About OSDA setting on office-31
zzzzzzzzzzzx opened this issue · comments
Hi, i read your code and paper. In the paper, you show the results HM (%) on Office under the OSDA scenario (ResNet-50). However, in the code, the class setting of Office is inconsistent with the previous method such as STA and ROS. In the previous method, the setting of office-31 is 10 known classes and 11 unknown classes. However, in the code, the unknown classes is the left 21 classes. Could u please explain it? Thanks!
Thanks for pointing out this mistake, we indeed report the results under the wrong setting, also a more challenging setting.
I have run the code under the 21-class setting and our method could achieve better results, I will update the new results recently.
However, fortunately, this will not influence the conclusion in the main paper.
: ) Excellent jobs !