative features that can generalize to unseen spoofing types from predefined presentation attacks; 2) quickly adapt to new spoofing types by learning from both the predefined attacks and a few examples of the new spoofing types. Therefore, we define face anti-spoofing as a zero- and few-shot learning problem. In this paper, we propose a novel Adaptive Inner-update Meta Face Anti-Spoofing (AIM-FAS) method to tackle this problem through meta-learning. Specifically, AIM-FAS trains a meta-learner focusing on the task of detecting unseen spoofing types by learning from predefined living and spoofing faces and a few examples of new attacks. To assess the proposed approach, we propose several benchmarks for zero- and few-shot FAS. Experiments show its superior performances on the presented benchmarks to existing methods in existing zero-shot FAS protocols.

scholarly journals Deep Feature Extraction for Resting-State Functional MRI by Self-Supervised Learning and Application to Schizophrenia Diagnosis

2020 ◽  
Author(s):  
Yuki Hashimoto ◽  
Yosuke Ogata ◽  
Manabu Honda ◽  
Yuichi Yamashita
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Functional Mri ◽  
Resting State ◽  
Feature Space ◽  
Training Data ◽  
Training Scheme ◽  
Mri Scans ◽  
The Subject ◽  
Deep Feature Extraction

AbstractIn this study, we propose a novel deep-learning technique for functional MRI analysis. We introduced an “identity feature” by a self-supervised learning schema, in which a neural network is trained solely based on the MRI-scans; furthermore, training does not require any explicit labels. The proposed method demonstrated that each temporal slice of resting state functional MRI contains enough information to identify the subject. The network learned a feature space in which the features were clustered per subject for the test data as well as for the training data; this is unlike the features extracted by conventional methods including region of interests pooling signals and principle component analysis. In addition, using a simple linear classifier for the identity features, we demonstrated that the extracted features could contribute to schizophrenia diagnosis. The classification accuracy of our identity features was higher than that of the conventional functional connectivity. Our results suggested that our proposed training scheme of the neural network captured brain functioning related to the diagnosis of psychiatric disorders as well as the identity of the subject. Our results together highlight the validity of our proposed technique as a design for self-supervised learning.

scholarly journals Nearest labelset using double distances for multi-label classification

2019 ◽  
Vol 5 ◽  
pp. e242
Author(s):  
Hyukjun Gweon ◽  
Matthias Schonlau ◽  
Stefan H. Steiner
Keyword(s):  
Maximum Likelihood ◽  
Supervised Learning ◽  
Feature Space ◽  
Training Data ◽  
Model Parameters ◽  
Data Sets ◽  
Weighted Sum ◽  
Novel Approach ◽  
Binomial Regression ◽  
F Measure

Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this article we propose a novel approach, Nearest Labelset using Double Distances (NLDD), that predicts the labelset observed in the training data that minimizes a weighted sum of the distances in both the feature space and the label space to the new instance. The weights specify the relative tradeoff between the two distances. The weights are estimated from a binomial regression of the number of misclassified labels as a function of the two distances. Model parameters are estimated by maximum likelihood. NLDD only considers labelsets observed in the training data, thus implicitly taking into account label dependencies. Experiments on benchmark multi-label data sets show that the proposed method on average outperforms other well-known approaches in terms of 0/1 loss, and multi-label accuracy and ranks second on the F-measure (after a method called ECC) and on Hamming loss (after a method called RF-PCT).

scholarly journals Generating Video From Images using GAN and CVAE

2020 ◽  
Vol 8 (5) ◽  
pp. 1401-1404
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Generative Models ◽  
Generative Model ◽  
Learning Systems ◽  
Training Data ◽  
Variational Autoencoder ◽  
Discriminative Model ◽  
To Come

In a given scene, people can often easily predict a lot of quick future occasions that may occur. However generalized pixel-level expectation in Machine Learning systems is difficult in light of the fact that it struggles with the ambiguity inherent in predicting what's to come. However, the objective of the paper is to concentrate on predicting the dense direction of pixels in a scene — what will move in the scene, where it will travel, and how it will deform through the span of one second for which we propose a conditional variational autoencoder as a solution for this issue. We likewise propose another structure for assessing generative models through an adversarial procedure, wherein we simultaneously train two models, a generative model G that catches the information appropriation, and a discriminative model D that gauges the likelihood that an example originated from the training data instead of G. We focus on two uses of GANs semi-supervised learning, and the age of pictures that human's find visually realistic. We present the Moments in Time Dataset, an enormous scale human-clarified assortment of one million short recordings relating to dynamic situations unfolding within three seconds.

scholarly journals Semi-Supervised Learning on Meta Structure: Multi-Task Tagging and Parsing in Low-Resource Scenarios

2020 ◽  
Vol 34 (05) ◽  
pp. 8344-8351 ◽  
Author(s):  
KyungTae Lim ◽  
Jay Yoon Lee ◽  
Jaime Carbonell ◽  
Thierry Poibeau
Keyword(s):  
Supervised Learning ◽  
Language Processing ◽  
Unlabeled Data ◽  
Training Data ◽  
Training Methods ◽  
Multiple Sources ◽  
Single View ◽  
Low Resource ◽  
Part Of Speech ◽  
Proposed Model

Multi-view learning makes use of diverse models arising from multiple sources of input or different feature subsets for the same task. For example, a given natural language processing task can combine evidence from models arising from character, morpheme, lexical, or phrasal views. The most common strategy with multi-view learning, especially popular in the neural network community, is to unify multiple representations into one unified vector through concatenation, averaging, or pooling, and then build a single-view model on top of the unified representation. As an alternative, we examine whether building one model per view and then unifying the different models can lead to improvements, especially in low-resource scenarios. More specifically, taking inspiration from co-training methods, we propose a semi-supervised learning approach based on multi-view models through consensus promotion, and investigate whether this improves overall performance. To test the multi-view hypothesis, we use moderately low-resource scenarios for nine languages and test the performance of the joint model for part-of-speech tagging and dependency parsing. The proposed model shows significant improvements across the test cases, with average gains of -0.9 ∼ +9.3 labeled attachment score (LAS) points. We also investigate the effect of unlabeled data on the proposed model by varying the amount of training data and by using different domains of unlabeled data.

Sign in / Sign up

Export Citation Format

Share Document