Probabilistic Label Trees for Efficient Large Scale Image Classification

被引：61

作者：

Liu, Baoyuan ^{[1
]}

Sadeghi, Fereshteh ^{[1
]}

Tappen, Marshall ^{[1
]}

Shamir, Ohad ^{[2
]}

Liu, Ce ^{[2
]}

机构：

[1] Univ Cent Florida, Orlando, FL 32816 USA

[2] Microsoft Res, Boston, NE USA

来源：

2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2013年

关键词：

D O I：

10.1109/CVPR.2013.114

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Large-scale recognition problems with thousands of classes pose a particular challenge because applying the classifier requires more computation as the number of classes grows. The label tree model integrates classification with the traversal of the tree so that complexity grows logarithmically. In this paper we show how the parameters of the label tree can be found using maximum likelihood estimation. This new probabilistic learning technique produces a label tree with significantly improved recognition accuracy.

引用

页码：843 / 850

页数：8

共 50 条

[1] Learning Balanced Trees for Large Scale Image Classification
Tien-Dung Mai
Thanh Duc Ngo
Duy-Dinh Le
Duc Anh Duong
Hoang, Kiem
Satoh, Shin'ichi
IMAGE ANALYSIS AND PROCESSING - ICIAP 2015, PT II, 2015, 9280 : 3 - 13
[2] Efficient large-scale multi-class image classification by learning balanced trees
Tien-Dung Mai
Thanh Duc Ngo
Duy-Dinh Le
Duc Anh Duong
Kiem Hoang
Satoh, Shin'ichi
COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 156 : 151 - 161
[3] Multi-label Image Classification with A Probabilistic Label Enhancement Model
Li, Xin
Zhao, Feipeng
Guo, Yuhong
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2014, : 430 - 439
[4] Belief Theory for Large-Scale Multi-label Image Classification
Znaidia, Amel
Le Borgne, Herve
Hudelot, Celine
BELIEF FUNCTIONS: THEORY AND APPLICATIONS, 2012, 164 : 205 - 212
[5] Efficient Large Scale Image Classification via Prediction Score Decomposition
Duy-Dinh Le
Tien-Dung Mai
Satoh, Shin'ichi
Thanh Duc Ngo
Duc Anh Duong
COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 : 770 - 785
[6] Correlated Input-Dependent Label Noise in Large-Scale Image Classification
Collier, Mark
Mustafa, Basil
Kokiopoulou, Efi
Jenatton, Rodolphe
Berent, Jesse
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 1551 - 1560
[7] Online probabilistic label trees
Jasinska-Kobus, Kalina
Wydmuch, Marek
Thiruvenkatachari, Devanathan
Dembczynski, Krzysztof
24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
[8] Label Filters for Large Scale Multilabel Classification
Niculescu-Mizil, Alexandru
Abbasnejad, Ehsan
ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54, 2017, 54 : 1448 - 1457
[9] Hierarchical Label Partitioning for Large Scale Classification
Puget, Raphael
Baskiotis, Nicolas
PROCEEDINGS OF THE 2015 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (IEEE DSAA 2015), 2015, : 103 - 112
[10] Classification of Image on a large scale with the SVM
Thanh-Nghi Doan
Thanh-Nghi Do
Poulet, Francois
TRAITEMENT DU SIGNAL, 2014, 31 (1-2) : 39 - 56

← 1 2 3 4 5 →