Cost-sensitive learning of hierarchical tree classifiers for large-scale image classification and novel category detection

Fan, Jianping; Ji, Zhang; Mei, Kuizhi; Peng, Jinye; Gao, Ling

doi:10.1016/j.patcog.2014.10.025

Cited by 44 publications

(22 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even at moderate scale distortion, classification error percentage (CEP) is scarcely ever zero [1], [2], [4]. At maximal scale distortion, CEP rises up to a few percent [12].…”

Section: Related Workmentioning

confidence: 99%

“…In fact, this function is determined at some SDI that is going to be mentioned specifically. Note that only variable r is continuous and nonnegative [12], [16], [20] may turn out to be nonsingle, and this is reflected in (1). As soon as ranges of variables are determined, the 5DLL A will be re-defined bounded above.…”

Section: Criterion Of Optimisationmentioning

confidence: 99%

“…Thus, they are treated as scaled ones regarding the average dimensions. Generally, this is a problem of image recognition [1], [2]. Objects appear closer and farther in front of the cam.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

-The research is focused on optimising two-layer perceptron for generalised scaled object classification problem. The optimisation criterion is minimisation of inaccuracy. The inaccuracy depends on training parameters and hidden layer neuron number. After its statistics is accumulated, minimisation is executed by a numerical search. Perceptron is optimised additionally by extra training. As it is done, the classification error percentage does not exceed 3 % in case of the worst scale distortion.

show abstract

“…Even at moderate scale distortion, classification error percentage (CEP) is scarcely ever zero [1], [2], [4]. At maximal scale distortion, CEP rises up to a few percent [12].…”

Section: Related Workmentioning

confidence: 99%

Section: Criterion Of Optimisationmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

show abstract

“…To solve (16), the Split Bregman Iteration (SBI) is employed. For better measuring subjective image quality, we also employed SSIM [24] to evaluate image quality. In each round of iteration, the reconstructed image is improved with respect to image quality.…”

Section: Optimization Formulation For Csrh Imaging Systemmentioning

confidence: 99%

Advances in Multimedia Information Processing -- PCM 2015

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.Recently no-reference image quality assessment (NR-IQA) methods take advantages of machine learning techniques. However, machine learning approaches need a number of human scored images and cause database dependency. In this paper, we propose a simple NR-IQA method that can estimate quality of distorted images without learning, producing comparable performance to learning based approaches. We employ singular value decomposition (SVD) since we have observed that singular values are commonly affected by various distortions. In detail, a decreasing rate of singular values is highly correlated to a degree of distortions regardless of their type. From the observation, our approach utilizes the decreasing rate of singular values to model a simple and reliable NR-IQA method. Experimental results show that the proposed method has reasonably high correlation to human scores. And the proposed method can secure simplicity and database independence.

show abstract

“…Palacios proposed a genetic fuzzy classifier, which is able to extract fuzzy rules from interval or fuzzy valued data, is extended to this type of classification [9]. Fan proposed a cost-sensitive learning algorithm to train hierarchical tree classifiers for large-scale image classification application [10]. The paper [11] is to examine whether classification cost is affected both by the cost-sensitive approach and by skewed distribution of class.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Cost-Sensitive Fussy Clustering for Uncertain Data Based on the Genetic Algorithm

Huang¹

2015

IJDTA

View full text Add to dashboard Cite

show abstract

Cost-sensitive learning of hierarchical tree classifiers for large-scale image classification and novel category detection

Cited by 44 publications

References 58 publications

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Advances in Multimedia Information Processing -- PCM 2015

Dynamic Cost-Sensitive Fussy Clustering for Uncertain Data Based on the Genetic Algorithm

Contact Info

Product

Resources

About