A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Max-Margin based Discriminative Feature Learning
[article]
2017
arXiv
pre-print
In this paper, we propose a new max-margin based discriminative feature learning method. ...
In addition, for multi-class classification tasks, we further intend to learn and leverage the correlation relationships among multiple class tasks for assisting in learning discriminative features. ...
In this paper, we propose a new Max-Margin based feature transformation method to Learn Discriminative Features for classification, called MMLDF. ...
arXiv:1412.4863v2
fatcat:ru3u3vsebnfb7gaa4pbf3ihy7u
Max-margin Metric Learning for Speaker Recognition
[article]
2016
arXiv
pre-print
In this paper, we propose a max-margin metric learning approach to solve the problems. It learns a linear transform with a criterion that the margin between target and imposter trials are maximized. ...
Additionally, the objective function is not directly related to the goal of the task, e.g., discriminating true speakers and imposters. ...
Tandem composition We note that both LDA and MMML learn a linear projection, though they are based on different learning criteria: LDA uses Fisher discriminant while MMML uses max-margin. ...
arXiv:1510.05940v2
fatcat:zvmd6fajujhfzioo42ogddirx4
Max-Margin Synchronous Grammar Induction for Machine Translation
2013
Conference on Empirical Methods in Natural Language Processing
We test the effectiveness of our max-margin estimation framework on a competitive hierarchical phrase-based system. ...
Alternatively, we propose a max-margin estimation approach to discriminatively inducing synchronous grammars for machine translation, which directly optimizes translation quality measured by BLEU. ...
As the max-margin method is able to use non-local features, we compare two settings of features for the max-margin method. ...
dblp:conf/emnlp/XiaoX13
fatcat:behu5l6oprg7rdetprjamgsoia
Structured Max-Margin Learning for Inter-Related Classifier Training and Multilabel Image Annotation
2011
IEEE Transactions on Image Processing
By leveraging the inter-concept visual similarity contexts for inter-related classifier training, our structured max-margin learning algorithm can significantly enhance the discrimination power of the ...
A structured max-margin learning algorithm is developed by incorporating the visual concept network, max-margin Markov networks and multitask learning to address the issue of huge inter-concept visual ...
In this paper, a structured max-margin learning scheme is developed by incorporating the visual concept network, multitask learning and max-margin Markov networks to enhance the discrimination power of ...
doi:10.1109/tip.2010.2073476
pmid:20833601
fatcat:36febhw22zcedi3ubhjerkoimi
Large Margin Discriminative Semi-Markov Model for Phonetic Recognition
2011
IEEE Transactions on Audio, Speech, and Language Processing
The parameters of the discriminant function are estimated by a large margin learning framework for structured prediction. ...
The SMM framework considered in this paper is based on a non-probabilistic discriminant function that is linear in the joint feature map which attempts to capture long-range statistical dependencies among ...
The parameters of the discriminant function are estimated by a large margin learning framework for structured prediction. ...
doi:10.1109/tasl.2011.2108286
fatcat:jdib52monnb27oay76zyq6txyu
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
[article]
2021
arXiv
pre-print
CME then reserves adequate margin space for novel classes by introducing simple-yet-effective class margin loss during feature learning. ...
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects. ...
Driven by the max-margin loss, the localization features are filtered out during detector training.
Base Training: Class Max-margin Max-Margin Loss. ...
arXiv:2103.04612v3
fatcat:veofjm2apbh4narn6zzba7adre
Structured max-margin learning for multi-label image annotation
2010
Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10
Our structured max-margin learning algorithm can leverage the inter-concept visual similarity contexts to learn a large number of inter-related classifiers simultaneously and improve their discrimination ...
Third, a structured max-margin learning algorithm is developed by incorporating the visual concept network, maxmargin Markov networks and multi-task learning to address the issue of huge inter-concept ...
STRUCTURED MAX-MARGIN LEARN-ING In this paper, a structured max-margin learning scheme is developed by incorporating the visual concept network, multi-task learning and max-margin Markov networks to enhance ...
doi:10.1145/1816041.1816056
dblp:conf/civr/XueLF10
fatcat:zmhoybpwo5drjlxi577nbyaawq
Unifying Spatial and Attribute Selection for Distracter-Resilient Tracking
2014
2014 IEEE Conference on Computer Vision and Pattern Recognition
This paper presents an initial attempt to unify the modeling of these two tasks for an effective solution, based on the introduction of a new quantity called Soft Visual Margin. ...
Different from other formulations of margin, this new quantity is analytical and is insensitive to noisy data. ...
margin-based metric learning methods [23, 20, 12, 21] . ...
doi:10.1109/cvpr.2014.448
dblp:conf/cvpr/JiangW14
fatcat:buhh6w7ydjcqlfokhtgy53ch7a
Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-based Supervision
[article]
2018
arXiv
pre-print
We, then, briefly review the related set-based loss functions, and subsequently propose a novel Max-Margin Loss which maximizes maximum possible inter-class margin with assistance of Support Vector Machines ...
In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization. ...
As the authors of [31] illustrated, set-based supervision can learn discriminative features rather than just separable features like sample-based approaches would learn. ...
arXiv:1708.00277v3
fatcat:6lw23h5hdjectmz4akzaycvchq
Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision
2017
2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
We, then, briefly review the related set-based loss functions, and subsequently we propose a novel Max-Margin Loss which maximizes maximum possible inter-class margin with assistance of Support Vector ...
In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample-and set-based optimization. ...
As the authors of [31] illustrated, set-based supervision can learn discriminative features rather than just separable features like sample-based approaches would learn. ...
doi:10.1109/iccvw.2017.195
dblp:conf/iccvw/GecerBK17
fatcat:kugye5w46fcbfpnq75caas2ptm
Max-Margin Weight Learning for Markov Logic Networks
[chapter]
2009
Lecture Notes in Computer Science
In this work, we present a new discriminative weight learning method for MLNs based on a maxmargin framework. ...
This results in a new model, Max-Margin Markov Logic Networks (M3LNs), that combines the expressiveness of MLNs with the predictive accuracy of structural Support Vector Machines (SVMs). ...
Conclusions We have presented a max-margin weight learning method for MLNs based on the framework of structural SVMs. ...
doi:10.1007/978-3-642-04180-8_54
fatcat:2mmjsmh6wra7vmj65bd7znlrxq
Online learning methods for discriminative training of phrase based statistical machine translation
2007
Machine Translation Summit
This paper investigates the task of training discriminatively a phrase based SMT system with millions of features using the structured perceptron and the Margin Infused Relax Algorithm (MIRA), two popular ...
online learning algorithms. ...
Typically, discriminative training algorithms come in two flavours, firstly likelihood-based methods which require feature expectations and secondly, margin-based methods which require either an N-best ...
dblp:conf/mtsummit/ArunK07
fatcat:gg2p2nuecrfndbg2veqt5fzlem
Large Margin Learning of Upstream Scene Understanding Models
2010
Neural Information Processing Systems
Max-margin training: from the comparison of the max-margin approach with the standard MLE
in both cases of using global features and not using global features, we can see that the max-margin
learning can ...
., scene categories), our max-margin learning approach iterates
between posterior probabilistic inference and max-margin parameter learning. ...
dblp:conf/nips/ZhuLLX10
fatcat:ctul2l5kyjajzmtqyostvejisq
Large Margin Learning of Bayesian Classifiers Based on Gaussian Mixture Models
[chapter]
2010
Lecture Notes in Computer Science
We present a discriminative learning framework for Gaussian mixture models (GMMs) used for classification based on the extended Baum-Welch (EBW) algorithm [1]. ...
We also show that the generative discriminatively parameterized GMM classifiers still allow to marginalize over missing features, a case where generative classifiers have an advantage over purely discriminative ...
In Section 3, we derive a discriminative learning method for CL-GMMs based on the EBW algorithm used for classification. Margin-based GMM learning is presented in Section 4. ...
doi:10.1007/978-3-642-15939-8_4
fatcat:6ze2aj2x4rgxxldydcapf7d7vq
Multi-feature max-margin hierarchical Bayesian model for action recognition
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, a multi-feature max-margin hierarchical Bayesian model (M 3 HBM) is proposed for action recognition. ...
For recognition, we employ Gibbs classifiers to minimize the expected loss function based on the max-margin principle and use the classifiers as regularization terms of M 3 HBM to perform Bayeisan estimation ...
Max-Margin Hierarchical Bayesian Model To make the learned STPs more discriminative for classification, we introduce max-margin classifiers to learn the representations. ...
doi:10.1109/cvpr.2015.7298769
dblp:conf/cvpr/YangYWHW15
fatcat:nrbiqvyaejfdbill6ntmsnhzzy
« Previous
Showing results 1 — 15 out of 75,024 results