|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM254134734 |
| 003 |
DE-627 |
| 005 |
20231224171725.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2016 xx |||||o 00| ||eng c |
| 028 |
5 |
2 |
|a pubmed24n0847.xml
|
| 035 |
|
|
|a (DE-627)NLM254134734
|
| 035 |
|
|
|a (NLM)26513778
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wei, Yunchao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a HCP
|b A Flexible CNN Framework for Multi-label Image Classification
|
| 264 |
|
1 |
|c 2016
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 20.11.2019
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground-truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) the shared CNN is flexible and can be well pre-trained with a large-scale single-label image dataset, e.g., ImageNet; and 4) it may naturally output multi-label prediction results. Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 90.5% by HCP only and 93.2% after the fusion with our complementary result in [44] based on hand-crafted features on the VOC 2012 dataset
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Xia, Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lin, Min
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Huang, Junshi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ni, Bingbing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Dong, Jian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhao, Yao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yan, Shuicheng
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 38(2016), 9 vom: 01. Sept., Seite 1901-1907
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:38
|g year:2016
|g number:9
|g day:01
|g month:09
|g pages:1901-1907
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 38
|j 2016
|e 9
|b 01
|c 09
|h 1901-1907
|