Presentation | 2012-09-03 Simultaneous training of multi-class object detectors via large scale image dataset introduction of target specific negative classes Asako KANEZAKI, Sho INABA, Yoshitaka USHIKU, Yuya YAMASHITA, Hiroshi MURAOKA, Tatsuya HARADA, Yasuo KUNIYOSHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose an efficient method to train multiple object detectors simultaneously using a large-scale image dataset. The one-vs-all approach that optimizes the boundary between positive samples from a target class and negative samples from the others has been the most standard approach for object detection. However, because this approach trains each object detector independently, the likelihoods are not balanced between object classes. The proposed method combines ideas derived from both detection and classification in order to balance the scores across all object classes. We optimized the boundary between target classes and their hard-negative samples, just as in detection, while simultaneously balancing the detector likelihoods across object classes, as done in multi-class classification. We evaluated the performances on multi-class object detection using a subset of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2011 dataset and showed our method outperformed a de facto standard method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | object detection / multiclass classification / large-scale image dataset / online learning |
Paper # | PRMU2012-42,IBISML2012-25 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2012/8/26(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Simultaneous training of multi-class object detectors via large scale image dataset introduction of target specific negative classes |
Sub Title (in English) | |
Keyword(1) | object detection |
Keyword(2) | multiclass classification |
Keyword(3) | large-scale image dataset |
Keyword(4) | online learning |
1st Author's Name | Asako KANEZAKI |
1st Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo() |
2nd Author's Name | Sho INABA |
2nd Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo |
3rd Author's Name | Yoshitaka USHIKU |
3rd Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo |
4th Author's Name | Yuya YAMASHITA |
4th Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo |
5th Author's Name | Hiroshi MURAOKA |
5th Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo |
6th Author's Name | Tatsuya HARADA |
6th Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo/JST PRESTO |
7th Author's Name | Yasuo KUNIYOSHI |
7th Author's Affiliation | Graduate School of Information Science and Technology The University of Tokyo |
Date | 2012-09-03 |
Paper # | PRMU2012-42,IBISML2012-25 |
Volume (vol) | vol.112 |
Number (no) | 197 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |