|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM286370085 |
| 003 |
DE-627 |
| 005 |
20231225051541.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2020 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2018.2848925
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0954.xml
|
| 035 |
|
|
|a (DE-627)NLM286370085
|
| 035 |
|
|
|a (NLM)29994466
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Opitz, Michael
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Deep Metric Learning with BIER
|b Boosting Independent Embeddings Robustly
|
| 264 |
|
1 |
|c 2020
|
| 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 10.03.2020
|
| 500 |
|
|
|a Date Revised 10.03.2020
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate the task of training this ensemble as an online gradient boosting problem. Each learner receives a reweighted training sample from the previous learners. Further, we propose two loss functions which increase the diversity in our ensemble. These loss functions can be applied either for weight initialization or during training. Together, our contributions leverage large embedding sizes more effectively by significantly reducing correlation of the embedding and consequently increase retrieval accuracy of the embedding. Our method works with any differentiable loss function and does not introduce any additional parameters during test time. We evaluate our metric learning method on image retrieval tasks and show that it improves over state-of-the-art methods on the CUB-200-2011, Cars-196, Stanford Online Products, In-Shop Clothes Retrieval and VehicleID datasets. Therefore, our findings suggest that by dividing deep networks at the end into several smaller and diverse networks, we can significantly reduce overfitting
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Waltner, Georg
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Possegger, Horst
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bischof, Horst
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 42(2020), 2 vom: 22. Feb., Seite 276-290
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:42
|g year:2020
|g number:2
|g day:22
|g month:02
|g pages:276-290
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2018.2848925
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 42
|j 2020
|e 2
|b 22
|c 02
|h 276-290
|