|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM313260427 |
003 |
DE-627 |
005 |
20231225150209.0 |
007 |
cr uuu---uuuuu |
008 |
231225s2023 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TPAMI.2020.3007032
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1044.xml
|
035 |
|
|
|a (DE-627)NLM313260427
|
035 |
|
|
|a (NLM)32750802
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Huang, Zilong
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a CCNet
|b Criss-Cross Attention for Semantic Segmentation
|
264 |
|
1 |
|c 2023
|
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 07.05.2023
|
500 |
|
|
|a Date Revised 07.05.2023
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a criss-cross network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11× less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85 percent of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9, 45.76 and 55.47 percent on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at https://github.com/speedinghzl/CCNethttps://github.com/speedinghzl/CCNet
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Wang, Xinggang
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Wei, Yunchao
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Huang, Lichao
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Shi, Humphrey
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Liu, Wenyu
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Huang, Thomas S
|e verfasserin
|4 aut
|
773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 6 vom: 30. Juni, Seite 6896-6908
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:6
|g day:30
|g month:06
|g pages:6896-6908
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2020.3007032
|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 45
|j 2023
|e 6
|b 30
|c 06
|h 6896-6908
|