danfenghong / IEEE_TGRS_MDL-RS

Danfeng Hong, Lianru Gao, Naoto Yokoya, Jing Yao, Jocelyn Chanussot, Qian Du, Bing Zhang. More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification, IEEE TGRS, 2021, 59(5): 4340-4354.
102 stars 21 forks source link

about LCZ targets #7

Open G-z-w opened 1 year ago

G-z-w commented 1 year ago

您好,请问LCZ数据标签与论文中对不上,实际是怎么处理的呢?

danfenghong commented 1 year ago

哪个标签和哪篇论文?我们自己的论文吗?

G-z-w @.***> 于2023年4月10日周一 16:26写道:

您好,请问LCZ数据标签与论文中对不上,实际是怎么处理的呢?

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TGRS_MDL-RS/issues/7, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZXTJN3XWAUN4PIP5RLXAO7Z5ANCNFSM6AAAAAAWYXNMQA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

G-z-w commented 1 year ago

感谢回复,More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification中标签如下, image ,但是在berlin_GT和HK_GT中有18个标签,berlin和HK分别如下(True表示存在) image image

danfenghong commented 1 year ago

由于两个地区的类别并不是完全覆盖,我们是一个区域训练另一个区域测试,需要找到相同的重叠的类别. 相关类别编号可以参考: http://www.classic.grss-ieee.org/2017-ieee-grss-data-fusion-contest/

G-z-w @.***> 于2023年4月10日周一 21:24写道:

感谢回复,More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification中标签如下, [image: image] https://user-images.githubusercontent.com/95175307/230908349-aeb28b91-2493-4a8c-8acc-3be4c5572695.png ,但是在berlin_GT和HK_GT中有18个标签,berlin和HK分别如下(True表示存在) [image: image] https://user-images.githubusercontent.com/95175307/230909462-83eef3c2-f268-49fc-b985-e25087267017.png [image: image] https://user-images.githubusercontent.com/95175307/230909517-f9ddd27b-d97b-4250-b4d6-af802c0c6dd6.png

— Reply to this email directly, view it on GitHub https://github.com/danfenghong/IEEE_TGRS_MDL-RS/issues/7#issuecomment-1501811991, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFL2GZWU4MDQW23D7GPPVULXAQC2DANCNFSM6AAAAAAWYXNMQA . You are receiving this because you commented.Message ID: @.***>

G-z-w commented 1 year ago

万分感谢!!