|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM334877377 |
| 003 |
DE-627 |
| 005 |
20250302201011.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2021.3138337
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1116.xml
|
| 035 |
|
|
|a (DE-627)NLM334877377
|
| 035 |
|
|
|a (NLM)34951840
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhu, Yi
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Improving Semantic Segmentation via Efficient Self-Training
|
| 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 Starting from the seminal work of Fully Convolutional Networks (FCN), there has been significant progress on semantic segmentation. However, deep learning models often require large amounts of pixelwise annotations to train accurate and robust models. Given the prohibitively expensive annotation cost of segmentation masks, we introduce a self-training framework in this paper to leverage pseudo labels generated from unlabeled data. In order to handle the data imbalance problem of semantic segmentation, we propose a centroid sampling strategy to uniformly select training samples from every class within each epoch. We also introduce a fast training schedule to alleviate the computational burden. This enables us to explore the usage of large amounts of pseudo labels. Our Centroid Sampling based Self-Training framework (CSST) achieves state-of-the-art results on Cityscapes and CamVid datasets. On PASCAL VOC 2012 test set, our models trained with the original train set even outperform the same models trained on the much bigger augmented train set. This indicates the effectiveness of CSST when there are fewer annotations. We also demonstrate promising few-shot generalization capability from Cityscapes to BDD100K and from Cityscapes to Mapillary datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Zhongyue
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wu, Chongruo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Zhi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a He, Tong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Hang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Manmatha, R
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Mu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Smola, Alexander
|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: 01. März, Seite 1589-1602
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:3
|g day:01
|g month:03
|g pages:1589-1602
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2021.3138337
|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 01
|c 03
|h 1589-1602
|