52,973 Hits in 6.0 sec

Cost-sensitive learning for large-scale hierarchical classification

Jianfu Chen, David Warren
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Margin re-scaling is sensitive to the scaling of loss functions.  ...  Given the characteristics of the task of hierarchical product classification, we shed insight into how and why common evaluation metrics such as error rate can be misleading, which is applicable for treating  ...  COST-SENSITIVE LEARNING FOR HI-ERARCHICAL PRODUCT CLASSIFICA-TION After choosing the average revenue loss as the appropriate performance evaluation metric for this task of hierarchical product classification  ... 
doi:10.1145/2505515.2505582 dblp:conf/cikm/ChenW13 fatcat:jprzqgytfnb6pldzvc2tfso6fm

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks [article]

Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
2021 arXiv   pre-print
To this end, we use the classical Conditional Risk Minimization (CRM) framework for hierarchy-aware classification.  ...  It significantly outperforms the state-of-the-art and consistently obtains large reductions in the average hierarchical distance of top-k predictions across datasets, with very little loss in accuracy.  ...  We study cost-sensitive classification in a large scale setting (e.g., ImageNet) and explore the use of a taxonomic hierarchy to obtain the misclassification costs.  ... 
arXiv:2104.00795v1 fatcat:vnj5u7w3ujdzldo5q4dz52zxku

What Does Classifying More Than 10,000 Image Categories Tell Us? [chapter]

Jia Deng, Alexander C. Berg, Kai Li, Li Fei-Fei
2010 Lecture Notes in Computer Science  
Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space.  ...  This paper presents a study of large scale categorization including a series of challenging experiments on classification with more than 10, 000 image classes.  ...  We thank Chris Baldassano, Jia Li, Olga Russakovsky, Hao Su, Bangpeng Yao and anonymous reviewers for their helpful comments.  ... 
doi:10.1007/978-3-642-15555-0_6 fatcat:w3s5rgykovfl7fkdwj3v3ijhhi

Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification

Huiru Xiao, Xin Liu, Yangqiu Song
2019 The World Wide Web Conference on - WWW '19  
Since we put a structure-sensitive cost to the learning algorithm to constrain the classification consistent with the class hierarchy and do not need to reconstruct the feature vectors for different structures  ...  Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly.  ...  Algorithm 1 presents the EM algorithm for the path cost-sensitive classification (PCEM).  ... 
doi:10.1145/3308558.3313658 dblp:conf/www/XiaoLS19 fatcat:nnu6qkc6knbyzlcrploz34aqvu

A comparative study on two large-scale hierarchical text classification tasks' solutions

Jian Zhang, Hai Zhao, Bao-Liang Lu
2010 2010 International Conference on Machine Learning and Cybernetics  
Patent classification is a large scale hierarchical text classification (LSHTC) task.  ...  For the first time, this paper compares two popular learning frameworks, namely hierarchical support vector machine (SVM) and k nearest neighbor (k-NN) that are applied to a LSHTC task.  ...  Introduction In recent years, along with the rapid development of the Internet, there is an increasing need for solutions to large-scale hierarchical text classification (LSHTC) tasks.  ... 
doi:10.1109/icmlc.2010.5580696 dblp:conf/icmlc/ZhangZL10 fatcat:psvka5y2dzggnepmsyixvls4fm

Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning [article]

Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang
2017 arXiv   pre-print
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation.  ...  Using a dataset consisting of 150 object classes from the ImageNet ILSVRC2012 data set, we find that the hierarchical classification method that maximizes expected reward for non-novel classes differs  ...  Acknowledgments We thank the authors of [ ] for providing the class to attribute mapping of their data set.  ... 
arXiv:1712.03151v1 fatcat:maz4josz7baehms6ixbscowf2e

Joint Hierarchical Category Structure Learning and Large-Scale Image Classification

Yanyun Qu, Li Lin, Fumin Shen, Chang Lu, Yang Wu, Yuan Xie, Dacheng Tao
2017 IEEE Transactions on Image Processing  
Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification.  ...  We propose a novel image classification method based on learning hierarchical inter-class structures.  ...  More flexible and effective features are required for large-scale image classification.  ... 
doi:10.1109/tip.2016.2615423 pmid:27723591 fatcat:25ee3qy7mna4dmrmhqfqgnvcsy

Evaluating knowledge transfer and zero-shot learning in a large-scale setting

Marcus Rohrbach, Michael Stark, Bernt Schiele
2011 CVPR 2011  
While none of the KT methods can improve over one-vs-all classification they prove valuable for zero-shot learning, especially hierarchical and direct similarity based KT.  ...  We also propose and describe several extensions of the evaluated approaches that are necessary for this large-scale study.  ...  cost sensitive classifier proposed by [6] .  ... 
doi:10.1109/cvpr.2011.5995627 dblp:conf/cvpr/RohrbachSS11 fatcat:uc655tnp7bb6jau4bcvdudjgzy

Synergy of multi-label hierarchical ensembles, data fusion, and cost-sensitive methods for gene functional inference

Nicolò Cesa-Bianchi, Matteo Re, Giorgio Valentini
2011 Machine Learning  
Our experiments show that key factors for the success of hierarchical ensemble methods are the integration and synergy among multilabel hierarchical, data fusion, and cost-sensitive approaches, as well  ...  Unlike previous works, which mostly looked at each one of these issues in isolation, we explore the interaction and potential synergy of hierarchical multilabel methods, data fusion methods, and cost-sensitive  ...  Acknowledgements We would like to thank the anonymous reviewers for their comments and suggestions.  ... 
doi:10.1007/s10994-011-5271-6 fatcat:5uvavmu6zjft3g7xvtc6sghsya

Guest editorial: Special issue on Extreme learning machine and applications (II)

Zhihong Man, Guang-Bin Huang
2015 Neural computing & applications (Print)  
The proposed algorithm can not only maintain the properties of ELM, but also be applicable to large-scale learning problems.  ...  In ''Real-time transient stability status prediction using cost-sensitive extreme learning machine'', the authors present a new realtime transient stability status prediction algorithm based on ELM for  ... 
doi:10.1007/s00521-015-2087-5 fatcat:tk6wm4jk65exhpszx6tfgms43y

FLAG: Faster Learning on Anchor Graph with Label Predictor Optimization

Weijie Fu, Meng Wang, Shijie Hao, Tingting Mu
2017 IEEE Transactions on Big Data  
As such, a challenge in scaling up these models is how to efficiently estimate the labels of these anchors while keeping classification performance.  ...  However, to obtain a high accuracy when a data distribution is complex, the scale of this anchor set still needs to be large, which thus inevitably incurs an expensive computational burden.  ...  The costs thus become impractical for large-scale datasets. Recent works seek to employ anchors to build fast graph-based learning methods [23] , [42] , [47] .  ... 
doi:10.1109/tbdata.2017.2757522 fatcat:g4d54b3sj5h2vbqxbmrvbjnvhu

Integrating Concept Ontology and Multitask Learning to Achieve More Effective Classifier Training for Multilevel Image Annotation

Jianping Fan, Yuli Gao, Hangzai Luo
2008 IEEE Transactions on Image Processing  
In this paper, we have developed a new scheme for achieving multilevel annotations of large-scale images automatically.  ...  In order to assist users on selecting more effective hypotheses for image classifier training, we have developed a novel hyperbolic framework for large-scale image visualization and interactive hypotheses  ...  Schonfeld for handling the review process of this paper.  ... 
doi:10.1109/tip.2008.916999 pmid:18270128 fatcat:bxokhjalpzcfdpwyk3yajzl3ni

Learning Compact Class Codes for Fast Inference in Large Multi Class Classification [chapter]

M. Cissé, T. Artières, Patrick Gallinari
2012 Lecture Notes in Computer Science  
We describe a new approach for classification with a very large number of classes where we assume some class similarity information is available, e.g. through a hierarchical organization.  ...  The proposed method learns a compact binary code using such an existing similarity information defined on classes.  ...  We compare these costs to those of the OVR method which is the most accurate technique for large scale classification [3] (see Table 1 ).  ... 
doi:10.1007/978-3-642-33460-3_38 fatcat:cnrogwiwffbgplcwni2g3emayq

Towards an Effective and Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images [article]

Eduardo Luz, Pedro Lopes Silva, Rodrigo Silva, Ludmila Silva, Gladston Moreira, David Menotti
2020 arXiv   pre-print
Thus, researchers have been looking for alternative screening methods and deep learning applied to chest X-rays of patients has been showing promising results.  ...  We also exploit the underlying taxonomy of the problem with a hierarchical classifier.  ...  For such aim, the models must have a low footprint and low latency, that is, the models must require little memory and perform inference quickly to allow use on embedded devices and large scale, enabling  ... 
arXiv:2004.05717v4 fatcat:qtnt73gkl5b3hpdbyl24yh3gry

Table of contents

2015 IEEE Transactions on Very Large Scale Integration (vlsi) Systems  
Verification, Testing, and Resiliency High-Density RAM/ROM Macros Using CMOS Gate-Array Base Cells: Hierarchical Verification Technique for Reducing Design Cost ........................................  ...  Pradhan 1448 VLSI Circuits for Machine Learning Overcoming Computational Errors in Sensing Platforms Through Embedded Machine-Learning Kernels .............. ...........................................  ... 
doi:10.1109/tvlsi.2015.2450031 fatcat:q3r63kdkkfae5gvkqoozbsatte
« Previous Showing results 1 — 15 out of 52,973 results