|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM338290168 |
| 003 |
DE-627 |
| 005 |
20240207231944.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3160362
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1283.xml
|
| 035 |
|
|
|a (DE-627)NLM338290168
|
| 035 |
|
|
|a (NLM)35298376
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Ye, Han-Jia
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Few-Shot Learning With a Strong Teacher
|
| 264 |
|
1 |
|c 2024
|
| 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 07.02.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner (a meta-model) that can learn from few-shot examples to generate a classifier. Typically, the few-shot learner is constructed or meta-trained by sampling multiple few-shot tasks in turn and optimizing the few-shot learner's performance in generating classifiers for those tasks. The performance is measured by how well the resulting classifiers classify the test (i.e., query) examples of those tasks. In this paper, we point out two potential weaknesses of this approach. First, the sampled query examples may not provide sufficient supervision for meta-training the few-shot learner. Second, the effectiveness of meta-learning diminishes sharply with the increasing number of shots (i.e., the number of training examples per class). To resolve these issues, we propose a novel meta-training objective for the few-shot learner, which is to encourage the few-shot learner to generate classifiers that perform like strong classifiers. Concretely, we associate each sampled few-shot task with a strong classifier, which is trained with ample labeled examples. The strong classifiers can be seen as the target classifiers that we hope the few-shot learner to generate given few-shot examples, and we use the strong classifiers to supervise the few-shot learner. We present an efficient way to construct the strong classifier, making our proposed objective an easily plug-and-play term to existing meta-learning based FSL methods. We validate our approach, (Learning with A Strong Teacher for few-SHOT learning), in combinations with many representative meta-learning methods. On several benchmark datasets including miniImageNet and tieredImageNet, our approach leads to a notable improvement across a variety of tasks. More importantly, with our approach, meta-learning based FSL methods can consistently outperform non-meta-learning based methods at different numbers of shots, even in many-shot settings, greatly strengthening their applicability
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Ming, Lu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhan, De-Chuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chao, Wei-Lun
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 3 vom: 02. Feb., Seite 1425-1440
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:3
|g day:02
|g month:02
|g pages:1425-1440
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3160362
|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 46
|j 2024
|e 3
|b 02
|c 02
|h 1425-1440
|