|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM258263865 |
| 003 |
DE-627 |
| 005 |
20231224184627.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2017 xx |||||o 00| ||eng c |
| 028 |
5 |
2 |
|a pubmed24n0860.xml
|
| 035 |
|
|
|a (DE-627)NLM258263865
|
| 035 |
|
|
|a (NLM)26960219
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Premachandran, Vittal
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Empirical Minimum Bayes Risk Prediction
|
| 264 |
|
1 |
|c 2017
|
| 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 Completed 06.08.2018
|
| 500 |
|
|
|a Date Revised 06.08.2018
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a When building vision systems that predict structured objects such as image segmentations or human poses, a crucial concern is performance under task-specific evaluation measures (e.g., Jaccard Index or Average Precision). An ongoing research challenge is to optimize predictions so as to maximize performance on such complex measures. In this work, we present a simple meta-algorithm that is surprisingly effective - Empirical Min Bayes Risk. EMBR takes as input a pre-trained model that would normally be the final product and learns three additional parameters so as to optimize performance on the complex instance-level high-order task-specific measure. We demonstrate EMBR in several domains, taking existing state-of-the-art algorithms and improving performance up to 8 percent, simply by learning three extra parameters. Our code is publicly available and the results presented in this paper can be replicated from our code-release
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, U.S. Gov't, Non-P.H.S.
|
| 700 |
1 |
|
|a Tarlow, Daniel
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yuille, Alan L
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Batra, Dhruv
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 39(2017), 1 vom: 11. Jan., Seite 75-86
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:39
|g year:2017
|g number:1
|g day:11
|g month:01
|g pages:75-86
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 39
|j 2017
|e 1
|b 11
|c 01
|h 75-86
|